diff --git a/.github/workflows/rhel-8.yml b/.github/workflows/rhel-8.yml index 8eae9b9371..86eee5aa9e 100644 --- a/.github/workflows/rhel-8.yml +++ b/.github/workflows/rhel-8.yml @@ -39,7 +39,7 @@ jobs: - name: Install Python prereqs run: | python3.9 -m pip install -r requirements.txt - python3.9 -m pip install pyinstaller pytest pytest-cov mock + python3.9 -m pip install pyinstaller pytest pytest-cov mock pytest-xdist - name: Configure and install run: | mkdir build diff --git a/.github/workflows/ubuntu-focal.yml b/.github/workflows/ubuntu-focal.yml index d72aaad70f..2b6534d437 100644 --- a/.github/workflows/ubuntu-focal.yml +++ b/.github/workflows/ubuntu-focal.yml @@ -35,7 +35,7 @@ jobs: - name: Install Python prereqs run: | python3 -m pip install -r requirements.txt - python3 -m pip install pyinstaller pytest pytest-cov mock + python3 -m pip install pyinstaller pytest pytest-cov mock pytest-xdist - name: Configure and install run: | mkdir build diff --git a/tests/test_analyze_workloads.py b/tests/test_analyze_workloads.py index eed1b5136b..bea44c88d7 100644 --- a/tests/test_analyze_workloads.py +++ b/tests/test_analyze_workloads.py @@ -21,57 +21,27 @@ omniperf = SourceFileLoader("omniperf", "src/omniperf").load_module() ################################################## -def test_device_inv_int_MI100(): +def test_analyze_ipblocks_SQ_TA_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/device_inv_int/MI100"], + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_TA/MI100"], ): omniperf.main() assert e.value.code == 0 -def test_dispatch_0_1_MI100(): +def test_analyze_ipblocks_SQ_TA_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0_1/MI100"], + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_TA/MI200"], ): omniperf.main() assert e.value.code == 0 -def test_dispatch_0_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_dispatch_2_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_2/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_dispatch_6_8_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_6_8/MI100"], - ): - omniperf.main() - assert e.value.code == 1 - - -def test_dispatch_7_MI100(): +def test_analyze_dispatch_7_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", @@ -81,27 +51,72 @@ def test_dispatch_7_MI100(): assert e.value.code == 1 -def test_dispatch_invalid_MI100(): +def test_analyze_dispatch_7_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/dispatch_invalid/MI100"], + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_7/MI200"], + ): + omniperf.main() + assert e.value.code == 1 + + +def test_analyze_kernel_substr_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/kernel_substr/MI100"], ): omniperf.main() assert e.value.code == 0 -def test_ipblocks_CPC_MI100(): +def test_analyze_kernel_substr_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPC/MI100"], + ["omniperf", "analyze", "--path", "tests/workloads/kernel_substr/MI200"], ): omniperf.main() assert e.value.code == 0 -def test_ipblocks_CPF_MI100(): +def test_analyze_dispatch_6_8_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_6_8/MI100"], + ): + omniperf.main() + assert e.value.code == 1 + + +def test_analyze_dispatch_6_8_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_6_8/MI200"], + ): + omniperf.main() + assert e.value.code == 1 + + +def test_analyze_mem_levels_L2_vL1d_LDS_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + [ + "omniperf", + "analyze", + "--path", + "tests/workloads/mem_levels_L2_vL1d_LDS/MI200", + ], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_CPF_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", @@ -111,47 +126,17 @@ def test_ipblocks_CPF_MI100(): assert e.value.code == 0 -def test_ipblocks_SPI_MI100(): +def test_analyze_ipblocks_CPF_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SPI/MI100"], + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPF/MI200"], ): omniperf.main() assert e.value.code == 0 -def test_ipblocks_SQC_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQC/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_ipblocks_SQ_CPC_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_CPC/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_ipblocks_SQ_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_ipblocks_SQ_SPI_MI100(): +def test_analyze_ipblocks_SQ_SPI_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", @@ -161,7 +146,358 @@ def test_ipblocks_SQ_SPI_MI100(): assert e.value.code == 0 -def test_ipblocks_SQ_SPI_TA_TCC_CPF_MI100(): +def test_analyze_ipblocks_SQ_SPI_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_SPI/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SQ_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SQ_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_no_roof_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/no_roof/MI100"] + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_no_roof_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/no_roof/MI200"] + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_join_type_grid_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/join_type_grid/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_join_type_grid_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/join_type_grid/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SQC_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQC/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SQC_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQC/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_TCP_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCP/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_TCP_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCP/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_TA_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TA/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_TA_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TA/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_TCC_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCC/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_TCC_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCC/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_TD_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TD/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_TD_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TD/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_dispatch_0_1_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0_1/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_dispatch_0_1_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0_1/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_dispatch_inv_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_inv/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_dispatch_inv_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_inv/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_device_inv_int_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/device_inv_int/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_device_inv_int_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/device_inv_int/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_mem_levels_HBM_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_HBM/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_mem_levels_L2_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_L2/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_device_filter_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/device_filter/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_device_filter_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/device_filter/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SPI_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SPI/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SPI_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SPI/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_mem_levels_vL1d_LDS_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + [ + "omniperf", + "analyze", + "--path", + "tests/workloads/mem_levels_vL1d_LDS/MI200", + ], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_mem_levels_vL1D_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_vL1D/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_kernel_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/kernel/MI100"] + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_kernel_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/kernel/MI200"] + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_join_type_kernel_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/join_type_kernel/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_join_type_kernel_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/join_type_kernel/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SQ_SPI_TA_TCC_CPF_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", @@ -176,7 +512,82 @@ def test_ipblocks_SQ_SPI_TA_TCC_CPF_MI100(): assert e.value.code == 0 -def test_ipblocks_SQ_SQC_TCP_CPC_MI100(): +def test_analyze_ipblocks_SQ_SPI_TA_TCC_CPF_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + [ + "omniperf", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200", + ], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_kernel_inv_str_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_str/MI100"], + ): + omniperf.main() + assert e.value.code == 1 + + +def test_analyze_kernel_inv_str_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_str/MI200"], + ): + omniperf.main() + assert e.value.code == 1 + + +def test_analyze_kernel_inv_int_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_int/MI100"], + ): + omniperf.main() + assert e.value.code == 1 + + +def test_analyze_kernel_inv_int_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_int/MI200"], + ): + omniperf.main() + assert e.value.code == 1 + + +def test_analyze_mem_levels_HBM_LDS_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_HBM_LDS/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_sort_dispatches_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/sort_dispatches/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SQ_SQC_TCP_CPC_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", @@ -191,188 +602,144 @@ def test_ipblocks_SQ_SQC_TCP_CPC_MI100(): assert e.value.code == 0 -def test_ipblocks_SQ_TA_MI100(): +def test_analyze_ipblocks_SQ_SQC_TCP_CPC_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_TA/MI100"], + [ + "omniperf", + "analyze", + "--path", + "tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200", + ], ): omniperf.main() assert e.value.code == 0 -def test_ipblocks_TA_MI100(): +def test_analyze_kernel_names_MI200(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TA/MI100"], + ["omniperf", "analyze", "--path", "tests/workloads/kernel_names/MI200"], ): omniperf.main() assert e.value.code == 0 -def test_ipblocks_TCC_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCC/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_ipblocks_TCP_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TCP/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_ipblocks_TD_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_TD/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_join_type_grid_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/join_type_grid/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_join_type_kernel_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/join_type_kernel/MI100"], - ): - omniperf.main() - - -def test_kernel_inv_int_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_int/MI100"], - ): - omniperf.main() - assert e.value.code == 1 - - -def test_kernel_inv_str_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_inv_str/MI100"], - ): - omniperf.main() - assert e.value.code == 1 - - -def test_kernel_substr_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_substr/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_kernel_summaries_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_summaries/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_kernel_verbose_0_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_verbose_0/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_kernel_verbose_1_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_verbose_1/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_kernel_verbose_2_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_verbose_2/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_kernel_verbose_3_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_verbose_3/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_kernel_verbose_4_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_verbose_4/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_kernel_verbose_5_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", - ["omniperf", "analyze", "--path", "tests/workloads/kernel_verbose_5/MI100"], - ): - omniperf.main() - assert e.value.code == 0 - - -def test_no_roof_MI100(): - with pytest.raises(SystemExit) as e: - with patch( - "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/no_roof/MI100"] - ): - omniperf.main() - assert e.value.code == 0 - - -def test_path_MI100(): +def test_analyze_path_MI100(): with pytest.raises(SystemExit) as e: with patch( "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/path/MI100"] ): omniperf.main() assert e.value.code == 0 + + +def test_analyze_path_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", ["omniperf", "analyze", "--path", "tests/workloads/path/MI200"] + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_sort_kernels_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/sort_kernels/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_dispatch_0_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_dispatch_0_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_0/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SQ_CPC_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_CPC/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_SQ_CPC_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_SQ_CPC/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_dispatch_2_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_2/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_dispatch_2_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/dispatch_2/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_CPC_MI100(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPC/MI100"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_ipblocks_CPC_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/ipblocks_CPC/MI200"], + ): + omniperf.main() + assert e.value.code == 0 + + +def test_analyze_mem_levels_LDS_MI200(): + with pytest.raises(SystemExit) as e: + with patch( + "sys.argv", + ["omniperf", "analyze", "--path", "tests/workloads/mem_levels_LDS/MI200"], + ): + omniperf.main() + assert e.value.code == 0 diff --git a/tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv index 5dfa84e3bc..17d5b91b30 100644 --- a/tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,48069,48069,16384,65536,12763,1638700,194272922419343,194285066464535,194285066489175,194272930391948 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,43546,43546,16384,65536,8369,1048580,194272930413559,194285066682455,194285066701335,194272930732383 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,171832,171832,1048576,256,0,0,8,8,16,64,0x0,0x7f261105ce80,43715,43715,16384,65536,8176,1048580,194272930764153,194285066722455,194285066741335,194272930942791 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1267481,1267481,1048576,256,0,0,8,8,16,64,0x0,0x7f0eb8168ec0,120424,120424,16384,65536,13369,1717376,1410193234401133,1410204895308401,1410204895332881,1410193242172960 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1267481,1267481,1048576,256,0,0,8,8,16,64,0x0,0x7f0eb8168ec0,46836,46836,16384,65536,8058,1048584,1410193242195944,1410204895428561,1410204895447761,1410193242512571 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1267481,1267481,1048576,256,0,0,8,8,16,64,0x0,0x7f0eb8168ec0,43828,43828,16384,65536,7998,1048588,1410193242544701,1410204895469361,1410204895488081,1410193242740050 diff --git a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv index d912fc3108..32a0f5b2d9 100644 --- a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273420605668,194285066464535,194285066489175,194273428330044 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273428350383,194285066682455,194285066701335,194273428660279 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172017,172017,1048576,256,0,0,8,8,16,64,0x0,0x7ff6bfca6e80,0,0,0,194273428688593,194285066722455,194285066741335,194273428860549 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1267667,1267667,1048576,256,0,0,8,8,16,64,0x0,0x7f9eef0c0ec0,0,0,0,1410193715977501,1410204895308401,1410204895332881,1410193723553168 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1267667,1267667,1048576,256,0,0,8,8,16,64,0x0,0x7f9eef0c0ec0,0,0,0,1410193723574359,1410204895428561,1410204895447761,1410193723871880 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1267667,1267667,1048576,256,0,0,8,8,16,64,0x0,0x7f9eef0c0ec0,0,0,0,1410193723900664,1410204895469361,1410204895488081,1410193724075433 diff --git a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv index 714649e733..7339590e5b 100644 --- a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,198372,25466512,194273910775706,194285066464535,194285066489175,194273918668841 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,178410,22861520,194273918687927,194285066682455,194285066701335,194273919011510 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172202,172202,1048576,256,0,0,8,8,16,64,0x0,0x7f80dbc10e80,65536,178762,22853312,194273919039884,194285066722455,194285066741335,194273919232939 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1267850,1267850,1048576,256,0,0,8,8,16,64,0x0,0x7f29fc24cec0,65536,217080,27847144,1410194196106960,1410204895308401,1410204895332881,1410194203543485 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1267850,1267850,1048576,256,0,0,8,8,16,64,0x0,0x7f29fc24cec0,65536,201340,25741952,1410194203562862,1410204895428561,1410204895447761,1410194203889688 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1267850,1267850,1048576,256,0,0,8,8,16,64,0x0,0x7f29fc24cec0,65536,200810,25639968,1410194203918102,1410204895469361,1410204895488081,1410194204085558 diff --git a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv index 5f0f862060..8abd5f32e9 100644 --- a/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,645046,82562784,194274390775457,194285066464535,194285066489175,194274398576077 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,656009,83967432,194274398595203,194285066682455,194285066701335,194274398895572 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172388,172388,1048576,256,0,0,8,8,16,64,0x0,0x7f91b7fd6e80,32768,654851,83819532,194274398924006,194285066722455,194285066741335,194274399099017 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1268033,1268033,1048576,256,0,0,8,8,16,64,0x0,0x7fedffc74ec0,32768,609944,78081400,1410194670380245,1410204895308401,1410204895332881,1410194678086308 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1268033,1268033,1048576,256,0,0,8,8,16,64,0x0,0x7fedffc74ec0,32768,673533,86217068,1410194678107769,1410204895428561,1410204895447761,1410194678459913 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1268033,1268033,1048576,256,0,0,8,8,16,64,0x0,0x7fedffc74ec0,32768,625490,80060980,1410194678486053,1410204895469361,1410204895488081,1410194678661503 diff --git a/tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv index fe78976967..53a68bfbd5 100644 --- a/tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,48374,48374,16676,387000,16384,25449189,235661,0,102288864,194274879224637,194285066464535,194285066489175,194274887852072 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,42333,42333,13500,338672,16384,24694478,228632,0,99275804,194274887882279,194285066682455,194285066701335,194274888171918 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,172574,172574,1048576,256,0,0,8,8,16,64,0x0,0x7f63ef9aae80,42877,42877,13541,343024,16384,24621688,230950,0,98996648,194274888210190,194285066722455,194285066741335,194274888401232 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1268218,1268218,1048576,256,0,0,8,8,16,64,0x0,0x7fa94f5d4ec0,48952,48952,18068,391624,16384,25128672,238750,0,101043548,1410195147235800,1410204895308401,1410204895332881,1410195154883924 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1268218,1268218,1048576,256,0,0,8,8,16,64,0x0,0x7fa94f5d4ec0,42936,42936,13804,343496,16384,24583226,234692,0,98863936,1410195154913951,1410204895428561,1410204895447761,1410195155354471 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1268218,1268218,1048576,256,0,0,8,8,16,64,0x0,0x7fa94f5d4ec0,42192,42192,13020,337544,16384,24104198,233666,0,96939712,1410195155392643,1410204895469361,1410204895488081,1410195155592380 diff --git a/tests/workloads/device_filter/MI100/log.txt b/tests/workloads/device_filter/MI100/log.txt new file mode 100644 index 0000000000..e01c4094be --- /dev/null +++ b/tests/workloads/device_filter/MI100/log.txt @@ -0,0 +1,679 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/device_filter/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155419' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155419_1267321' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155419_1267321/input0_results_240321_155419' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155419_1267321/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155419_1267321/input0_results_240321_155419 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155419' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155419_1267507' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155419_1267507/input0_results_240321_155419' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155419_1267507/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155419_1267507/input0_results_240321_155419 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155420' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155420_1267690' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155420_1267690/input0_results_240321_155420' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155420_1267690/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155420_1267690/input0_results_240321_155420 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155420' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155420_1267873' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155420_1267873/input0_results_240321_155420' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155420_1267873/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155420_1267873/input0_results_240321_155420 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155421' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155421_1268058' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155421_1268058/input0_results_240321_155421' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155421_1268058/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155421_1268058/input0_results_240321_155421 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155421' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155421_1268241' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155421_1268241/input0_results_240321_155421' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155421_1268241/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155421_1268241/input0_results_240321_155421 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155422' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155422_1268424' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155422_1268424/input0_results_240321_155422' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155422_1268424/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155422_1268424/input0_results_240321_155422 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155422' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155422_1268607' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155422_1268607/input0_results_240321_155422' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155422_1268607/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155422_1268607/input0_results_240321_155422 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155423' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155423_1268793' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155423_1268793/input0_results_240321_155423' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155423_1268793/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155423_1268793/input0_results_240321_155423 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155423' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155423_1268978' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155423_1268978/input0_results_240321_155423' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155423_1268978/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155423_1268978/input0_results_240321_155423 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155424' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155424_1269161' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155424_1269161/input0_results_240321_155424' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155424_1269161/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155424_1269161/input0_results_240321_155424 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155425' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155425_1269348' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155425_1269348/input0_results_240321_155425' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155425_1269348/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155425_1269348/input0_results_240321_155425 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155425' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155425_1269531' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155425_1269531/input0_results_240321_155425' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155425_1269531/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155425_1269531/input0_results_240321_155425 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155426' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155426_1269719' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155426_1269719/input0_results_240321_155426' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155426_1269719/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155426_1269719/input0_results_240321_155426 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155427' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155427_1269903' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155427_1269903/input0_results_240321_155427' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155427_1269903/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155427_1269903/input0_results_240321_155427 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155427' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155427_1270091' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155427_1270091/input0_results_240321_155427' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155427_1270091/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155427_1270091/input0_results_240321_155427 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155428' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155428_1270276' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155428_1270276/input0_results_240321_155428' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155428_1270276/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155428_1270276/input0_results_240321_155428 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155428' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155428_1270459' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155428_1270459/input0_results_240321_155428' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155428_1270459/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155428_1270459/input0_results_240321_155428 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155428' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155428_1270642' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155428_1270642/input0_results_240321_155428' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155428_1270642/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155428_1270642/input0_results_240321_155428 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155429' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155429_1270830' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155429_1270830/input0_results_240321_155429' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155429_1270830/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155429_1270830/input0_results_240321_155429 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155429' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155429_1271014' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155429_1271014/input0_results_240321_155429' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155429_1271014/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155429_1271014/input0_results_240321_155429 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155430' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155430_1271202' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155430_1271202/input0_results_240321_155430' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155430_1271202/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155430_1271202/input0_results_240321_155430 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155430' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155430_1271386' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155430_1271386/input0_results_240321_155430' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155430_1271386/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155430_1271386/input0_results_240321_155430 + |-> [rocprof] File 'tests/workloads/device_filter/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/kernel_verbose_0/MI100/pmc_dispatch_info.csv b/tests/workloads/device_filter/MI100/pmc_dispatch_info.csv similarity index 100% rename from tests/workloads/kernel_verbose_0/MI100/pmc_dispatch_info.csv rename to tests/workloads/device_filter/MI100/pmc_dispatch_info.csv diff --git a/tests/workloads/device_filter/MI100/pmc_perf.csv b/tests/workloads/device_filter/MI100/pmc_perf.csv index 686bbd8b36..4ebc984e2e 100644 --- a/tests/workloads/device_filter/MI100/pmc_perf.csv +++ b/tests/workloads/device_filter/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_4,obj_4,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_6,obj_6,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_7,obj_7,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_8,obj_8,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_9,obj_9,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_10,obj_10,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_11,obj_11,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_12,obj_12,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_15,obj_15,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_16,obj_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fde441d4e80,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,0,49511,0,0,64,0x7f3e60c9ce80,4096,0,453,0,4096,0,0,0,4099,0,908,0,4096,0,1984,0,4096,0,1437,0,4096,0,5277,0,4144,0,109,0,4096,0,2814,0,4096,0,39,0,4096,0,320,0,4144,0,718,0,4221,0,6748,0,4096,0,0,0,4096,0,363,0,4096,0,1005,0,4096,0,2756,0,4096,0,1901,0,4096,0,7287,0,4096,0,2210,0,4096,0,1396,0,4096,0,82,0,4096,0,2754,0,4096,0,2030,0,4096,0,0,0,4096,0,0,0,4096,0,1252,0,4216,0,1075,0,4096,0,519,0,4096,0,0,0,4097,0,0,0,4096,0,4,0,4096,0,2134,0,64,0x7fe4f1e68e80,4244,0,0,1981534,2935,0,0,1915945,6476,0,0,2194672,1496,0,0,1810650,773,0,0,1656548,3877,0,0,2039141,1667,0,0,1818115,3418,0,0,1978226,1674,0,0,1761786,3443,0,0,1997252,4503,0,0,2076072,2624,0,0,1864141,2435,0,0,1883999,2427,0,0,1893825,2845,0,0,1868957,2662,0,0,1994085,3963,0,0,1987695,927,0,0,1650137,3746,0,0,1940536,1848,0,0,1864568,2467,0,0,1931672,3663,0,0,2002468,2027,0,0,1796257,2969,0,0,2007956,1753,0,0,1772645,932,0,0,1700905,2090,0,0,1857306,3957,0,0,1980981,1934,0,0,1711472,4658,0,0,2137910,5217,0,0,2098477,1353,0,0,1725857,64,0x7f32df54ce80,0,3592917,4096,4096,0,4430480,4096,4096,0,3199046,4096,4096,0,3658465,4096,4096,0,3671226,4096,4096,0,3925206,4096,4096,0,3772613,4096,4096,0,3982183,4096,4096,0,4035872,4096,4096,0,4135655,4096,4096,0,4638037,4096,4096,0,5053819,4096,4096,0,4269725,4096,4096,0,4446952,4096,4096,0,3268689,4096,4096,0,3934704,4096,4096,0,3519363,4096,4096,0,4842876,4096,4096,0,3475510,4096,4096,0,3847119,4096,4096,0,3944591,4096,4096,0,3556276,4096,4096,0,3878967,4096,4096,0,2942631,4096,4096,0,3391567,4096,4096,0,4281734,4096,4096,0,3812897,4096,4096,0,3039482,4096,4096,0,3695822,4096,4096,0,3897657,4096,4096,0,4030661,4096,4096,0,3898185,4096,4096,64,0x7f2b358f0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46952,0,131533.0,131072.0,0.0,131104.0,64,0x7f52539fae80,381872,230810,3375249,16384,25068515,144,48,0,47733,47733,3815066.0,3002055.0,6762.0,737874.0,2091981.0,0.0,2993208.0,2681308.0,380159,240748,47733,0,47733,0,1527456.0,947059.0,0.0,0.0,64,0x7f956bba8e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131292.0,0.0,432.0,131291.0,64,0x7f44161ece80,1807606,360448,163840,0,0,180224,114688,0,71907270.0,197035886.0,76549948.0,131072.0,0.0,588330.0,0,0,26287,71046.0,0.0,0.0,71046.0,64,0x7fa4391cce80,32768,0,0,0,16384,16384,393216,23605514,960.0,513937.0,0.0,524288.0,965398.0,32768.0,0,0,0,15914,131072.0,131072.0,0.0,131072.0,64,0x7feded874e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdc4fd40e80,0,8192,4096,8192,0,8240,4144,8240,141,8319,4364,8460,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7feb2fd38e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,44679.0,116229.0,64,0x7faffaee2e80,0,0,192,0,65536,64469,48,1347,32092,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48072,1718,0,48.0,316.0,0.0,262288.0,64,0x7f982e7dce80,0.0,64,0x7ff858716e80,131072.0,131072.0,0.0,2551695.0,0.0,0.0,129760322.0,61651014.0,64,0x7f4b37d50e80,190372,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13555,29939,9879,550,0,46722,262648.0,0.0,188.0,262460.0,64,0x7f1f51b16e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86606.0,44466.0,131111.0,0.0,194285066464535,194285066489175 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fde441d4e80,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,0,44152,0,0,64,0x7f3e60c9ce80,4096,0,1212,0,4098,0,0,0,4096,0,1633,0,4096,0,1163,0,4096,0,1422,0,4097,0,805,0,4144,0,166,0,4096,0,2379,0,4096,0,1508,0,4096,0,2819,0,4144,0,6281,0,4217,0,5813,0,4096,0,424,0,4096,0,2156,0,4096,0,5119,0,4096,0,1399,0,4096,0,2260,0,4096,0,3382,0,4096,0,7487,0,4096,0,1729,0,4096,0,1724,0,4096,0,2043,0,4096,0,1342,0,4097,0,0,0,4096,0,322,0,4096,0,4802,0,4216,0,42,0,4096,0,180,0,4096,0,0,0,4097,0,1958,0,4096,0,184,0,4096,0,3918,0,64,0x7fe4f1e68e80,3219,0,0,1562312,731,0,0,1285276,2423,0,0,1538043,1536,0,0,1405284,1684,0,0,1543199,1748,0,0,1404916,3554,0,0,1680074,2221,0,0,1586501,1093,0,0,1325850,1472,0,0,1398736,3112,0,0,1632394,1228,0,0,1380641,2389,0,0,1460729,3115,0,0,1628789,1555,0,0,1374840,3935,0,0,1709254,2255,0,0,1465568,834,0,0,1344720,4213,0,0,1671870,1297,0,0,1420662,2362,0,0,1525225,1424,0,0,1408994,3211,0,0,1639511,2683,0,0,1647393,1365,0,0,1322748,1782,0,0,1420327,2550,0,0,1557342,5391,0,0,1727912,1442,0,0,1421847,2240,0,0,1541356,4576,0,0,1735518,1507,0,0,1459347,64,0x7f32df54ce80,0,5658087,2748,2748,0,3619563,2714,2714,0,2418594,2712,2712,0,2572533,2697,2697,0,2843853,2716,2716,0,2984112,2712,2712,0,2359649,2712,2712,0,2871855,2710,2710,0,3014279,2730,2730,0,4360044,2684,2684,0,2709665,2724,2724,0,4494899,2734,2734,0,2432485,2712,2712,0,3153878,2672,2672,0,3039553,2744,2744,0,2359250,2700,2700,0,2898959,2736,2736,0,3840021,2710,2710,0,3053562,2714,2714,0,3500255,2716,2716,0,2561979,2713,2713,0,2935477,2733,2733,0,3563788,2703,2703,0,2625817,2705,2705,0,3077528,2723,2723,0,3574562,2694,2694,0,3570602,2744,2744,0,3482203,2718,2718,0,3428227,2726,2726,0,2963549,2712,2712,0,2918923,2724,2724,0,2596552,2676,2676,64,0x7f2b358f0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,6570,44835,1079,131879.0,131072.0,0.0,107520.0,64,0x7f52539fae80,340616,229944,3361732,16384,24531568,0,48,0,42576,42576,3739316.0,3078645.0,6342.0,882161.0,2135594.0,0.0,3069429.0,2758188.0,340608,239737,42576,0,42576,0,1362432.0,813711.0,0.0,0.0,64,0x7f956bba8e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131306.0,0.0,466.0,131305.0,64,0x7f44161ece80,1494893,360448,163840,0,0,180224,114688,0,72343460.0,201193433.0,71593158.0,131072.0,0.0,657177.0,0,0,25423,55539.0,0.0,0.0,55539.0,64,0x7fa4391cce80,32768,0,0,0,16384,16384,393216,23307083,960.0,513877.0,0.0,524288.0,1054076.0,32768.0,0,0,0,13905,86557.0,86557.0,0.0,86557.0,64,0x7feded874e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdc4fd40e80,0,8192,4096,8192,0,8240,4144,8240,0,8343,4247,8343,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7feb2fd38e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70762.0,140151.0,64,0x7faffaee2e80,0,0,48,0,65536,65536,0,0,31164,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42484,1791,0,48.0,222.0,0.0,262144.0,64,0x7f982e7dce80,0.0,64,0x7ff858716e80,131072.0,131072.0,0.0,2553450.0,0.0,0.0,89599350.0,33108575.0,64,0x7f4b37d50e80,188542,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13935,30319,8715,2900,0,42027,262518.0,0.0,47.0,262471.0,64,0x7f1f51b16e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86610.0,0.0,131112.0,0.0,194285066682455,194285066701335 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fde441d4e80,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,0,43925,0,0,64,0x7f3e60c9ce80,4096,0,2330,0,4098,0,2325,0,4096,0,851,0,4096,0,956,0,4096,0,1646,0,4097,0,3487,0,4144,0,696,0,4096,0,592,0,4096,0,821,0,4096,0,4368,0,4144,0,3674,0,4218,0,3889,0,4096,0,4219,0,4096,0,5031,0,4096,0,1526,0,4096,0,551,0,4096,0,1891,0,4096,0,5222,0,4096,0,2262,0,4096,0,1781,0,4096,0,4366,0,4096,0,1546,0,4096,0,1776,0,4097,0,336,0,4096,0,2299,0,4096,0,2151,0,4216,0,873,0,4096,0,65,0,4096,0,2418,0,4097,0,1235,0,4096,0,44,0,4096,0,5028,0,64,0x7fe4f1e68e80,2581,0,0,1511750,452,0,0,1256508,1323,0,0,1390576,1776,0,0,1462619,187,0,0,1248769,407,0,0,1202378,4877,0,0,1770431,732,0,0,1350563,384,0,0,1297308,611,0,0,1409649,734,0,0,1316694,472,0,0,1211940,5044,0,0,1732488,925,0,0,1354968,973,0,0,1354973,1379,0,0,1405363,838,0,0,1299353,304,0,0,1218957,1817,0,0,1490833,1160,0,0,1372320,6271,0,0,1857282,1787,0,0,1506243,2092,0,0,1549318,1143,0,0,1276492,1402,0,0,1413228,407,0,0,1247513,1429,0,0,1415070,2561,0,0,1523401,1592,0,0,1438727,3126,0,0,1579821,509,0,0,1259292,433,0,0,1265277,64,0x7f32df54ce80,0,4973079,2711,2711,0,4058889,2720,2720,0,4493430,2668,2668,0,2681406,2721,2721,0,3890042,2680,2680,0,3429252,2728,2728,0,3641605,2720,2720,0,2647654,2696,2696,0,4801850,2670,2670,0,4146136,2716,2716,0,3501863,2708,2708,0,5478603,2720,2720,0,3272465,2690,2690,0,4965405,2694,2694,0,3568915,2680,2680,0,2650896,2684,2684,0,5242056,2690,2690,0,5388472,2732,2732,0,3438659,2672,2672,0,3025780,2719,2719,0,3314562,2688,2688,0,4226397,2740,2740,0,2854399,2688,2688,0,2504232,2702,2702,0,2846498,2696,2696,0,3364195,2692,2692,0,3733085,2720,2720,0,2430030,2696,2696,0,3363474,2706,2706,0,3242097,2718,2718,0,3867473,2704,2704,0,3004985,2680,2680,64,0x7f2b358f0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3379,38734,0,131355.0,131072.0,0.0,86412.0,64,0x7f52539fae80,344136,228164,3344197,16384,24508735,0,48,0,43016,43016,3712661.0,3062302.0,5248.0,790272.0,2158126.0,0.0,3052498.0,2741055.0,344128,237955,43016,0,43016,0,1376512.0,799393.0,0.0,0.0,64,0x7f956bba8e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131294.0,0.0,442.0,131293.0,64,0x7f44161ece80,1534560,360448,163840,0,0,180224,114688,0,69519286.0,194844419.0,72720170.0,131072.0,0.0,599441.0,0,0,25599,60145.0,0.0,0.0,60145.0,64,0x7fa4391cce80,32768,0,0,0,16384,16384,393216,22493453,960.0,513854.0,0.0,524288.0,884676.0,32768.0,0,0,0,13233,86402.0,86402.0,0.0,86402.0,64,0x7feded874e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdc4fd40e80,0,8192,4096,8192,0,8240,4144,8240,0,8323,4227,8323,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7feb2fd38e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,72097.0,143327.0,64,0x7faffaee2e80,0,0,48,0,65536,65536,0,0,29889,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41786,1792,0,48.0,215.0,0.0,262144.0,64,0x7f982e7dce80,0.0,64,0x7ff858716e80,131072.0,131072.0,0.0,2561361.0,0.0,0.0,92664244.0,36722243.0,64,0x7f4b37d50e80,189261,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14630,31014,8640,2891,0,40712,262480.0,0.0,47.0,262433.0,64,0x7f1f51b16e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86404.0,0.0,131112.0,0.0,194285066722455,194285066741335 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_7,obj_7,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_8,obj_8,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_9,obj_9,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_12,obj_12,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_13,obj_13,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_14,obj_14,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_15,obj_15,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_16,obj_16,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fab361b4ec0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,0,48919,0,0,64,0x7fcef8488ec0,3178,0,0,1989716,3828,0,0,2029581,2147,0,0,1840244,3150,0,0,1981722,3564,0,0,2000038,2303,0,0,1910529,3722,0,0,2156848,2992,0,0,1983852,2925,0,0,1954644,1904,0,0,1867800,2287,0,0,1859824,1144,0,0,1723378,3832,0,0,2075650,1838,0,0,1825016,939,0,0,1731341,4836,0,0,2169119,3268,0,0,2105648,1387,0,0,1730524,3558,0,0,2012253,3099,0,0,2065011,3215,0,0,1991619,4716,0,0,2142014,1050,0,0,1729380,2985,0,0,1943287,2532,0,0,1906673,1413,0,0,1742963,1771,0,0,1821336,5406,0,0,2168814,7139,0,0,2309186,4474,0,0,2052360,941,0,0,1703610,2043,0,0,1893628,64,0x7f902ae28ec0,32768,0,0,0,16384,16384,393216,22572501,960.0,513923.0,0.0,524288.0,871874.0,32768.0,0,0,0,17314,131072.0,131072.0,0.0,131072.0,64,0x7f3f35754ec0,131072.0,131072.0,0.0,2409959.0,0.0,0.0,121536767.0,61043302.0,64,0x7f62ab39cec0,0,8240,4144,8240,0,8332,4236,8332,47,8193,4144,8240,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fefba830ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47264,0,131529.0,131072.0,0.0,131104.0,64,0x7f946182cec0,2668313,360448,163840,0,0,180224,114688,0,66461910.0,198762304.0,82267543.0,131072.0,0.0,584003.0,0,0,26341,88336.0,0.0,0.0,88336.0,64,0x7fd142090ec0,0,0,192,0,65536,64500,48,1369,31711,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47689,1889,0,48.0,321.0,0.0,262288.0,64,0x7f1d907b0ec0,189071,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13210,29594,10288,588,0,46232,262567.0,0.0,188.0,262379.0,64,0x7f0824c18ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f8dfb500ec0,0,3248350,4096,4096,0,4871147,4096,4096,0,3733614,4096,4096,0,3761081,4096,4096,0,3982222,4096,4096,0,4371531,4096,4096,0,4962208,4096,4096,0,3876458,4096,4096,0,4184150,4096,4096,0,4259580,4096,4096,0,4442041,4096,4096,0,4597837,4096,4096,0,4595977,4096,4096,0,3341380,4096,4096,0,3103595,4096,4096,0,3376485,4096,4096,0,3800349,4096,4096,0,4543294,4096,4096,0,4142103,4096,4096,0,4636937,4096,4096,0,3503440,4096,4096,0,3847774,4096,4096,0,4186868,4096,4096,0,3517191,4096,4096,0,3044955,4096,4096,0,3910833,4096,4096,0,3721204,4096,4096,0,3015534,4096,4096,0,3226765,4096,4096,0,3260975,4096,4096,0,3108838,4096,4096,0,3400350,4096,4096,64,0x7f95620d4ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,50329.0,113836.0,64,0x7fb114e0cec0,384264,232283,3388141,16384,24917631,144,48,0,48032,48032,3836786.0,3007511.0,6856.0,1081652.0,2068396.0,0.0,2998812.0,2688504.0,382551,242228,48032,0,48032,0,1537024.0,960623.0,0.0,0.0,64,0x7f6cf8164ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86699.0,44373.0,131111.0,0.0,64,0x7f7ee8328ec0,4096,0,277,0,4096,0,2658,0,4096,0,1561,0,4099,0,189,0,4096,0,4362,0,4096,0,1284,0,4096,0,140,0,4096,0,1131,0,4096,0,596,0,4097,0,3418,0,4096,0,620,0,4096,0,3264,0,4096,0,1359,0,4096,0,936,0,4096,0,3801,0,4096,0,0,0,4096,0,7140,0,4096,0,2717,0,4096,0,1181,0,4096,0,1314,0,4096,0,558,0,4096,0,4654,0,4096,0,658,0,4144,0,572,0,4096,0,0,0,4096,0,514,0,4096,0,141,0,4229,0,2546,0,4096,0,75,0,4096,0,1915,0,4144,0,678,0,4096,0,2678,0,64,0x7f47bebf8ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131407.0,0.0,662.0,131406.0,64,0x7f25e97f8ec0,0.0,1410204895308401,1410204895332881 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fab361b4ec0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,0,42687,0,0,64,0x7fcef8488ec0,2018,0,0,1525678,1962,0,0,1359989,2891,0,0,1749636,246,0,0,1273296,1728,0,0,1417282,544,0,0,1381923,2334,0,0,1585793,1780,0,0,1504840,1111,0,0,1354791,626,0,0,1292673,1120,0,0,1442930,1413,0,0,1450524,1735,0,0,1489184,2725,0,0,1583541,1367,0,0,1449124,1938,0,0,1511122,1136,0,0,1403144,1585,0,0,1432685,524,0,0,1263398,2944,0,0,1564928,1945,0,0,1478651,1071,0,0,1439027,3498,0,0,1668001,818,0,0,1281646,1251,0,0,1325293,574,0,0,1282071,2367,0,0,1536424,5088,0,0,1734566,698,0,0,1444757,1391,0,0,1269682,2549,0,0,1610215,1594,0,0,1514854,64,0x7f902ae28ec0,32768,0,0,0,16384,16384,393216,22176273,0.0,524288.0,0.0,524288.0,774654.0,32768.0,0,0,0,11930,86694.0,86694.0,0.0,86694.0,64,0x7f3f35754ec0,131072.0,131072.0,0.0,2552952.0,0.0,0.0,97834598.0,44063956.0,64,0x7f62ab39cec0,0,8240,4144,8240,0,8340,4244,8340,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fefba830ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,6893,42102,1128,131405.0,131072.0,0.0,86842.0,64,0x7f946182cec0,1703157,360448,163840,0,0,180224,114688,0,70257254.0,194240499.0,74334910.0,131072.0,0.0,566706.0,0,0,25563,67781.0,0.0,0.0,67781.0,64,0x7fd142090ec0,0,0,96,0,65536,65545,0,0,34236,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,505,49166,6143,0,96.0,641.0,0.0,262144.0,64,0x7f1d907b0ec0,185345,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14531,30915,8904,3213,0,41573,262465.0,0.0,47.0,262418.0,64,0x7f0824c18ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f8dfb500ec0,0,3299199,2720,2720,0,3796232,2690,2690,0,4037035,2704,2704,0,3499984,2740,2740,0,2953324,2704,2704,0,3190286,2703,2703,0,3837586,2739,2739,0,4306873,2738,2738,0,3445860,2696,2696,0,3554725,2680,2680,0,3844778,2732,2732,0,4897832,2724,2724,0,2733460,2720,2720,0,3116911,2692,2692,0,5017286,2726,2726,0,3541627,2726,2726,0,3341724,2724,2724,0,3845608,2666,2666,0,4128542,2706,2706,0,4550617,2710,2710,0,2632965,2726,2726,0,4009816,2745,2745,0,3886885,2693,2693,0,3138020,2684,2684,0,2569575,2696,2696,0,3038228,2689,2689,0,5433430,2746,2746,0,3362008,2720,2720,0,2705425,2720,2720,0,3018845,2677,2677,0,2657329,2720,2720,0,2564211,2728,2728,64,0x7f95620d4ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,53985.0,122666.0,64,0x7fb114e0cec0,337136,227281,3338046,16384,24238368,0,48,0,42141,42141,3698723.0,3059204.0,5679.0,1041383.0,2058143.0,0.0,3049703.0,2737991.0,337128,236755,42141,0,42141,0,1348512.0,811904.0,0.0,0.0,64,0x7f6cf8164ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,63132.0,23700.0,75029.0,0.0,64,0x7f7ee8328ec0,4096,0,319,0,4096,0,849,0,4096,0,2646,0,4096,0,4191,0,4096,0,1674,0,4096,0,0,0,4096,0,1272,0,4096,0,613,0,4096,0,199,0,4097,0,0,0,4096,0,559,0,4096,0,122,0,4096,0,341,0,4098,0,0,0,4096,0,3074,0,4096,0,1112,0,4096,0,1477,0,4096,0,1789,0,4096,0,1853,0,4096,0,255,0,4096,0,380,0,4096,0,666,0,4096,0,361,0,4145,0,523,0,4096,0,569,0,4096,0,388,0,4096,0,382,0,4222,0,3291,0,4096,0,0,0,4097,0,0,0,4144,0,0,0,4096,0,0,0,64,0x7f47bebf8ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131403.0,0.0,660.0,131402.0,64,0x7f25e97f8ec0,0.0,1410204895428561,1410204895447761 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fab361b4ec0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,0,42595,0,0,64,0x7fcef8488ec0,2141,0,0,1487363,1628,0,0,1427737,1720,0,0,1489382,1193,0,0,1389113,2033,0,0,1495177,1029,0,0,1428949,3343,0,0,1631193,1967,0,0,1523450,2531,0,0,1550820,1684,0,0,1466414,1046,0,0,1357541,792,0,0,1292997,1400,0,0,1428682,1249,0,0,1401370,3975,0,0,1696807,1830,0,0,1511089,3304,0,0,1587585,865,0,0,1237162,1773,0,0,1475974,640,0,0,1293807,2475,0,0,1518192,1861,0,0,1528917,3573,0,0,1667422,1624,0,0,1411841,2254,0,0,1509451,318,0,0,1138937,2456,0,0,1508835,3242,0,0,1515990,3953,0,0,1617761,1767,0,0,1469955,2353,0,0,1543828,747,0,0,1306805,64,0x7f902ae28ec0,32768,0,0,0,16384,16384,393216,22626370,960.0,513931.0,0.0,524288.0,873359.0,32768.0,0,0,0,13972,86461.0,86461.0,0.0,86461.0,64,0x7f3f35754ec0,131072.0,131072.0,0.0,2370799.0,0.0,0.0,125948792.0,50360983.0,64,0x7f62ab39cec0,0,8240,4144,8240,0,8358,4262,8358,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fefba830ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2719,39724,0,131389.0,131072.0,0.0,86549.0,64,0x7f946182cec0,2268124,360448,163840,0,0,180224,114688,0,66132528.0,169872119.0,69018580.0,131072.0,0.0,649640.0,0,0,25209,70119.0,0.0,0.0,70119.0,64,0x7fd142090ec0,0,0,48,0,65536,65536,0,0,30650,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,455,42186,1745,0,48.0,266.0,0.0,262144.0,64,0x7f1d907b0ec0,157150,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13819,30203,8598,3422,0,41797,262485.0,0.0,47.0,262438.0,64,0x7f0824c18ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f8dfb500ec0,0,4266052,2740,2740,0,4177475,2728,2728,0,2830829,2685,2685,0,2554632,2696,2696,0,3935895,2736,2736,0,4894463,2726,2726,0,3930129,2685,2685,0,2952218,2692,2692,0,5021880,2730,2730,0,4037405,2682,2682,0,3216474,2696,2696,0,4185008,2702,2702,0,4468192,2728,2728,0,4534647,2692,2692,0,3000659,2678,2678,0,2485127,2680,2680,0,4638385,2728,2728,0,4893805,2710,2710,0,3589291,2660,2660,0,2473677,2703,2703,0,3731175,2726,2726,0,3844653,2739,2739,0,4236158,2676,2676,0,2753064,2670,2670,0,3588985,2702,2702,0,3922330,2704,2704,0,2822037,2728,2728,0,3192377,2692,2692,0,3405218,2728,2728,0,3375260,2704,2704,0,3225207,2700,2700,0,2599060,2686,2686,64,0x7f95620d4ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,61534.0,133332.0,64,0x7fb114e0cec0,336520,226102,3318006,16384,24650454,0,48,0,42064,42064,3681176.0,3026158.0,5984.0,780016.0,2076587.0,0.0,3016634.0,2704773.0,336512,235891,42064,0,42064,0,1346048.0,810086.0,0.0,0.0,64,0x7f6cf8164ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86568.0,0.0,131112.0,0.0,64,0x7f7ee8328ec0,4096,0,4971,0,4096,0,670,0,4096,0,2507,0,4096,0,940,0,4096,0,3815,0,4096,0,2065,0,4096,0,1655,0,4096,0,824,0,4096,0,3827,0,4097,0,707,0,4096,0,4766,0,4096,0,4248,0,4096,0,2689,0,4098,0,1370,0,4096,0,4462,0,4096,0,118,0,4096,0,2487,0,4096,0,4075,0,4096,0,774,0,4096,0,1333,0,4096,0,1708,0,4096,0,4001,0,4096,0,4844,0,4145,0,1927,0,4096,0,2658,0,4096,0,3904,0,4096,0,1169,0,4251,0,1379,0,4096,0,4744,0,4097,0,1185,0,4144,0,3579,0,4096,0,3170,0,64,0x7f47bebf8ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131410.0,0.0,674.0,131409.0,64,0x7f25e97f8ec0,0.0,1410204895469361,1410204895488081 diff --git a/tests/workloads/device_filter/MI100/sysinfo.csv b/tests/workloads/device_filter/MI100/sysinfo.csv index 3b3294c9b8..1085042716 100644 --- a/tests/workloads/device_filter/MI100/sysinfo.csv +++ b/tests/workloads/device_filter/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -device_filter,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:57 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +device_filter,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:54:18 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/device_filter/MI100/timestamps.csv b/tests/workloads/device_filter/MI100/timestamps.csv index 37942f7a55..020027b2d6 100644 --- a/tests/workloads/device_filter/MI100/timestamps.csv +++ b/tests/workloads/device_filter/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066439120,194285066464535,194285066489175,194285066502310 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066502350,194285066682455,194285066701335,194285066702839 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,175921,175921,1048576,256,0,0,8,8,16,64,0x0,0x7ff832f9ae80,194285066713930,194285066722455,194285066741335,194285066742634 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1271546,1271546,1048576,256,0,0,8,8,16,64,0x0,0x7facae2fcec0,1410204895282038,1410204895308401,1410204895332881,1410204895343735 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1271546,1271546,1048576,256,0,0,8,8,16,64,0x0,0x7facae2fcec0,1410204895345248,1410204895428561,1410204895447761,1410204895449153 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1271546,1271546,1048576,256,0,0,8,8,16,64,0x0,0x7facae2fcec0,1410204895459924,1410204895469361,1410204895488081,1410204895489490 diff --git a/tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv index ca02cd7a40..f5569067c4 100644 --- a/tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,27379,27379,16384,65536,13546,1530804,199109067732799,199121780771567,199121780791247,199109083780798 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,40641,40641,16384,65536,9422,1048620,199109083800004,199121780810127,199121780825807,199109084104139 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330344,330344,1048576,256,0,0,8,0,16,64,0x0,0x7fe6cf348ec0,40214,40214,16384,65536,9321,1048756,199109084143764,199121780890127,199121780906607,199109084308516 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4154776,4154776,1048576,256,0,0,8,0,16,64,0x0,0x7f4aeac78ec0,28399,28399,16384,65536,16539,1859828,1412689608475887,1412702536508356,1412702536528996,1412689624744624 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4154776,4154776,1048576,256,0,0,8,0,16,64,0x0,0x7f4aeac78ec0,41854,41854,16384,65536,9149,1048652,1412689624764922,1412702536548036,1412702536563556,1412689625202329 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4154776,4154776,1048576,256,0,0,8,0,16,64,0x0,0x7f4aeac78ec0,42687,42687,16384,65536,9446,1048640,1412689625231735,1412702536625636,1412702536642116,1412689625401916 diff --git a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv index 242baf8ff9..59edb8ff79 100644 --- a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109550821338,199121780771567,199121780791247,199109566789335 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109566805174,199121780810127,199121780825807,199109567096836 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330545,330545,1048576,256,0,0,8,0,16,64,0x0,0x7f3c42f94ec0,0,0,0,199109567123557,199121780890127,199121780906607,199109567286696 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4154974,4154974,1048576,256,0,0,8,0,16,64,0x0,0x7f1046a28ec0,0,0,0,1412690095463857,1412702536508356,1412702536528996,1412690111629429 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4154974,4154974,1048576,256,0,0,8,0,16,64,0x0,0x7f1046a28ec0,0,0,0,1412690111650128,1412702536548036,1412702536563556,1412690111919096 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4154974,4154974,1048576,256,0,0,8,0,16,64,0x0,0x7f1046a28ec0,0,0,0,1412690111945456,1412702536625636,1412702536642116,1412690112092594 diff --git a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv index 07b2c32d82..20f5c007fe 100644 --- a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,211460,23579520,199110030597901,199121780771567,199121780791247,199110046727484 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,254912,28465096,199110046748423,199121780810127,199121780825807,199110047009096 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330728,330728,1048576,256,0,0,8,0,16,64,0x0,0x7fc8f8a6cec0,65536,258838,28871464,199110047035506,199121780890127,199121780906607,199110047184308 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4155175,4155175,1048576,256,0,0,8,0,16,64,0x0,0x7fd9f40c4ec0,65536,172670,19277760,1412690576047496,1412702536508356,1412702536528996,1412690592443443 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4155175,4155175,1048576,256,0,0,8,0,16,64,0x0,0x7fd9f40c4ec0,65536,228700,25581136,1412690592461567,1412702536548036,1412702536563556,1412690592741416 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4155175,4155175,1048576,256,0,0,8,0,16,64,0x0,0x7fd9f40c4ec0,65536,231114,25926712,1412690592767165,1412702536625636,1412702536642116,1412690592915886 diff --git a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv index 82f95e25a3..566cc05b22 100644 --- a/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,288902,32346476,199110514009110,199121780771567,199121780791247,199110529778261 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,593947,66524552,199110529795433,199121780810127,199121780825807,199110530092144 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,330929,330929,1048576,256,0,0,8,0,16,64,0x0,0x7fd12bbd8ec0,32768,602236,67452520,199110530118254,199121780890127,199121780906607,199110530290219 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4155361,4155361,1048576,256,0,0,8,0,16,64,0x0,0x7f9045bb8ec0,32768,290637,32556924,1412691060480394,1412702536508356,1412702536528996,1412691076529415 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4155361,4155361,1048576,256,0,0,8,0,16,64,0x0,0x7f9045bb8ec0,32768,589721,66052460,1412691076546758,1412702536548036,1412702536563556,1412691076842818 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4155361,4155361,1048576,256,0,0,8,0,16,64,0x0,0x7f9045bb8ec0,32768,574435,64354132,1412691076869588,1412702536625636,1412702536642116,1412691077020423 diff --git a/tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv index 88fc5ecb4c..b5619f2427 100644 --- a/tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,27492,27492,10876,219944,16384,10773590,127834,0,43600528,199110993347043,199121780771567,199121780791247,199111009505921 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,41046,41046,13175,328376,16384,19783221,224811,0,79611516,199111009533263,199121780810127,199121780825807,199111009819264 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,331115,331115,1048576,256,0,0,8,0,16,64,0x0,0x7f16a9730ec0,40621,40621,11924,324976,16384,19553416,225262,0,78707700,199111009854681,199121780890127,199121780906607,199111010019924 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4155559,4155559,1048576,256,0,0,8,0,16,64,0x0,0x7f2e47d90ec0,27782,27782,11060,222264,16384,10980955,128903,0,44430920,1412691542352890,1412702536508356,1412702536528996,1412691558586810 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4155559,4155559,1048576,256,0,0,8,0,16,64,0x0,0x7f2e47d90ec0,42364,42364,13501,338920,16384,20566692,235190,0,82737616,1412691558614052,1412702536548036,1412702536563556,1412691558909250 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4155559,4155559,1048576,256,0,0,8,0,16,64,0x0,0x7f2e47d90ec0,40646,40646,12686,325176,16384,19387932,222546,0,78034296,1412691558944307,1412702536625636,1412702536642116,1412691559104820 diff --git a/tests/workloads/device_filter/MI200/log.txt b/tests/workloads/device_filter/MI200/log.txt new file mode 100644 index 0000000000..89cba4ac79 --- /dev/null +++ b/tests/workloads/device_filter/MI200/log.txt @@ -0,0 +1,739 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/device_filter/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_163557' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163557_4154616' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163557_4154616/input0_results_240321_163557' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163557_4154616/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163557_4154616/input0_results_240321_163557 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_163557' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163557_4154814' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163557_4154814/input0_results_240321_163557' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163557_4154814/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163557_4154814/input0_results_240321_163557 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_163558' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163558_4155015' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163558_4155015/input0_results_240321_163558' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163558_4155015/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163558_4155015/input0_results_240321_163558 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_163558' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163558_4155199' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163558_4155199/input0_results_240321_163558' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163558_4155199/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163558_4155199/input0_results_240321_163558 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_163559' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163559_4155399' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163559_4155399/input0_results_240321_163559' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163559_4155399/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163559_4155399/input0_results_240321_163559 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_163559' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163559_4155605' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163559_4155605/input0_results_240321_163559' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163559_4155605/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163559_4155605/input0_results_240321_163559 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_163600' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163600_4155792' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163600_4155792/input0_results_240321_163600' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163600_4155792/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163600_4155792/input0_results_240321_163600 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_163600' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163600_4155978' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163600_4155978/input0_results_240321_163600' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163600_4155978/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163600_4155978/input0_results_240321_163600 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_163601' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163601_4156163' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163601_4156163/input0_results_240321_163601' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163601_4156163/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163601_4156163/input0_results_240321_163601 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_163601' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163601_4156379' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163601_4156379/input0_results_240321_163601' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163601_4156379/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163601_4156379/input0_results_240321_163601 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_163602' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163602_4156580' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163602_4156580/input0_results_240321_163602' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163602_4156580/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163602_4156580/input0_results_240321_163602 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_163602' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163602_4156781' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163602_4156781/input0_results_240321_163602' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163602_4156781/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163602_4156781/input0_results_240321_163602 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_163603' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163603_4156967' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163603_4156967/input0_results_240321_163603' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163603_4156967/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163603_4156967/input0_results_240321_163603 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_163604' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163604_4157155' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163604_4157155/input0_results_240321_163604' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163604_4157155/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163604_4157155/input0_results_240321_163604 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_163605' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163605_4157340' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163605_4157340/input0_results_240321_163605' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163605_4157340/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163605_4157340/input0_results_240321_163605 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_163605' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163605_4157525' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163605_4157525/input0_results_240321_163605' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163605_4157525/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163605_4157525/input0_results_240321_163605 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_163606' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163606_4157708' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163606_4157708/input0_results_240321_163606' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163606_4157708/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163606_4157708/input0_results_240321_163606 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_163606' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163606_4157893' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163606_4157893/input0_results_240321_163606' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163606_4157893/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163606_4157893/input0_results_240321_163606 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_163607' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163607_4158080' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163607_4158080/input0_results_240321_163607' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163607_4158080/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163607_4158080/input0_results_240321_163607 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_163607' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163607_4158281' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163607_4158281/input0_results_240321_163607' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163607_4158281/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163607_4158281/input0_results_240321_163607 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_163608' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163608_4158468' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163608_4158468/input0_results_240321_163608' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163608_4158468/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163608_4158468/input0_results_240321_163608 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_163608' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163608_4158670' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163608_4158670/input0_results_240321_163608' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163608_4158670/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163608_4158670/input0_results_240321_163608 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_163609' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163609_4158857' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163609_4158857/input0_results_240321_163609' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163609_4158857/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163609_4158857/input0_results_240321_163609 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_163609' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163609_4159041' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163609_4159041/input0_results_240321_163609' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163609_4159041/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163609_4159041/input0_results_240321_163609 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_filter/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_163610' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_filter/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163610_4159225' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163610_4159225/input0_results_240321_163610' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163610_4159225/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163610_4159225/input0_results_240321_163610 + |-> [rocprof] File 'tests/workloads/device_filter/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/device_filter/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/kernel_verbose_5/MI100/pmc_dispatch_info.csv b/tests/workloads/device_filter/MI200/pmc_dispatch_info.csv similarity index 100% rename from tests/workloads/kernel_verbose_5/MI100/pmc_dispatch_info.csv rename to tests/workloads/device_filter/MI200/pmc_dispatch_info.csv diff --git a/tests/workloads/device_filter/MI200/pmc_perf.csv b/tests/workloads/device_filter/MI200/pmc_perf.csv index c5ff376c7a..f0e55ce424 100644 --- a/tests/workloads/device_filter/MI200/pmc_perf.csv +++ b/tests/workloads/device_filter/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_3,obj_3,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_13,obj_13,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_14,obj_14,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_15,obj_15,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_16,obj_16,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_17,obj_17,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_18,obj_18,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a8d118ec0,0,393216,163840,0,0,0,0,0,18192,0.0,0.0,0.0,32768.0,0.0,0.0,404.0,32768.0,4096,16384,352,28648,1959,0,56.0,6.0,0.0,204115.0,64,0x7fc01fea8ec0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,0,27649,0,0,64,0x7f7dbc560ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41566892.0,35963380.0,0.0,64,0x7f1e9c334ec0,2266,4098,2268,6364,2304,4096,2304,6400,2258,4096,2258,6354,2293,4096,2293,6389,2294,4097,2295,6391,2296,4096,2296,6392,2265,4096,2265,6361,2259,4096,2259,6355,2264,4096,2264,6360,2268,4096,2268,6364,2307,4096,2307,6403,2259,4096,2259,6355,2296,4096,2296,6392,2241,4096,2241,6337,2295,4096,2295,6391,2265,4096,2265,6361,2296,4096,2296,6392,2289,4096,2289,6385,2272,4098,2274,6370,2285,4096,2285,6381,2273,4096,2273,6369,2261,4096,2261,6357,2284,4096,2284,6380,2481,4098,2483,6579,2310,4096,2310,6406,2299,4096,2299,6395,2290,4096,2290,6386,2270,4096,2270,6366,2284,4096,2284,6380,2274,4096,2274,6370,2263,4096,2263,6359,2285,4096,2285,6381,64,0x7f61a3950ec0,232256,129710,16384,0,16384,16384,32768,49152,29031,29031,1963928.0,1376026.0,3395.0,177094.0,1080961.0,0.0,1367746.0,1069337.0,230545,137846,29031,0,29031,0,928992.0,489441.0,0.0,0.0,64,0x7f85d9680ec0,0,1222161,4096,4096,0,1294970,4096,4096,0,1055300,4096,4096,0,1352829,4096,4096,0,1415575,4096,4096,0,1355138,4096,4096,0,1217705,4096,4096,0,1445989,4096,4096,0,1143331,4096,4096,0,1058640,4096,4096,0,1085347,4096,4096,0,1450439,4096,4096,0,1391096,4096,4096,0,1303465,4096,4096,0,1164874,4096,4096,0,1264499,4096,4096,0,1245139,4096,4096,0,1586344,4096,4096,0,1067662,4096,4096,0,1645609,4096,4096,0,1179812,4096,4096,0,1473415,4096,4096,0,1531899,4096,4096,0,1149818,4096,4096,0,1272169,4096,4096,0,1059596,4096,4096,0,1204653,4096,4096,0,1266661,4096,4096,0,1397846,4096,4096,0,1155763,4096,4096,0,1270045,4096,4096,0,1393299,4096,4096,64,0x7f89fa890ec0,1270,116237,0,0,65536,63800,56,1680,64,0x7fd0d2be8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f08643d4ec0,6309,0,4096,6323,0,4096,6411,0,4096,6397,0,4096,6331,0,4096,6323,0,4096,6388,0,4096,6485,0,4096,6486,0,4096,6311,0,4096,6326,0,4096,6414,0,4096,6396,0,4096,6332,0,4096,6328,0,4096,6389,0,4096,6395,0,4096,6402,0,4096,6292,0,4096,6337,0,4096,6385,0,4096,6347,0,4096,6351,0,4096,6499,0,4096,6337,0,4096,6395,0,4096,6404,0,4096,6288,0,4096,6339,0,4096,6386,0,4096,6351,0,4096,6354,0,4096,64,0x7ff854f58ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10145,0,814,27538,0,73243.0,131072.0,0.0,65568.0,64,0x7f4126794ec0,0,0,0,224,0,65536,64169,56,64,0x7fd0b879cec0,10377321,9384630,648627,344064,1565336,0,0,163840,832.0,515136.0,0.0,524288.0,252802.0,32768.0,441329,0,0,11202,131072.0,131072.0,0.0,131072.0,64,0x7fc6d5a1cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,34350.0,46165.0,19371.0,64,0x7fd0d002cec0,114688,0,32768,32768,16384,16384,65536,49152,28333967.0,87418890.0,38825053.0,131072.0,0.0,214467.0,0,0,15472,301.0,131080.0,0.0,8.0,64,0x7ff4297c4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12322,18857,7191,545,0,26141,204027.0,0.0,72944.0,131083.0,64,0x7f0b2a81cec0,32768,32768,0,64,0x7fda70128ec0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,197,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,362,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4100,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f3c3f648ec0,0,0,0,1001867,0,0,0,1034501,0,0,0,1039801,0,0,0,1149913,16,0,0,1127038,0,0,0,1061247,0,0,0,1102693,18,0,0,1303069,0,0,0,1109414,0,0,0,1002710,0,0,0,1023850,0,0,0,1088630,0,0,0,1100645,0,0,0,1135139,0,0,0,981449,7,0,0,1207898,0,0,0,1037454,61,0,0,1205959,0,0,0,954309,0,0,0,1088841,0,0,0,1094129,0,0,0,1084983,0,0,0,1109150,0,0,0,1086548,0,0,0,972888,0,0,0,1066849,0,0,0,1000714,0,0,0,1127056,43,0,0,1104743,0,0,0,1069381,0,0,0,1101394,0,0,0,1160834,64,0x7f53b09e8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,951355.0,199121780771567,199121780791247 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a8d118ec0,0,393216,163840,0,0,0,0,0,27713,0.0,0.0,0.0,32768.0,0.0,0.0,179.0,32768.0,4096,16384,302,36962,1920,0,56.0,0.0,0.0,200346.0,64,0x7fc01fea8ec0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,0,42159,0,0,64,0x7f7dbc560ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118471975.0,66267208.0,0.0,64,0x7f1e9c334ec0,2161,4099,2164,6260,2151,4098,2153,6249,2178,4096,2178,6274,2142,4096,2142,6238,2189,4097,2190,6286,2136,4096,2136,6232,2178,4096,2178,6274,2169,4096,2169,6265,2175,4096,2175,6271,2165,4096,2165,6261,2156,4096,2156,6252,2178,4096,2178,6274,2145,4096,2145,6241,2130,4096,2130,6226,2141,4096,2141,6237,2186,4096,2186,6282,2159,4097,2160,6256,2172,4096,2172,6268,2168,4098,2170,6266,2182,4096,2182,6278,2164,4096,2164,6260,2162,4096,2162,6258,2147,4096,2147,6243,2141,4096,2141,6237,2148,4096,2148,6244,2166,4096,2166,6262,2176,4096,2176,6272,2172,4096,2172,6268,2177,4097,2178,6274,2167,4096,2167,6263,2165,4096,2165,6261,2149,4096,2149,6245,64,0x7f61a3950ec0,328560,221627,16384,0,16384,16384,32768,49152,41069,41069,3158598.0,2460968.0,5037.0,337420.0,1680863.0,0.0,2448414.0,2138415.0,328552,231375,41069,0,41069,0,1314208.0,766352.0,0.0,0.0,64,0x7f85d9680ec0,0,3232678,2856,2856,0,3335659,2888,2888,0,3761389,2866,2866,0,3639512,2880,2880,0,4397834,2868,2868,0,4507952,2844,2844,0,3066646,2852,2852,0,4327187,2824,2824,0,3471679,2824,2824,0,3920499,2852,2852,0,3591748,2890,2890,0,3687937,2864,2864,0,3014193,2880,2880,0,3520333,2864,2864,0,3856037,2840,2840,0,4205632,2852,2852,0,3989474,2816,2816,0,3539459,2852,2852,0,3836590,2880,2880,0,3720161,2872,2872,0,4301203,2840,2840,0,4296486,2892,2892,0,3771862,2820,2820,0,5227377,2848,2848,0,3937104,2848,2848,0,4223077,2816,2816,0,3659150,2852,2852,0,4100095,2878,2878,0,3498362,2864,2864,0,3425720,2840,2840,0,3595413,2892,2892,0,4396528,2820,2820,64,0x7f89fa890ec0,0,184365,0,0,65536,63800,56,1680,64,0x7fd0d2be8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7f08643d4ec0,6270,0,4096,6284,0,4096,6261,0,4096,6270,0,4096,6274,0,4096,6308,0,4096,6257,0,4096,6261,0,4096,6260,0,4096,6269,0,4096,6286,0,4096,6259,0,4096,6276,0,4096,6276,0,4096,6312,0,4096,6256,0,4096,6271,0,4096,6242,0,4096,6266,0,4096,6291,0,4096,6262,0,4096,6266,0,4096,6279,0,4096,6318,0,4096,6319,0,4096,6270,0,4096,6246,0,4096,6267,0,4096,6289,0,4096,6258,0,4096,6268,0,4096,6283,0,4096,64,0x7ff854f58ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21157,0,3388,39296,0,69259.0,131072.0,0.0,45450.0,64,0x7f4126794ec0,0,0,0,56,0,65536,65536,0,64,0x7fd0b879cec0,19081381,17928759,808558,344064,2721065,0,0,163840,832.0,515144.0,0.0,524288.0,663743.0,32768.0,958763,0,0,13853,90744.0,90744.0,0.0,90744.0,64,0x7fc6d5a1cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131074.0,89223.0,45570.0,0.0,64,0x7fd0d002cec0,114688,0,32768,32768,16384,16384,65536,49152,57664325.0,203725507.0,46739559.0,131072.0,0.0,538226.0,0,0,25176,5889.0,131084.0,0.0,22.0,64,0x7ff4297c4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27800,27794,8751,550,0,35684,200707.0,0.0,69632.0,131075.0,64,0x7f0b2a81cec0,32768,32768,0,64,0x7fda70128ec0,4096,0,121,0,4096,0,39,0,4097,0,368,0,4096,0,521,0,4096,0,41,0,4096,0,573,0,4096,0,419,0,4096,0,260,0,4096,0,1208,0,4096,0,113,0,4096,0,386,0,4096,0,1155,0,4096,0,865,0,4096,0,0,0,4096,0,1421,0,4097,0,370,0,4097,0,1191,0,4096,0,1103,0,4097,0,312,0,4097,0,1088,0,4100,0,151,0,4096,0,1553,0,4096,0,1450,0,4096,0,422,0,4096,0,165,0,4096,0,313,0,4096,0,42,0,4096,0,48,0,4097,0,1560,0,4096,0,26,0,4098,0,30,0,4096,0,155,0,64,0x7f3c3f648ec0,595,0,0,1975494,231,0,0,1999416,266,0,0,1962958,486,0,0,1859654,452,0,0,2029586,2134,0,0,2497031,259,0,0,1914490,679,0,0,2226582,1021,0,0,2186328,310,0,0,1754375,448,0,0,2277055,512,0,0,1972859,452,0,0,1747124,669,0,0,2298676,1081,0,0,2352290,844,0,0,2150303,270,0,0,2217530,1097,0,0,2314692,744,0,0,2035454,982,0,0,2335155,341,0,0,1930718,2722,0,0,2599638,0,0,0,1731854,163,0,0,2117254,170,0,0,2182808,871,0,0,2212921,400,0,0,2010053,375,0,0,1878286,1125,0,0,2240574,68,0,0,1744642,1513,0,0,2182432,336,0,0,2284276,64,0x7f53b09e8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2043679.0,199121780810127,199121780825807 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a8d118ec0,0,393216,163840,0,0,0,0,0,29721,0.0,0.0,0.0,32768.0,0.0,0.0,272.0,32768.0,4096,16384,302,40740,1956,0,56.0,9.0,0.0,201143.0,64,0x7fc01fea8ec0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,0,42528,0,0,64,0x7f7dbc560ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119995005.0,71157945.0,0.0,64,0x7f1e9c334ec0,2174,4099,2177,6273,2198,4098,2200,6296,2164,4096,2164,6260,2183,4096,2183,6279,2219,4097,2220,6316,2182,4096,2182,6278,2161,4096,2161,6257,2165,4096,2165,6261,2162,4096,2162,6258,2174,4096,2174,6270,2197,4096,2197,6293,2161,4096,2161,6257,2184,4096,2184,6280,2164,4096,2164,6260,2176,4096,2176,6272,2158,4096,2158,6254,2165,4097,2166,6262,2180,4096,2180,6276,2174,4098,2176,6272,2158,4096,2158,6254,2204,4096,2204,6300,2171,4096,2171,6267,2170,4096,2170,6266,2173,4096,2173,6269,2175,4096,2175,6271,2169,4096,2169,6265,2183,4096,2183,6279,2177,4096,2177,6273,2161,4097,2162,6258,2207,4096,2207,6303,2173,4096,2173,6269,2172,4096,2172,6268,64,0x7f61a3950ec0,331976,223954,16384,0,16384,16384,32768,49152,41496,41496,3188123.0,2487009.0,4110.0,395442.0,1802846.0,0.0,2474216.0,2164747.0,331968,233067,41496,0,41496,0,1327872.0,773543.0,0.0,0.0,64,0x7f85d9680ec0,0,3174388,2828,2828,0,3079431,2872,2872,0,4333494,2860,2860,0,3418129,2868,2868,0,4391738,2888,2888,0,3919640,2856,2856,0,2924396,2856,2856,0,3585551,2812,2812,0,3542793,2812,2812,0,3521330,2828,2828,0,3163722,2872,2872,0,4322369,2864,2864,0,2595513,2870,2870,0,3097719,2888,2888,0,3966381,2856,2856,0,3072174,2856,2856,0,3254967,2808,2808,0,5016060,2850,2850,0,3044454,2842,2842,0,4084529,2852,2852,0,3183913,2844,2844,0,4116338,2896,2896,0,4476701,2824,2824,0,3439648,2824,2824,0,4469803,2824,2824,0,3515651,2804,2804,0,3608618,2844,2844,0,3926221,2836,2836,0,3799220,2856,2856,0,4531322,2840,2840,0,3175626,2896,2896,0,2960598,2824,2824,64,0x7f89fa890ec0,0,185461,0,0,65536,63800,56,1680,64,0x7fd0d2be8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f08643d4ec0,6230,0,4096,6247,0,4096,6271,0,4096,6262,0,4096,6268,0,4096,6297,0,4096,6260,0,4096,6261,0,4096,6263,0,4096,6231,0,4096,6249,0,4096,6272,0,4096,6262,0,4096,6271,0,4096,6296,0,4096,6258,0,4096,6252,0,4096,6279,0,4096,6258,0,4096,6249,0,4096,6248,0,4096,6278,0,4096,6256,0,4096,6282,0,4096,6284,0,4096,6253,0,4096,6283,0,4096,6263,0,4096,6251,0,4096,6246,0,4096,6279,0,4096,6256,0,4096,64,0x7ff854f58ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21726,0,2836,38956,0,69585.0,131072.0,0.0,45457.0,64,0x7f4126794ec0,0,0,0,56,0,65536,65536,0,64,0x7fd0b879cec0,18992598,17897611,750923,344064,2740347,0,0,163840,832.0,515158.0,0.0,524288.0,568711.0,32768.0,952685,0,0,13344,91058.0,91058.0,0.0,91058.0,64,0x7fc6d5a1cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,103025.0,45587.0,0.0,64,0x7fd0d002cec0,114688,0,32768,32768,16384,16384,65536,49152,57005676.0,199044416.0,48768208.0,131072.0,0.0,508170.0,0,0,25041,4173.0,131082.0,0.0,18.0,64,0x7ff4297c4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32824,28015,9582,2832,0,39458,200837.0,0.0,69750.0,131087.0,64,0x7f0b2a81cec0,32768,32768,0,64,0x7fda70128ec0,4096,0,238,0,4096,0,85,0,4097,0,0,0,4096,0,122,0,4096,0,18,0,4096,0,437,0,4096,0,120,0,4096,0,1206,0,4096,0,532,0,4096,0,127,0,4096,0,287,0,4096,0,0,0,4096,0,318,0,4096,0,241,0,4096,0,145,0,4097,0,8,0,4097,0,24,0,4096,0,1914,0,4097,0,57,0,4097,0,1065,0,4101,0,113,0,4096,0,852,0,4096,0,222,0,4096,0,1719,0,4096,0,988,0,4096,0,43,0,4096,0,0,0,4096,0,750,0,4097,0,248,0,4096,0,14,0,4098,0,1554,0,4096,0,69,0,64,0x7f3c3f648ec0,554,0,0,2261820,1209,0,0,2575791,0,0,0,1621827,74,0,0,2037275,1180,0,0,2524103,404,0,0,2022422,0,0,0,1430425,0,0,0,1570629,0,0,0,1436278,0,0,0,1816981,0,0,0,2176448,0,0,0,1730391,0,0,0,1903018,514,0,0,2162762,284,0,0,2032468,0,0,0,1676391,0,0,0,1652474,0,0,0,1749102,92,0,0,1948161,0,0,0,1995391,0,0,0,1534929,69,0,0,2085733,332,0,0,2008735,201,0,0,2284680,0,0,0,2025651,0,0,0,1369773,0,0,0,1833494,0,0,0,1956247,0,0,0,1711645,0,0,0,1547265,0,0,0,1706631,322,0,0,2191072,64,0x7f53b09e8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2033587.0,199121780890127,199121780906607 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_1,obj_1,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_2,obj_2,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_3,obj_3,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_6,obj_6,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_7,obj_7,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_14,obj_14,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_15,obj_15,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_16,obj_16,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_17,obj_17,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_18,obj_18,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fb673fe4ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10610,0,814,27111,0,73433.0,131072.0,0.0,65568.0,64,0x7f3d464b0ec0,1919,113235,0,0,65536,63800,56,1680,64,0x7fa4eb060ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,376,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4100,0,0,0,4097,0,0,0,4100,0,5,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f82a1118ec0,32768,32768,0,64,0x7f67fc544ec0,0,1075573,4096,4096,0,1417686,4096,4096,0,1258273,4096,4096,0,1060007,4096,4096,0,1286569,4096,4096,0,1447276,4096,4096,0,1280967,4096,4096,0,1618387,4096,4096,0,1318248,4096,4096,0,1051744,4096,4096,0,1139989,4096,4096,0,1249440,4096,4096,0,1202030,4096,4096,0,1096887,4096,4096,0,1351422,4096,4096,0,1295455,4096,4096,0,1122716,4096,4096,0,998998,4096,4096,0,1129159,4096,4096,0,1344252,4096,4096,0,1246222,4096,4096,0,1225622,4096,4096,0,1196343,4096,4096,0,1174131,4096,4096,0,1361353,4096,4096,0,1128266,4096,4096,0,1060998,4096,4096,0,1114399,4096,4096,0,1200938,4096,4096,0,1221875,4096,4096,0,1202747,4096,4096,0,1510103,4096,4096,64,0x7fbea6bd8ec0,0,0,0,224,0,65536,63724,56,64,0x7f2c2b190ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fdff74f8ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12200,18528,7929,548,0,26218,204031.0,0.0,72952.0,131079.0,64,0x7fd58c9c8ec0,6361,0,4096,6387,0,4096,6330,0,4096,6369,0,4096,6338,0,4096,6386,0,4096,6377,0,4096,6403,0,4096,6411,0,4096,6367,0,4096,6390,0,4096,6330,0,4096,6366,0,4096,6337,0,4096,6393,0,4096,6374,0,4096,6385,0,4096,6421,0,4096,6356,0,4096,6386,0,4096,6354,0,4096,6397,0,4096,6374,0,4096,6509,0,4096,6342,0,4096,6386,0,4096,6420,0,4096,6361,0,4096,6386,0,4096,6353,0,4096,6400,0,4096,6377,0,4096,64,0x7f6bf1be8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39899193.0,34866167.0,0.0,64,0x7f062f654ec0,233368,131088,16384,0,16384,16384,32768,49152,29170,29170,1981790.0,1397458.0,3826.0,182431.0,1090351.0,0.0,1388708.0,1089303.0,231657,139224,29170,0,29170,0,933440.0,503963.0,0.0,0.0,64,0x7fd082a6cec0,11019692,9727391,948237,344064,1642378,0,0,163840,832.0,515136.0,0.0,524288.0,255343.0,32768.0,514602,0,0,11124,131072.0,131072.0,0.0,131072.0,64,0x7f49fad2cec0,0,0,0,995471,0,0,0,1188419,0,0,0,1162214,0,0,0,1119449,0,0,0,1064991,141,0,0,1241005,0,0,0,1112744,0,0,0,1146304,0,0,0,991149,0,0,0,975572,0,0,0,1124745,0,0,0,1146696,0,0,0,1092856,0,0,0,1138712,59,0,0,1168001,128,0,0,1249807,0,0,0,1047697,0,0,0,1114799,0,0,0,1086495,0,0,0,1186054,0,0,0,1025214,50,0,0,1143171,0,0,0,1163409,11,0,0,1247356,0,0,0,1145547,0,0,0,949939,0,0,0,968318,0,0,0,1164988,0,0,0,1138563,0,0,0,1036491,22,0,0,1020700,277,0,0,1264387,64,0x7f8937e1cec0,0,393216,163840,0,0,0,0,0,17622,0.0,0.0,0.0,32768.0,0.0,0.0,394.0,32768.0,4096,16384,352,27084,1285,0,56.0,3.0,0.0,204781.0,64,0x7f9b3c4b8ec0,2238,4096,2238,6334,2306,4096,2306,6402,2290,4096,2290,6386,2336,4096,2336,6432,2243,4096,2243,6339,2274,4096,2274,6370,2283,4096,2283,6379,2315,4096,2315,6411,2314,4096,2314,6410,2236,4096,2236,6332,2311,4096,2311,6407,2291,4096,2291,6387,2340,4096,2340,6436,2245,4098,2247,6343,2275,4096,2275,6371,2286,4096,2286,6382,2310,4096,2310,6406,2314,4097,2315,6411,2261,4096,2261,6357,2259,4096,2259,6355,2320,4096,2320,6416,2326,4096,2326,6422,2219,4097,2220,6316,2455,4099,2458,6554,2236,4096,2236,6332,2314,4096,2314,6410,2317,4101,2322,6418,2262,4096,2262,6358,2263,4096,2263,6359,2317,4096,2317,6413,2325,4096,2325,6421,2219,4096,2219,6315,64,0x7fe3ae6f0ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,946842.0,64,0x7feea7214ec0,114688,0,32768,32768,16384,16384,65536,49152,28401315.0,84745583.0,37489688.0,131072.0,0.0,239425.0,0,0,15693,907.0,131080.0,0.0,8.0,64,0x7f2d49e28ec0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,0,27332,0,0,64,0x7f65d0258ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,34459.0,46034.0,19502.0,1412702536508356,1412702536528996 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fb673fe4ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20651,0,2714,38531,0,70103.0,131072.0,0.0,45638.0,64,0x7f3d464b0ec0,0,179554,0,0,65536,63800,56,1680,64,0x7fa4eb060ec0,4097,0,0,0,4096,0,67,0,4096,0,20,0,4096,0,409,0,4096,0,33,0,4096,0,433,0,4096,0,171,0,4096,0,0,0,4096,0,315,0,4096,0,0,0,4096,0,0,0,4099,0,1,0,4096,0,1989,0,4096,0,22,0,4096,0,114,0,4096,0,0,0,4096,0,663,0,4096,0,244,0,4097,0,0,0,4096,0,0,0,4096,0,2673,0,4097,0,627,0,4096,0,641,0,4097,0,22,0,4097,0,51,0,4100,0,333,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,231,0,4096,0,1554,0,4096,0,12,0,64,0x7f82a1118ec0,32768,32768,0,64,0x7f67fc544ec0,0,3487235,2828,2828,0,4157595,2872,2872,0,4088459,2836,2836,0,4512823,2824,2824,0,4479294,2878,2878,0,3963567,2852,2852,0,3372890,2868,2868,0,3863964,2834,2834,0,3602988,2836,2836,0,3323349,2828,2828,0,4987976,2872,2872,0,2990246,2844,2844,0,2897963,2824,2824,0,3854347,2888,2888,0,3440634,2854,2854,0,3526410,2868,2868,0,3358045,2820,2820,0,4643620,2844,2844,0,3967100,2856,2856,0,3785664,2840,2840,0,3645224,2826,2826,0,4421071,2852,2852,0,3343544,2808,2808,0,4425104,2840,2840,0,4030783,2844,2844,0,4081144,2816,2816,0,3548386,2844,2844,0,3739971,2856,2856,0,3801765,2840,2840,0,3033956,2826,2826,0,3330640,2846,2846,0,3339400,2812,2812,64,0x7fbea6bd8ec0,0,0,0,56,0,65536,65536,0,64,0x7f2c2b190ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fdff74f8ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32154,28129,9481,2411,0,39238,200670.0,0.0,69589.0,131081.0,64,0x7fd58c9c8ec0,6267,0,4096,6275,0,4096,6292,0,4096,6275,0,4096,6247,0,4096,6261,0,4096,6269,0,4096,6256,0,4096,6259,0,4096,6268,0,4096,6280,0,4096,6291,0,4096,6274,0,4096,6246,0,4096,6257,0,4096,6272,0,4096,6250,0,4096,6293,0,4096,6256,0,4096,6279,0,4096,6240,0,4096,6248,0,4096,6256,0,4096,6276,0,4096,6283,0,4096,6254,0,4096,6295,0,4096,6259,0,4096,6280,0,4096,6236,0,4096,6252,0,4096,6261,0,4096,64,0x7f6bf1be8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119179051.0,58335835.0,0.0,64,0x7f062f654ec0,329064,220427,16384,0,16384,16384,32768,49152,41132,41132,3142976.0,2471730.0,4711.0,343556.0,1697502.0,0.0,2459586.0,2150625.0,329056,230249,41132,0,41132,0,1316224.0,782876.0,0.0,0.0,64,0x7fd082a6cec0,17881422,17248930,288428,344064,2587800,0,0,163840,0.0,524288.0,0.0,524288.0,474695.0,32768.0,787304,0,0,11358,91554.0,91554.0,0.0,91554.0,64,0x7f49fad2cec0,0,0,0,1666654,98,0,0,1875833,40,0,0,1709646,0,0,0,1629090,148,0,0,1856096,58,0,0,2022763,0,0,0,1415869,105,0,0,2097760,0,0,0,1859235,0,0,0,1663611,63,0,0,1935808,0,0,0,1816118,0,0,0,1602485,233,0,0,2099153,19,0,0,1814938,224,0,0,2156601,211,0,0,2217762,0,0,0,1607370,32,0,0,1861661,0,0,0,1681311,0,0,0,1513007,182,0,0,2107928,55,0,0,1794652,35,0,0,2087197,10,0,0,1638307,0,0,0,1731125,86,0,0,1942387,0,0,0,1598553,323,0,0,2226062,354,0,0,2213475,0,0,0,1878880,130,0,0,2170632,64,0x7f8937e1cec0,0,393216,163840,0,0,0,0,0,27594,0.0,0.0,0.0,32768.0,0.0,0.0,214.0,32768.0,4096,16384,302,36916,1988,0,56.0,0.0,0.0,200227.0,64,0x7f9b3c4b8ec0,2176,4096,2176,6272,2201,4096,2201,6297,2170,4096,2170,6266,2190,4098,2192,6288,2184,4096,2184,6280,2180,4096,2180,6276,2215,4096,2215,6311,2160,4096,2160,6256,2164,4096,2164,6260,2178,4096,2178,6274,2204,4096,2204,6300,2173,4096,2173,6269,2196,4096,2196,6292,2186,4097,2187,6283,2183,4096,2183,6279,2218,4096,2218,6314,2185,4096,2185,6281,2170,4097,2171,6267,2206,4096,2206,6302,2178,4097,2179,6275,2169,4096,2169,6265,2189,4096,2189,6285,2176,4097,2177,6273,2227,4097,2228,6324,2171,4096,2171,6267,2189,4096,2189,6285,2171,4099,2174,6270,2207,4097,2208,6304,2180,4096,2180,6276,2173,4096,2173,6269,2192,4096,2192,6288,2179,4096,2179,6275,64,0x7fe3ae6f0ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2073299.0,64,0x7feea7214ec0,114688,0,32768,32768,16384,16384,65536,49152,59047744.0,196997604.0,50613057.0,131072.0,0.0,472196.0,0,0,23000,4178.0,131073.0,0.0,0.0,64,0x7f2d49e28ec0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,0,40580,0,0,64,0x7f65d0258ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,79022.0,45630.0,0.0,1412702536548036,1412702536563556 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fb673fe4ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21801,0,2701,39836,0,70275.0,131072.0,0.0,45685.0,64,0x7f3d464b0ec0,0,184306,0,0,65536,63800,56,1680,64,0x7fa4eb060ec0,4097,0,1182,0,4096,0,316,0,4096,0,0,0,4096,0,54,0,4096,0,1173,0,4096,0,176,0,4096,0,546,0,4096,0,773,0,4096,0,478,0,4096,0,455,0,4096,0,102,0,4099,0,0,0,4096,0,171,0,4096,0,126,0,4096,0,90,0,4096,0,914,0,4096,0,432,0,4096,0,670,0,4097,0,254,0,4096,0,125,0,4096,0,197,0,4097,0,679,0,4096,0,1137,0,4097,0,19,0,4097,0,0,0,4099,0,705,0,4096,0,546,0,4096,0,1564,0,4096,0,2,0,4096,0,0,0,4096,0,69,0,4096,0,26,0,64,0x7f82a1118ec0,32768,32768,0,64,0x7f67fc544ec0,0,3668257,2808,2808,0,4217226,2856,2856,0,3789386,2848,2848,0,4130933,2864,2864,0,3640120,2832,2832,0,3540081,2832,2832,0,4046394,2888,2888,0,4295731,2844,2844,0,3909283,2844,2844,0,3169180,2808,2808,0,3431764,2856,2856,0,3765707,2848,2848,0,3398915,2864,2864,0,3380048,2832,2832,0,3167392,2832,2832,0,4459113,2880,2880,0,4130513,2844,2844,0,4483482,2864,2864,0,3837105,2836,2836,0,4082336,2828,2828,0,4527583,2820,2820,0,4437303,2888,2888,0,3418107,2794,2794,0,4154890,2804,2804,0,4694477,2804,2804,0,4509477,2842,2842,0,3883648,2868,2868,0,2762080,2836,2836,0,4059679,2826,2826,0,3222971,2820,2820,0,3903307,2884,2884,0,3513115,2796,2796,64,0x7fbea6bd8ec0,0,0,0,56,0,65536,65536,0,64,0x7f2c2b190ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fdff74f8ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31161,27156,9537,2513,0,39174,200815.0,0.0,69734.0,131081.0,64,0x7fd58c9c8ec0,6251,0,4096,6249,0,4096,6250,0,4096,6275,0,4096,6280,0,4096,6249,0,4096,6238,0,4096,6265,0,4096,6265,0,4096,6251,0,4096,6247,0,4096,6254,0,4096,6268,0,4096,6281,0,4096,6249,0,4096,6238,0,4096,6258,0,4096,6254,0,4096,6254,0,4096,6248,0,4096,6240,0,4096,6267,0,4096,6259,0,4096,6273,0,4096,6277,0,4096,6259,0,4096,6253,0,4096,6258,0,4096,6249,0,4096,6242,0,4096,6270,0,4096,6258,0,4096,64,0x7f6bf1be8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,123714249.0,60701513.0,0.0,64,0x7f062f654ec0,325808,219172,16384,0,16384,16384,32768,49152,40725,40725,3122002.0,2448600.0,4872.0,362032.0,1782958.0,0.0,2436301.0,2125631.0,325800,227537,40725,0,40725,0,1303200.0,769688.0,0.0,0.0,64,0x7fd082a6cec0,19619111,18310872,964175,344064,2767095,0,0,163840,832.0,515136.0,0.0,524288.0,667696.0,32768.0,1043259,0,0,14106,91236.0,91236.0,0.0,91236.0,64,0x7f49fad2cec0,169,0,0,1930926,418,0,0,1897548,465,0,0,1912786,1142,0,0,2287886,1670,0,0,2065022,0,0,0,1959511,543,0,0,1877636,1312,0,0,2278650,980,0,0,1967219,345,0,0,1762118,181,0,0,2085339,144,0,0,1751113,104,0,0,1960605,94,0,0,1652767,180,0,0,2006293,812,0,0,2297233,283,0,0,1933496,584,0,0,2328019,330,0,0,2036734,3551,0,0,2715057,1246,0,0,2242440,996,0,0,2232321,156,0,0,1617406,0,0,0,2110286,0,0,0,1586728,435,0,0,1767845,187,0,0,1903314,0,0,0,1818125,729,0,0,2288702,56,0,0,1673504,1367,0,0,2235658,267,0,0,2012861,64,0x7f8937e1cec0,0,393216,163840,0,0,0,0,0,29726,0.0,0.0,0.0,32768.0,0.0,0.0,218.0,32768.0,4096,16384,302,40835,1949,0,56.0,7.0,0.0,200499.0,64,0x7f9b3c4b8ec0,2180,4096,2180,6276,2179,4096,2179,6275,2158,4096,2158,6254,2180,4098,2182,6278,2191,4096,2191,6287,2180,4096,2180,6276,2154,4096,2154,6250,2167,4096,2167,6263,2172,4096,2172,6268,2179,4096,2179,6275,2178,4096,2178,6274,2161,4096,2161,6257,2186,4096,2186,6282,2201,4097,2202,6298,2184,4096,2184,6280,2151,4096,2151,6247,2161,4096,2161,6257,2205,4097,2206,6302,2172,4096,2172,6268,2179,4097,2180,6276,2160,4096,2160,6256,2178,4096,2178,6274,2179,4097,2180,6276,2232,4097,2233,6329,2182,4096,2182,6278,2163,4096,2163,6259,2208,4099,2211,6307,2173,4097,2174,6270,2179,4096,2179,6275,2167,4096,2167,6263,2181,4096,2181,6277,2182,4096,2182,6278,64,0x7fe3ae6f0ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2098145.0,64,0x7feea7214ec0,114688,0,32768,32768,16384,16384,65536,49152,60806005.0,203361326.0,47991410.0,131072.0,0.0,573104.0,0,0,26036,2107.0,131081.0,0.0,16.0,64,0x7f2d49e28ec0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,0,40160,0,0,64,0x7f65d0258ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,83989.0,45611.0,0.0,1412702536625636,1412702536642116 diff --git a/tests/workloads/device_filter/MI200/roofline.csv b/tests/workloads/device_filter/MI200/roofline.csv index f9b85b413e..717503e7c3 100644 --- a/tests/workloads/device_filter/MI200/roofline.csv +++ b/tests/workloads/device_filter/MI200/roofline.csv @@ -1,2 +1,2 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.6548,1388.108,1389.2015,5015.9297,5012.8184,5019.041,9223.8145,9223.0537,9224.5752,18052.502,18051.623,18053.381,20935.658,20875.303,20996.014,20266.73,20266.039,20267.422,170456.62,170450.44,170462.81,164889.83,164885.14,164894.52,41426.273,41425.676,41426.871,41480.551,41480.051,41481.051,166346.09,165855.02,166837.17 +0,1388.7948,1388.2125,1389.3771,5016.1738,5013.2036,5019.144,9226.4229,9225.7852,9227.0605,17715.307,17712.113,17718.5,20942.453,20882.1,21002.807,20272.682,20272.182,20273.182,170487.92,170484.22,170491.62,164932.06,164926.69,164937.44,41438.844,41438.195,41439.492,41498.918,41498.344,41499.492,166413.58,165921.97,166905.19 diff --git a/tests/workloads/device_filter/MI200/sysinfo.csv b/tests/workloads/device_filter/MI200/sysinfo.csv index 2819017c4f..3f85440ab2 100644 --- a/tests/workloads/device_filter/MI200/sysinfo.csv +++ b/tests/workloads/device_filter/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -device_filter,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:29:36 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +device_filter,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:35:56 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/device_filter/MI200/timestamps.csv b/tests/workloads/device_filter/MI200/timestamps.csv index fa4e99ac33..6c85ccd5ad 100644 --- a/tests/workloads/device_filter/MI200/timestamps.csv +++ b/tests/workloads/device_filter/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780746738,199121780771567,199121780791247,199121780807012 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780801932,199121780810127,199121780825807,199121780887234 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,334902,334902,1048576,256,0,0,8,0,16,64,0x0,0x7fc789a84ec0,199121780836327,199121780890127,199121780906607,199121780907502 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4159385,4159385,1048576,256,0,0,8,0,16,64,0x0,0x7f7aee850ec0,1412702536482286,1412702536508356,1412702536528996,1412702536542951 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4159385,4159385,1048576,256,0,0,8,0,16,64,0x0,0x7f7aee850ec0,1412702536540095,1412702536548036,1412702536563556,1412702536623202 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4159385,4159385,1048576,256,0,0,8,0,16,64,0x0,0x7f7aee850ec0,1412702536574069,1412702536625636,1412702536642116,1412702536643421 diff --git a/tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv index 9336186cbd..2a4e83a1cc 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,47824,47824,16384,65536,14415,1841604,194245701996654,194257894802798,194257894826478,194245709757699 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,42607,42607,16384,65536,8172,1048580,194245709780272,194257894909678,194257894929198,194245710148639 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163106,163106,1048576,256,0,0,8,8,16,64,0x0,0x7fd0d59ece80,42359,42359,16384,65536,8301,1048580,194245710180850,194257894949838,194257894968558,194245710367043 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1258700,1258700,1048576,256,0,0,8,8,16,64,0x0,0x7f801c880ec0,48936,48936,16384,65536,14799,1880476,1410167129401874,1410178815497695,1410178815522495,1410167137099481 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1258700,1258700,1048576,256,0,0,8,8,16,64,0x0,0x7f801c880ec0,42186,42186,16384,65536,8222,1048592,1410167137124759,1410178815542975,1410178815562015,1410167137378738 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1258700,1258700,1048576,256,0,0,8,8,16,64,0x0,0x7f801c880ec0,42316,42316,16384,65536,8221,1048584,1410167137410247,1410178815623775,1410178815642655,1410167137580208 diff --git a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv index ee64ae70f6..17d7fadd1f 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246201989340,194257894802798,194257894826478,194246209682066 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246209701843,194257894909678,194257894929198,194246209982224 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163295,163295,1048576,256,0,0,8,8,16,64,0x0,0x7f1c0fd10e80,0,0,0,194246210010568,194257894949838,194257894968558,194246210167986 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1258888,1258888,1048576,256,0,0,8,8,16,64,0x0,0x7fe5d42a0ec0,0,0,0,1410167602796952,1410178815497695,1410178815522495,1410167610304281 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1258888,1258888,1048576,256,0,0,8,8,16,64,0x0,0x7fe5d42a0ec0,0,0,0,1410167610324359,1410178815542975,1410178815562015,1410167610647999 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1258888,1258888,1048576,256,0,0,8,8,16,64,0x0,0x7fe5d42a0ec0,0,0,0,1410167610676222,1410178815623775,1410178815642655,1410167610853958 diff --git a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv index 4ac1a5e172..128f30dd8f 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,202308,25952544,194246693370130,194257894802798,194257894826478,194246701328779 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,182670,23344896,194246701348828,194257894909678,194257894929198,194246701641622 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163481,163481,1048576,256,0,0,8,8,16,64,0x0,0x7f41294aee80,65536,181360,23270400,194246701670366,194257894949838,194257894968558,194246701840689 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1259074,1259074,1048576,256,0,0,8,8,16,64,0x0,0x7fb789834ec0,65536,202864,26025240,1410168079709865,1410178815497695,1410178815522495,1410168087360905 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1259074,1259074,1048576,256,0,0,8,8,16,64,0x0,0x7fb789834ec0,65536,174246,22311240,1410168087381153,1410178815542975,1410178815562015,1410168087724951 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1259074,1259074,1048576,256,0,0,8,8,16,64,0x0,0x7fb789834ec0,65536,172432,22133472,1410168087753315,1410178815623775,1410178815642655,1410168087940107 diff --git a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv index 5df6e22d20..db731ce0b1 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,645357,82598164,194247183554014,194257894802798,194257894826478,194247191243955 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,670028,85765020,194247191265515,194257894909678,194257894929198,194247191518214 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163664,163664,1048576,256,0,0,8,8,16,64,0x0,0x7f0703804e80,32768,644220,82464252,194247191549022,194257894949838,194257894968558,194247191732850 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1259257,1259257,1048576,256,0,0,8,8,16,64,0x0,0x7efca8c4cec0,32768,619812,79322476,1410168553148666,1410178815497695,1410178815522495,1410168560839471 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1259257,1259257,1048576,256,0,0,8,8,16,64,0x0,0x7efca8c4cec0,32768,672501,86073620,1410168560860901,1410178815542975,1410178815562015,1410168561160366 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1259257,1259257,1048576,256,0,0,8,8,16,64,0x0,0x7efca8c4cec0,32768,653970,83703936,1410168561188710,1410178815623775,1410178815642655,1410168561366956 diff --git a/tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv index 91bf93a983..8684064711 100644 --- a/tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,48152,48152,17278,385224,16384,24999057,233984,0,100494368,194247678463586,194257894802798,194257894826478,194247686158065 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,42999,42999,13485,344000,16384,25054375,233600,0,100720288,194247686185978,194257894909678,194257894929198,194247686516484 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,163849,163849,1048576,256,0,0,8,8,16,64,0x0,0x7f24c9b52e80,43151,43151,13780,345216,16384,23923902,232092,0,96192684,194247686554565,194257894949838,194257894968558,194247686738744 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1259442,1259442,1048576,256,0,0,8,8,16,64,0x0,0x7fbda6074ec0,48635,48635,18326,389088,16384,24577632,235420,0,98846104,1410169028962927,1410178815497695,1410178815522495,1410169036445289 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1259442,1259442,1048576,256,0,0,8,8,16,64,0x0,0x7fbda6074ec0,41605,41605,13181,332848,16384,23608799,226270,0,94967360,1410169036474975,1410178815542975,1410178815562015,1410169036807712 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1259442,1259442,1048576,256,0,0,8,8,16,64,0x0,0x7fbda6074ec0,41728,41728,13800,333832,16384,23454903,231784,0,94343436,1410169036845844,1410178815623775,1410178815642655,1410169037034279 diff --git a/tests/workloads/device_inv_int/MI100/log.txt b/tests/workloads/device_inv_int/MI100/log.txt new file mode 100644 index 0000000000..029cc963c4 --- /dev/null +++ b/tests/workloads/device_inv_int/MI100/log.txt @@ -0,0 +1,679 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/device_inv_int/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155353' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155353_1258540' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155353_1258540/input0_results_240321_155353' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155353_1258540/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155353_1258540/input0_results_240321_155353 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155353' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155353_1258728' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155353_1258728/input0_results_240321_155353' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155353_1258728/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155353_1258728/input0_results_240321_155353 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155354' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155354_1258914' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155354_1258914/input0_results_240321_155354' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155354_1258914/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155354_1258914/input0_results_240321_155354 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155354' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155354_1259097' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155354_1259097/input0_results_240321_155354' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155354_1259097/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155354_1259097/input0_results_240321_155354 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155355' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155355_1259282' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155355_1259282/input0_results_240321_155355' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155355_1259282/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155355_1259282/input0_results_240321_155355 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155355' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155355_1259466' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155355_1259466/input0_results_240321_155355' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155355_1259466/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155355_1259466/input0_results_240321_155355 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155355' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155355_1259649' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155355_1259649/input0_results_240321_155355' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155355_1259649/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155355_1259649/input0_results_240321_155355 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155356' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155356_1259832' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155356_1259832/input0_results_240321_155356' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155356_1259832/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155356_1259832/input0_results_240321_155356 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155356' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155356_1260018' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155356_1260018/input0_results_240321_155356' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155356_1260018/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155356_1260018/input0_results_240321_155356 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155357' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155357_1260201' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155357_1260201/input0_results_240321_155357' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155357_1260201/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155357_1260201/input0_results_240321_155357 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155358' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155358_1260385' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155358_1260385/input0_results_240321_155358' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155358_1260385/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155358_1260385/input0_results_240321_155358 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155358' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155358_1260569' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155358_1260569/input0_results_240321_155358' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155358_1260569/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155358_1260569/input0_results_240321_155358 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155359' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155359_1260752' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155359_1260752/input0_results_240321_155359' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155359_1260752/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155359_1260752/input0_results_240321_155359 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155400' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155400_1260935' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155400_1260935/input0_results_240321_155400' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155400_1260935/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155400_1260935/input0_results_240321_155400 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155401' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155401_1261120' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155401_1261120/input0_results_240321_155401' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155401_1261120/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155401_1261120/input0_results_240321_155401 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155401' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155401_1261307' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155401_1261307/input0_results_240321_155401' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155401_1261307/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155401_1261307/input0_results_240321_155401 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155401' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155401_1261503' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155401_1261503/input0_results_240321_155401' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155401_1261503/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155401_1261503/input0_results_240321_155401 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155402' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155402_1261690' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155402_1261690/input0_results_240321_155402' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155402_1261690/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155402_1261690/input0_results_240321_155402 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155402' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155402_1261891' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155402_1261891/input0_results_240321_155402' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155402_1261891/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155402_1261891/input0_results_240321_155402 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155403' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155403_1262078' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155403_1262078/input0_results_240321_155403' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155403_1262078/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155403_1262078/input0_results_240321_155403 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155403' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155403_1262261' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155403_1262261/input0_results_240321_155403' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155403_1262261/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155403_1262261/input0_results_240321_155403 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155404' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155404_1262461' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155404_1262461/input0_results_240321_155404' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155404_1262461/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155404_1262461/input0_results_240321_155404 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155404' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155404_1262661' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155404_1262661/input0_results_240321_155404' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155404_1262661/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155404_1262661/input0_results_240321_155404 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/device_inv_int/MI100/pmc_dispatch_info.csv b/tests/workloads/device_inv_int/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/device_inv_int/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/device_inv_int/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/device_inv_int/MI100/pmc_perf.csv b/tests/workloads/device_inv_int/MI100/pmc_perf.csv index 630c08cd36..847784d36f 100644 --- a/tests/workloads/device_inv_int/MI100/pmc_perf.csv +++ b/tests/workloads/device_inv_int/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_1,obj_1,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,TCC_EA_ATOMIC_LEVEL_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_7,obj_7,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_8,obj_8,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fcf0932ee80,131072.0,131072.0,0.0,2566886.0,0.0,0.0,121840349.0,58445288.0,64,0x7ff44e090e80,0,4527760,4096,4096,0,3555075,4096,4096,0,2775410,4096,4096,0,3418968,4096,4096,0,4238708,4096,4096,0,2987453,4096,4096,0,3716834,4096,4096,0,4981364,4096,4096,0,3278531,4096,4096,0,3073029,4096,4096,0,3931357,4096,4096,0,4760082,4096,4096,0,2991096,4096,4096,0,4375993,4096,4096,0,4199466,4096,4096,0,3009560,4096,4096,0,3287903,4096,4096,0,3971461,4096,4096,0,4254037,4096,4096,0,4627029,4096,4096,0,3949698,4096,4096,0,4293693,4096,4096,0,4053840,4096,4096,0,3067426,4096,4096,0,3522697,4096,4096,0,3575519,4096,4096,0,5577921,4096,4096,0,3023500,4096,4096,0,4493256,4096,4096,0,3531987,4096,4096,0,3123815,4096,4096,0,2809669,4096,4096,64,0x7f5c6c79ee80,2197,0,0,1825758,3688,0,0,1993202,1773,0,0,1767972,6611,0,0,2229155,1848,0,0,1799238,964,0,0,1727628,3278,0,0,1973798,2685,0,0,1887535,1931,0,0,1888618,1815,0,0,1857040,1007,0,0,1755433,1417,0,0,1761046,2480,0,0,1921293,5265,0,0,2122584,1286,0,0,1761950,6088,0,0,2184448,3078,0,0,1963396,593,0,0,1645137,4360,0,0,2094990,3224,0,0,1923765,2123,0,0,1986131,4211,0,0,2047900,722,0,0,1619918,6858,0,0,2157641,2635,0,0,1899838,1951,0,0,1856611,3161,0,0,1952531,4438,0,0,2024809,2658,0,0,1902416,2845,0,0,1885019,2557,0,0,1994981,3414,0,0,2025850,64,0x7f45b1126e80,0.0,64,0x7fce2156ae80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8469,4373,8469,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fcddb37ae80,187897,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13344,29728,9915,550,0,45970,262612.0,0.0,188.0,262424.0,64,0x7f1f422b4e80,1833987,360448,163840,0,0,180224,114688,0,67918409.0,194039889.0,69898979.0,131072.0,0.0,683023.0,0,0,26884,85053.0,0.0,0.0,85053.0,64,0x7f0aeb206e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86526.0,44546.0,131111.0,0.0,64,0x7f0a32744e80,0,0,192,0,65536,64413,48,1376,31580,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47664,1753,0,48.0,263.0,0.0,262288.0,64,0x7ff35b1e8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48080,0,131680.0,131072.0,0.0,131104.0,64,0x7f7b58daae80,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,0,48212,0,0,64,0x7f36ddc8ae80,32768,0,0,0,16384,16384,393216,23005499,960.0,513903.0,0.0,524288.0,889072.0,32768.0,0,0,0,16742,131072.0,131072.0,0.0,131072.0,64,0x7f2f61292e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,46844.0,117046.0,64,0x7fcaef4e6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131345.0,0.0,538.0,131344.0,64,0x7f64f24f6e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6a2c826e80,4096,0,5848,0,4229,0,5984,0,4099,0,3303,0,4096,0,3660,0,4096,0,1999,0,4096,0,5546,0,4096,0,139,0,4096,0,3715,0,4144,0,416,0,4096,0,904,0,4144,0,1979,0,4096,0,2160,0,4096,0,0,0,4096,0,0,0,4096,0,2882,0,4096,0,0,0,4097,0,234,0,4096,0,3518,0,4096,0,4635,0,4096,0,356,0,4096,0,5351,0,4096,0,0,0,4096,0,3151,0,4144,0,88,0,4096,0,0,0,4096,0,174,0,4096,0,711,0,4096,0,557,0,4096,0,742,0,4096,0,353,0,4096,0,5158,0,4096,0,488,0,64,0x7f621b26ee80,380000,230046,3335699,16384,24097627,144,48,0,47499,47499,3803607.0,2960470.0,6886.0,1090442.0,2081779.0,0.0,2949969.0,2640041.0,378543,240004,47499,0,47499,0,1519968.0,970987.0,0.0,0.0,194257894802798,194257894826478 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fcf0932ee80,131072.0,131072.0,0.0,2611149.0,0.0,0.0,113086249.0,45751167.0,64,0x7ff44e090e80,0,3365818,2708,2708,0,4226863,2718,2718,0,3622979,2678,2678,0,3211610,2726,2726,0,4633233,2696,2696,0,3700931,2717,2717,0,4413258,2686,2686,0,3805762,2716,2716,0,3549104,2678,2678,0,4663676,2686,2686,0,4215530,2684,2684,0,4818752,2728,2728,0,3003802,2726,2726,0,3212344,2666,2666,0,3408405,2678,2678,0,3409004,2700,2700,0,4631889,2694,2694,0,5387890,2684,2684,0,3501197,2660,2660,0,4252721,2704,2704,0,4940336,2710,2710,0,4423994,2734,2734,0,4513618,2672,2672,0,3806442,2700,2700,0,3168336,2706,2706,0,3137423,2717,2717,0,3735098,2712,2712,0,3082439,2704,2704,0,3313063,2694,2694,0,2985552,2712,2712,0,3723447,2708,2708,0,4554880,2716,2716,64,0x7f5c6c79ee80,3477,0,0,1677901,2673,0,0,1543497,1180,0,0,1282168,2236,0,0,1399042,1649,0,0,1385229,325,0,0,1231987,4929,0,0,1784217,2176,0,0,1445048,1069,0,0,1387247,820,0,0,1291456,3516,0,0,1656123,1911,0,0,1511916,2515,0,0,1575273,2180,0,0,1418914,7771,0,0,2010820,5681,0,0,1707998,746,0,0,1329781,216,0,0,1255758,3485,0,0,1668061,3640,0,0,1657957,2850,0,0,1456156,973,0,0,1447484,2838,0,0,1510469,2073,0,0,1419852,394,0,0,1231310,2176,0,0,1495991,1637,0,0,1358263,3335,0,0,1573230,2517,0,0,1459606,2698,0,0,1458964,4793,0,0,1701931,1749,0,0,1319873,64,0x7f45b1126e80,0.0,64,0x7fce2156ae80,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8445,4349,8445,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fcddb37ae80,186426,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11130,27514,8753,2874,0,41283,262414.0,0.0,47.0,262367.0,64,0x7f1f422b4e80,1309158,360448,163840,0,0,180224,114688,0,69824744.0,186221412.0,69391074.0,131072.0,0.0,591139.0,0,0,25286,66142.0,0.0,0.0,66142.0,64,0x7f0aeb206e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86455.0,44617.0,131110.0,0.0,64,0x7f0a32744e80,0,0,48,0,65536,65536,0,0,30644,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,482,45503,4141,0,48.0,222.0,0.0,262144.0,64,0x7ff35b1e8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2757,40308,0,131579.0,131072.0,0.0,86936.0,64,0x7f7b58daae80,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,0,38719,0,0,64,0x7f36ddc8ae80,32768,0,0,0,16384,16384,393216,22341817,960.0,514039.0,0.0,524288.0,1021354.0,32768.0,0,0,0,13651,86557.0,86557.0,0.0,86557.0,64,0x7f2f61292e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,53083.0,120688.0,64,0x7fcaef4e6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131770.0,0.0,1390.0,131767.0,64,0x7f64f24f6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6a2c826e80,4096,0,3298,0,4247,0,698,0,4096,0,0,0,4097,0,521,0,4096,0,3129,0,4096,0,1065,0,4096,0,344,0,4096,0,1864,0,4144,0,916,0,4096,0,1289,0,4144,0,1859,0,4096,0,4737,0,4096,0,6859,0,4097,0,203,0,4096,0,12,0,4096,0,242,0,4097,0,836,0,4098,0,1802,0,4096,0,382,0,4096,0,635,0,4096,0,1750,0,4096,0,5598,0,4096,0,0,0,4144,0,0,0,4096,0,2506,0,4096,0,2897,0,4096,0,0,0,4096,0,2951,0,4096,0,1501,0,4096,0,0,0,4096,0,610,0,4096,0,478,0,64,0x7f621b26ee80,383976,255497,3751630,16384,24605329,0,48,0,47996,47996,4121567.0,3589567.0,6010.0,1253940.0,2487457.0,0.0,3580777.0,3272539.0,383968,264629,47996,0,47996,1068,1535872.0,953280.0,3.0,0.0,194257894909678,194257894929198 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fcf0932ee80,131072.0,131072.0,0.0,2555628.0,0.0,0.0,116932893.0,46914420.0,64,0x7ff44e090e80,0,2825135,2720,2720,0,2686487,2711,2711,0,5260778,2696,2696,0,3193974,2746,2746,0,2909188,2682,2682,0,2633911,2761,2761,0,2131598,2706,2706,0,3632339,2748,2748,0,2695958,2664,2664,0,4889651,2732,2732,0,2469835,2709,2709,0,3587606,2758,2758,0,2843456,2696,2696,0,2612871,2714,2714,0,3059147,2700,2700,0,3021221,2733,2733,0,2716164,2684,2684,0,5232311,2738,2738,0,2529687,2716,2716,0,3210409,2726,2726,0,2943608,2670,2670,0,2491290,2786,2786,0,2593772,2706,2706,0,4393415,2702,2702,0,3411270,2692,2692,0,2517710,2756,2756,0,2051713,2714,2714,0,2861911,2728,2728,0,2619552,2690,2690,0,2610323,2727,2727,0,2385440,2724,2724,0,2800681,2716,2716,64,0x7f5c6c79ee80,1749,0,0,1435090,2262,0,0,1508459,1448,0,0,1416248,2213,0,0,1468240,2423,0,0,1596292,1450,0,0,1425724,596,0,0,1344216,1438,0,0,1431695,2907,0,0,1582506,1107,0,0,1412589,961,0,0,1355688,2393,0,0,1481766,4053,0,0,1690528,581,0,0,1297654,3106,0,0,1604022,2362,0,0,1450864,3135,0,0,1591297,1217,0,0,1324008,4426,0,0,1749904,1458,0,0,1382650,3663,0,0,1661357,1557,0,0,1463431,1532,0,0,1532500,1089,0,0,1324656,3061,0,0,1538480,482,0,0,1246056,1437,0,0,1424126,4059,0,0,1569945,2145,0,0,1553308,1849,0,0,1448343,1742,0,0,1469827,2632,0,0,1543838,64,0x7f45b1126e80,0.0,64,0x7fce2156ae80,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8357,4261,8357,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fcddb37ae80,152832,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12642,29026,8362,2338,0,40237,262413.0,0.0,47.0,262366.0,64,0x7f1f422b4e80,1573989,360448,163840,0,0,180224,114688,0,69279840.0,196075939.0,71851195.0,131072.0,0.0,680636.0,0,0,26233,83217.0,0.0,0.0,83217.0,64,0x7f0aeb206e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86617.0,0.0,131112.0,0.0,64,0x7f0a32744e80,0,0,48,0,65536,65536,0,0,30132,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41885,1692,0,48.0,217.0,0.0,262144.0,64,0x7ff35b1e8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3195,111310,158,131593.0,131072.0,0.0,86970.0,64,0x7f7b58daae80,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,0,42883,0,0,64,0x7f36ddc8ae80,32768,0,0,0,16384,16384,393216,22373479,960.0,513995.0,0.0,524288.0,901334.0,32768.0,0,0,0,13147,86574.0,86574.0,0.0,86574.0,64,0x7f2f61292e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,30492.0,96863.0,64,0x7fcaef4e6e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131347.0,0.0,548.0,131346.0,64,0x7f64f24f6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6a2c826e80,4096,0,2857,0,4237,0,1585,0,4096,0,1240,0,4097,0,0,0,4096,0,1583,0,4096,0,4907,0,4096,0,2012,0,4096,0,3220,0,4144,0,5275,0,4096,0,4725,0,4144,0,3382,0,4096,0,3280,0,4096,0,4613,0,4097,0,4372,0,4096,0,911,0,4096,0,0,0,4097,0,1525,0,4098,0,5923,0,4096,0,2246,0,4096,0,235,0,4096,0,5127,0,4096,0,3832,0,4096,0,1806,0,4144,0,0,0,4096,0,682,0,4096,0,4944,0,4096,0,2321,0,4096,0,94,0,4096,0,1560,0,4096,0,1020,0,4096,0,559,0,4096,0,633,0,64,0x7f621b26ee80,327464,228650,3346779,16384,23991293,0,48,0,40932,40932,3726932.0,3060657.0,5116.0,1064756.0,2179351.0,0.0,3051600.0,2742254.0,327456,237771,40932,0,40932,0,1309824.0,829271.0,0.0,0.0,194257894949838,194257894968558 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_1,obj_1,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_2,obj_2,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_4,obj_4,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_5,obj_5,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_12,obj_12,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_14,obj_14,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_15,obj_15,TCC_EA_ATOMIC_LEVEL_sum,wave_size_16,obj_16,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f394b3c8ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86608.0,44464.0,131111.0,0.0,64,0x7f1157048ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131373.0,0.0,594.0,131372.0,64,0x7f054d110ec0,32768,0,0,0,16384,16384,393216,22516793,960.0,513969.0,0.0,524288.0,1082088.0,32768.0,0,0,0,18009,131072.0,131072.0,0.0,131072.0,64,0x7f0d9a6e4ec0,131072.0,131072.0,0.0,2530193.0,0.0,0.0,130469136.0,60586854.0,64,0x7f1915260ec0,1976025,360448,163840,0,0,180224,114688,0,69974320.0,202984485.0,73836923.0,131072.0,0.0,663668.0,0,0,25943,81999.0,0.0,0.0,81999.0,64,0x7f94c4df8ec0,0,3704789,4096,4096,0,4662470,4096,4096,0,4005066,4096,4096,0,3897481,4096,4096,0,3492877,4096,4096,0,3126734,4096,4096,0,3038150,4096,4096,0,4157858,4096,4096,0,3910648,4096,4096,0,3643486,4096,4096,0,3376522,4096,4096,0,3973717,4096,4096,0,4405310,4096,4096,0,3556620,4096,4096,0,3111214,4096,4096,0,3337385,4096,4096,0,3641938,4096,4096,0,4553114,4096,4096,0,3229303,4096,4096,0,3622224,4096,4096,0,4630358,4096,4096,0,3633897,4096,4096,0,3203696,4096,4096,0,3713422,4096,4096,0,4096205,4096,4096,0,3472068,4096,4096,0,3849050,4096,4096,0,3266450,4096,4096,0,3902180,4096,4096,0,3552470,4096,4096,0,3197246,4096,4096,0,4060423,4096,4096,64,0x7f61bdfc0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47946,0,131541.0,131072.0,0.0,131104.0,64,0x7f0eedcb0ec0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,0,48359,0,0,64,0x7f8b51b14ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdebf20ec0,0,8192,4096,8192,0,8479,4383,8479,0,8192,4096,8192,188,8196,4288,8384,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f1da8644ec0,398008,244740,3532818,16384,25169958,144,48,0,49750,49750,4023076.0,3137724.0,6218.0,859488.0,2198593.0,0.0,3128097.0,2817347.0,396487,254666,49750,0,49750,0,1592000.0,991575.0,0.0,0.0,64,0x7f1a1620cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,13289.0,136659.0,64,0x7f8161e94ec0,0,0,192,0,65536,64418,48,1347,30689,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,46801,1825,0,48.0,171.0,0.0,262288.0,64,0x7f35a6df8ec0,3167,0,0,1923398,6455,0,0,2205548,4987,0,0,2013445,5689,0,0,2184677,5884,0,0,2078169,3966,0,0,1965045,6802,0,0,2196734,2387,0,0,1969294,2414,0,0,1801262,3074,0,0,1786513,6883,0,0,2190765,3620,0,0,1955596,7574,0,0,2231884,6086,0,0,2219420,4267,0,0,1968705,6154,0,0,2169545,4686,0,0,1994054,3065,0,0,1809151,6836,0,0,2148765,5041,0,0,2034865,7061,0,0,2176903,6252,0,0,2200927,7018,0,0,2143241,7862,0,0,2284143,3690,0,0,1928306,7575,0,0,2219552,6726,0,0,2173854,7653,0,0,2214824,6171,0,0,2094404,8318,0,0,2315275,7511,0,0,2237685,3330,0,0,1915440,64,0x7f6dc8558ec0,4096,0,2638,0,4096,0,1208,0,4097,0,1271,0,4099,0,1406,0,4096,0,971,0,4096,0,270,0,4096,0,1507,0,4096,0,1516,0,4096,0,375,0,4096,0,1291,0,4096,0,745,0,4096,0,2290,0,4096,0,2494,0,4096,0,2954,0,4096,0,4464,0,4096,0,1288,0,4096,0,5703,0,4096,0,6147,0,4096,0,2717,0,4096,0,653,0,4216,0,2598,0,4096,0,708,0,4096,0,5102,0,4096,0,1555,0,4096,0,1816,0,4217,0,3402,0,4096,0,635,0,4096,0,1070,0,4096,0,540,0,4096,0,726,0,4144,0,478,0,4144,0,2436,0,64,0x7efdb78b8ec0,0.0,64,0x7f9675324ec0,200706,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14008,30392,10321,588,0,46386,262539.0,0.0,188.0,262351.0,1410178815497695,1410178815522495 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f394b3c8ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,47148.0,42533.0,40468.0,0.0,64,0x7f1157048ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131089.0,0.0,32.0,131088.0,64,0x7f054d110ec0,32768,0,0,0,16384,16384,393216,22196520,0.0,524288.0,0.0,524288.0,760199.0,32768.0,0,0,0,20784,131072.0,131072.0,0.0,131072.0,64,0x7f0d9a6e4ec0,131072.0,131072.0,0.0,2579293.0,0.0,0.0,125150806.0,47099589.0,64,0x7f1915260ec0,1448593,360448,163840,0,0,180224,114688,0,70372025.0,181027155.0,73352132.0,131072.0,0.0,641090.0,0,0,25734,55732.0,0.0,0.0,55732.0,64,0x7f94c4df8ec0,0,4351823,2724,2724,0,3483284,2704,2704,0,3121933,2702,2702,0,3186633,2697,2697,0,3974459,2726,2726,0,3696253,2708,2708,0,3624260,2708,2708,0,4524009,2712,2712,0,4508251,2712,2712,0,3800637,2690,2690,0,3818434,2720,2720,0,4103593,2734,2734,0,4011090,2711,2711,0,4637963,2678,2678,0,4178002,2704,2704,0,3278641,2676,2676,0,4386837,2704,2704,0,4759071,2694,2694,0,3648135,2703,2703,0,4043161,2700,2700,0,4728536,2690,2690,0,3763496,2744,2744,0,3225754,2696,2696,0,2721871,2668,2668,0,4052185,2710,2710,0,3737660,2716,2716,0,3550664,2736,2736,0,3220081,2676,2676,0,4043580,2712,2712,0,3520159,2685,2685,0,3032959,2684,2684,0,3875483,2696,2696,64,0x7f61bdfc0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3401,39512,0,131396.0,131072.0,0.0,86596.0,64,0x7f0eedcb0ec0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,0,42455,0,0,64,0x7f8b51b14ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdebf20ec0,0,8192,4096,8192,0,8475,4379,8475,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8241,4145,8241,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f1da8644ec0,349072,236670,3452356,16384,25152532,0,48,0,43633,43633,3839396.0,3167416.0,6186.0,1037197.0,2326480.0,0.0,3158050.0,2848115.0,349064,246441,43633,0,43633,0,1396256.0,841490.0,0.0,0.0,64,0x7f1a1620cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,29863.0,118761.0,64,0x7f8161e94ec0,0,0,48,0,65536,65536,0,0,30140,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41446,1676,0,48.0,195.0,0.0,262144.0,64,0x7f35a6df8ec0,2291,0,0,1453849,6910,0,0,1803275,891,0,0,1355948,5750,0,0,1719347,1437,0,0,1421927,5528,0,0,1716968,2294,0,0,1536333,6920,0,0,1897785,5853,0,0,1868412,4169,0,0,1725696,5630,0,0,1789212,2986,0,0,1525852,2782,0,0,1490531,6143,0,0,1825258,1659,0,0,1523524,2882,0,0,1615109,4967,0,0,1765947,3105,0,0,1592657,730,0,0,1275458,5172,0,0,1716783,7682,0,0,1878861,7168,0,0,1864501,4134,0,0,1605329,7152,0,0,1823240,2287,0,0,1482347,4461,0,0,1676682,1864,0,0,1438473,6881,0,0,1859936,3149,0,0,1521891,5423,0,0,1746370,4683,0,0,1708507,2451,0,0,1434811,64,0x7f6dc8558ec0,4096,0,1171,0,4096,0,773,0,4097,0,0,0,4096,0,0,0,4096,0,5351,0,4096,0,100,0,4096,0,0,0,4096,0,1571,0,4096,0,1971,0,4096,0,3676,0,4096,0,386,0,4097,0,5783,0,4096,0,3163,0,4097,0,0,0,4096,0,4675,0,4096,0,110,0,4096,0,366,0,4096,0,7211,0,4096,0,2292,0,4098,0,3081,0,4216,0,606,0,4096,0,2832,0,4096,0,0,0,4096,0,367,0,4096,0,2408,0,4218,0,416,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,177,0,4144,0,0,0,4144,0,3546,0,64,0x7efdb78b8ec0,0.0,64,0x7f9675324ec0,188822,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12641,29025,8635,2420,0,40309,262353.0,0.0,47.0,262306.0,1410178815542975,1410178815562015 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f394b3c8ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86295.0,0.0,131112.0,0.0,64,0x7f1157048ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131383.0,0.0,620.0,131382.0,64,0x7f054d110ec0,32768,0,0,0,16384,16384,393216,22850828,960.0,513941.0,0.0,524288.0,908292.0,32768.0,0,0,0,15024,86353.0,86353.0,0.0,86353.0,64,0x7f0d9a6e4ec0,131072.0,131072.0,0.0,2580593.0,0.0,0.0,120479250.0,46475773.0,64,0x7f1915260ec0,1286796,360448,163840,0,0,180224,114688,0,71135042.0,199818787.0,74217385.0,131072.0,0.0,607261.0,0,0,25478,63258.0,0.0,0.0,63258.0,64,0x7f94c4df8ec0,0,3266048,2752,2752,0,4007512,2692,2692,0,3449751,2700,2700,0,3502063,2685,2685,0,3528435,2692,2692,0,3172588,2714,2714,0,3261266,2716,2716,0,3810453,2694,2694,0,3759141,2714,2714,0,3539735,2668,2668,0,3491354,2724,2724,0,3477421,2688,2688,0,3283853,2734,2734,0,3264932,2708,2708,0,3354387,2726,2726,0,3238121,2680,2680,0,3668210,2700,2700,0,3991835,2702,2702,0,3122189,2688,2688,0,3322570,2716,2716,0,4968419,2722,2722,0,3321645,2736,2736,0,3322243,2708,2708,0,3394966,2668,2668,0,3984675,2686,2686,0,3425530,2676,2676,0,3485372,2706,2706,0,3215908,2700,2700,0,3656565,2708,2708,0,3316687,2724,2724,0,3418035,2729,2729,0,4102515,2732,2732,64,0x7f61bdfc0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3359,39512,0,131428.0,131072.0,0.0,86553.0,64,0x7f0eedcb0ec0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,64,0x7f8b51b14ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdebf20ec0,0,8192,4096,8192,0,8479,4383,8479,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8241,4145,8241,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f1da8644ec0,348688,238694,3464820,16384,24994608,0,48,0,43585,43585,3869648.0,3183459.0,5560.0,975258.0,2339285.0,0.0,3174141.0,2864601.0,348680,248159,43585,0,43585,0,1394720.0,825560.0,0.0,0.0,64,0x7f1a1620cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,19300.0,109627.0,64,0x7f8161e94ec0,0,0,48,0,65536,65536,0,0,30399,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41962,1702,0,48.0,214.0,0.0,262144.0,64,0x7f35a6df8ec0,2837,0,0,1429952,2688,0,0,1484715,2569,0,0,1459722,7388,0,0,1844522,3369,0,0,1441352,913,0,0,1286922,4946,0,0,1714972,7764,0,0,1934942,1719,0,0,1360662,1538,0,0,1357935,6685,0,0,1784656,5236,0,0,1748367,3382,0,0,1512327,2446,0,0,1641530,2834,0,0,1611417,6957,0,0,1798081,3315,0,0,1470033,1023,0,0,1280911,2962,0,0,1484476,4670,0,0,1711471,3373,0,0,1514058,3445,0,0,1524704,5552,0,0,1700583,7781,0,0,1867977,2243,0,0,1454700,2031,0,0,1425674,6321,0,0,1801622,5014,0,0,1816021,4093,0,0,1578254,3343,0,0,1567976,4619,0,0,1657818,1853,0,0,1454663,64,0x7f6dc8558ec0,4096,0,5394,0,4096,0,1781,0,4097,0,1101,0,4096,0,1817,0,4096,0,4196,0,4096,0,2350,0,4096,0,1731,0,4096,0,4315,0,4096,0,852,0,4096,0,3550,0,4096,0,4527,0,4097,0,2846,0,4096,0,1616,0,4097,0,498,0,4096,0,2391,0,4096,0,1147,0,4096,0,4394,0,4096,0,3599,0,4096,0,1781,0,4098,0,914,0,4216,0,1164,0,4096,0,4192,0,4096,0,3606,0,4096,0,2504,0,4096,0,387,0,4233,0,3388,0,4096,0,735,0,4096,0,2788,0,4096,0,538,0,4096,0,6180,0,4144,0,0,0,4144,0,3928,0,64,0x7efdb78b8ec0,0.0,64,0x7f9675324ec0,190852,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,15046,31430,8655,2361,0,40447,262415.0,0.0,47.0,262368.0,1410178815623775,1410178815642655 diff --git a/tests/workloads/device_inv_int/MI100/sysinfo.csv b/tests/workloads/device_inv_int/MI100/sysinfo.csv index 7bbeb8f319..3beb72b6ec 100644 --- a/tests/workloads/device_inv_int/MI100/sysinfo.csv +++ b/tests/workloads/device_inv_int/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:30 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:53:52 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/device_inv_int/MI100/timestamps.csv b/tests/workloads/device_inv_int/MI100/timestamps.csv index 0ddc84a6d7..179ee599d5 100644 --- a/tests/workloads/device_inv_int/MI100/timestamps.csv +++ b/tests/workloads/device_inv_int/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894775994,194257894802798,194257894826478,194257894838072 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894839254,194257894909678,194257894929198,194257894930367 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,167187,167187,1048576,256,0,0,8,8,16,64,0x0,0x7f75a08c8e80,194257894941187,194257894949838,194257894968558,194257894969812 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1262821,1262821,1048576,256,0,0,8,8,16,64,0x0,0x7f366fb34ec0,1410178815466976,1410178815497695,1410178815522495,1410178815537880 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1262821,1262821,1048576,256,0,0,8,8,16,64,0x0,0x7f366fb34ec0,1410178815534784,1410178815542975,1410178815562015,1410178815636256 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1262821,1262821,1048576,256,0,0,8,8,16,64,0x0,0x7f366fb34ec0,1410178815573177,1410178815623775,1410178815642655,1410178815648288 diff --git a/tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv index eabfc56e56..67c10d8a8b 100644 --- a/tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,27912,27912,16384,65536,13514,1516880,198989177854165,199001894935363,199001894955843,198989193725590 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,41103,41103,16384,65536,9163,1048712,198989193746269,199001895045923,199001895062403,198989194045705 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320367,320367,1048576,256,0,0,8,0,16,64,0x0,0x7fc46ea24ec0,42248,42248,16384,65536,9321,1048688,198989194074961,199001895083363,199001895098883,198989194247106 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4144746,4144746,1048576,256,0,0,8,0,16,64,0x0,0x7ff86800cec0,27678,27678,16384,65536,13718,1552004,1412569418785866,1412582414437599,1412582414457599,1412569434785613 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4144746,4144746,1048576,256,0,0,8,0,16,64,0x0,0x7ff86800cec0,41715,41715,16384,65536,9728,1048636,1412569434805591,1412582414476479,1412582414491999,1412569435124494 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4144746,4144746,1048576,256,0,0,8,0,16,64,0x0,0x7ff86800cec0,42139,42139,16384,65536,9154,1048652,1412569435153789,1412582414551359,1412582414567679,1412569435328620 diff --git a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv index aca17b9215..64548b2cf8 100644 --- a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989659429121,199001894935363,199001894955843,198989675029403 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989675045944,199001895045923,199001895062403,198989675468113 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320552,320552,1048576,256,0,0,8,0,16,64,0x0,0x7fd2d0168ec0,0,0,0,198989675494523,199001895083363,199001895098883,198989675627705 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4144947,4144947,1048576,256,0,0,8,0,16,64,0x0,0x7f93fef18ec0,0,0,0,1412569904374106,1412582414437599,1412582414457599,1412569920255991 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4144947,4144947,1048576,256,0,0,8,0,16,64,0x0,0x7f93fef18ec0,0,0,0,1412569920277472,1412582414476479,1412582414491999,1412569920573351 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4144947,4144947,1048576,256,0,0,8,0,16,64,0x0,0x7f93fef18ec0,0,0,0,1412569920599611,1412582414551359,1412582414567679,1412569920753051 diff --git a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv index 148ad78395..891678f0d8 100644 --- a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,170884,19184888,198990137856562,199001894935363,199001894955843,198990153574507 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,270394,30243744,198990153590808,199001895045923,199001895062403,198990153897729 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320753,320753,1048576,256,0,0,8,0,16,64,0x0,0x7f4cb8e90ec0,65536,259860,29229728,198990153924269,199001895083363,199001895098883,198990154075054 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4145133,4145133,1048576,256,0,0,8,0,16,64,0x0,0x7fa244294ec0,65536,195342,21793984,1412570388029401,1412582414437599,1412582414457599,1412570404294060 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4145133,4145133,1048576,256,0,0,8,0,16,64,0x0,0x7fa244294ec0,65536,307640,34543088,1412570404315240,1412582414476479,1412582414491999,1412570404581574 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4145133,4145133,1048576,256,0,0,8,0,16,64,0x0,0x7fa244294ec0,65536,266008,29709392,1412570404607944,1412582414551359,1412582414567679,1412570404762556 diff --git a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv index b0ad335a3a..6b5d78be95 100644 --- a/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,278475,31173412,198990619125670,199001894935363,199001894955843,198990634836722 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,559977,62717076,198990634856980,199001895045923,199001895062403,198990635121510 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,320954,320954,1048576,256,0,0,8,0,16,64,0x0,0x7f40f4f68ec0,32768,569028,63722036,198990635147840,199001895083363,199001895098883,198990635324454 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4145318,4145318,1048576,256,0,0,8,0,16,64,0x0,0x7f895b6e0ec0,32768,289884,32469952,1412570872387977,1412582414437599,1412582414457599,1412570888873843 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4145318,4145318,1048576,256,0,0,8,0,16,64,0x0,0x7f895b6e0ec0,32768,599906,67183036,1412570888893811,1412582414476479,1412582414491999,1412570889171757 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4145318,4145318,1048576,256,0,0,8,0,16,64,0x0,0x7f895b6e0ec0,32768,583331,65336048,1412570889198147,1412582414551359,1412582414567679,1412570889355965 diff --git a/tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv index f11c4d6e02..8400a4db06 100644 --- a/tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,29013,29013,11176,232112,16384,11736679,138268,0,47442548,198991099206579,199001894935363,199001894955843,198991115265029 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,40851,40851,13491,326816,16384,18989824,219727,0,76441744,198991115292040,199001895045923,199001895062403,198991115577520 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,321157,321157,1048576,256,0,0,8,0,16,64,0x0,0x7f6e1b100ec0,41371,41371,13947,330976,16384,19441122,223986,0,78257552,198991115612746,199001895083363,199001895098883,198991115779131 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4145521,4145521,1048576,256,0,0,8,0,16,64,0x0,0x7f7f9d9b0ec0,27994,27994,11226,223960,16384,10642083,128366,0,43085488,1412571356271493,1412582414437599,1412582414457599,1412571372190678 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4145521,4145521,1048576,256,0,0,8,0,16,64,0x0,0x7f7f9d9b0ec0,40639,40639,12658,325120,16384,19865141,225740,0,79939960,1412571372218141,1412582414476479,1412582414491999,1412571372507969 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4145521,4145521,1048576,256,0,0,8,0,16,64,0x0,0x7f7f9d9b0ec0,40808,40808,12670,326472,16384,19726094,225982,0,79390392,1412571372543296,1412582414551359,1412582414567679,1412571372709790 diff --git a/tests/workloads/device_inv_int/MI200/log.txt b/tests/workloads/device_inv_int/MI200/log.txt new file mode 100644 index 0000000000..5fbb652493 --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/log.txt @@ -0,0 +1,739 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/device_inv_int/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_163357' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163357_4144586' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163357_4144586/input0_results_240321_163357' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163357_4144586/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163357_4144586/input0_results_240321_163357 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_163357' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163357_4144787' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163357_4144787/input0_results_240321_163357' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163357_4144787/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163357_4144787/input0_results_240321_163357 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_163358' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163358_4144973' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163358_4144973/input0_results_240321_163358' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163358_4144973/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163358_4144973/input0_results_240321_163358 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_163358' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163358_4145158' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163358_4145158/input0_results_240321_163358' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163358_4145158/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163358_4145158/input0_results_240321_163358 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_163359' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163359_4145361' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163359_4145361/input0_results_240321_163359' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163359_4145361/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163359_4145361/input0_results_240321_163359 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_163359' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163359_4145564' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163359_4145564/input0_results_240321_163359' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163359_4145564/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163359_4145564/input0_results_240321_163359 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_163400' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163400_4145766' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163400_4145766/input0_results_240321_163400' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163400_4145766/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163400_4145766/input0_results_240321_163400 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_163400' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163400_4145967' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163400_4145967/input0_results_240321_163400' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163400_4145967/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163400_4145967/input0_results_240321_163400 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_163401' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163401_4146168' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163401_4146168/input0_results_240321_163401' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163401_4146168/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163401_4146168/input0_results_240321_163401 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_163401' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163401_4146384' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163401_4146384/input0_results_240321_163401' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163401_4146384/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163401_4146384/input0_results_240321_163401 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_163402' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163402_4146586' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163402_4146586/input0_results_240321_163402' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163402_4146586/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163402_4146586/input0_results_240321_163402 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_163402' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163402_4146787' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163402_4146787/input0_results_240321_163402' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163402_4146787/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163402_4146787/input0_results_240321_163402 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_163403' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163403_4146988' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163403_4146988/input0_results_240321_163403' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163403_4146988/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163403_4146988/input0_results_240321_163403 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_163404' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163404_4147191' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163404_4147191/input0_results_240321_163404' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163404_4147191/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163404_4147191/input0_results_240321_163404 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_163404' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163404_4147378' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163404_4147378/input0_results_240321_163404' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163404_4147378/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163404_4147378/input0_results_240321_163404 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_163405' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163405_4147580' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163405_4147580/input0_results_240321_163405' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163405_4147580/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163405_4147580/input0_results_240321_163405 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_163406' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163406_4147766' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163406_4147766/input0_results_240321_163406' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163406_4147766/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163406_4147766/input0_results_240321_163406 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_163406' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163406_4147965' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163406_4147965/input0_results_240321_163406' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163406_4147965/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163406_4147965/input0_results_240321_163406 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_163407' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163407_4148166' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163407_4148166/input0_results_240321_163407' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163407_4148166/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163407_4148166/input0_results_240321_163407 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_163407' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163407_4148353' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163407_4148353/input0_results_240321_163407' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163407_4148353/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163407_4148353/input0_results_240321_163407 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_163408' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163408_4148536' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163408_4148536/input0_results_240321_163408' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163408_4148536/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163408_4148536/input0_results_240321_163408 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_163408' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163408_4148723' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163408_4148723/input0_results_240321_163408' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163408_4148723/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163408_4148723/input0_results_240321_163408 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_163409' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163409_4148911' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163409_4148911/input0_results_240321_163409' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163409_4148911/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163409_4148911/input0_results_240321_163409 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_163409' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163409_4149094' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163409_4149094/input0_results_240321_163409' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163409_4149094/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163409_4149094/input0_results_240321_163409 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/device_inv_int/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_163410' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/device_inv_int/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163410_4149281' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163410_4149281/input0_results_240321_163410' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163410_4149281/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163410_4149281/input0_results_240321_163410 + |-> [rocprof] File 'tests/workloads/device_inv_int/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/device_inv_int/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/device_inv_int/MI200/pmc_dispatch_info.csv b/tests/workloads/device_inv_int/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/device_inv_int/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/device_inv_int/MI200/pmc_perf.csv b/tests/workloads/device_inv_int/MI200/pmc_perf.csv index 61f39cd23c..fe5254addc 100644 --- a/tests/workloads/device_inv_int/MI200/pmc_perf.csv +++ b/tests/workloads/device_inv_int/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_3,obj_3,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_6,obj_6,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_7,obj_7,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_10,obj_10,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_11,obj_11,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_12,obj_12,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_13,obj_13,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_14,obj_14,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_15,obj_15,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_16,obj_16,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_17,obj_17,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_18,obj_18,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a6c228ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,216,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,90,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f2937a68ec0,11006002,9848553,813385,344064,1688971,0,0,163840,832.0,515136.0,0.0,524288.0,261212.0,32768.0,508615,0,0,10959,131072.0,131072.0,0.0,131072.0,64,0x7f94aab9cec0,114688,0,32768,32768,16384,16384,65536,49152,27239232.0,85502204.0,39234167.0,131072.0,0.0,214329.0,0,0,14836,985.0,131081.0,0.0,10.0,64,0x7f8ec991cec0,0,1179824,4096,4096,0,1184747,4096,4096,0,1095241,4096,4096,0,1312053,4096,4096,0,1119705,4096,4096,0,1279152,4096,4096,0,1146894,4096,4096,0,1419418,4096,4096,0,1059357,4096,4096,0,955392,4096,4096,0,1177723,4096,4096,0,1147610,4096,4096,0,1142555,4096,4096,0,1295423,4096,4096,0,1244614,4096,4096,0,1176565,4096,4096,0,1307790,4096,4096,0,1099403,4096,4096,0,1255268,4096,4096,0,1441413,4096,4096,0,1096315,4096,4096,0,1313792,4096,4096,0,1070022,4096,4096,0,1165463,4096,4096,0,1269843,4096,4096,0,1221566,4096,4096,0,960162,4096,4096,0,1209517,4096,4096,0,1356484,4096,4096,0,1216090,4096,4096,0,1005949,4096,4096,0,1352581,4096,4096,64,0x7f29664d0ec0,230544,129864,16384,0,16384,16384,32768,49152,28817,28817,1966047.0,1356490.0,3655.0,143485.0,1055507.0,0.0,1348383.0,1050292.0,228833,137984,28817,0,28817,0,922144.0,489395.0,0.0,0.0,64,0x7f2a5913cec0,0,0,0,224,0,65536,64214,56,64,0x7fb169968ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,936867.0,64,0x7f5b58528ec0,6358,0,4096,6390,0,4096,6365,0,4096,6363,0,4096,6359,0,4096,6377,0,4096,6327,0,4096,6330,0,4096,6335,0,4096,6361,0,4096,6392,0,4096,6371,0,4096,6365,0,4096,6363,0,4096,6376,0,4096,6329,0,4096,6343,0,4096,6323,0,4096,6337,0,4096,6394,0,4096,6391,0,4096,6355,0,4096,6374,0,4096,6604,0,4096,6440,0,4096,6346,0,4096,6323,0,4096,6339,0,4096,6395,0,4096,6386,0,4096,6352,0,4096,6380,0,4096,64,0x7ffbde45cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,36964499.0,33819093.0,0.0,64,0x7f4f6bc44ec0,0,393216,163840,0,0,0,0,0,18192,0.0,0.0,0.0,32768.0,0.0,0.0,384.0,32768.0,4096,16384,352,28917,2240,0,56.0,8.0,0.0,204076.0,64,0x7f45efd94ec0,32768,32768,0,64,0x7f0432dc4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,34583.0,46155.0,19381.0,64,0x7f3368474ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13656,18873,8498,545,0,27677,203868.0,0.0,72787.0,131081.0,64,0x7fd115474ec0,0,0,0,1079720,0,0,0,1134252,0,0,0,1045421,0,0,0,1022469,0,0,0,1142703,0,0,0,1146218,0,0,0,1128724,0,0,0,1111887,0,0,0,955800,0,0,0,1049019,0,0,0,1027599,0,0,0,1083365,0,0,0,973437,0,0,0,1124813,0,0,0,1061835,0,0,0,1168236,0,0,0,963833,0,0,0,1046292,0,0,0,1106744,0,0,0,1096318,0,0,0,1033391,0,0,0,1060045,0,0,0,1015723,0,0,0,1103195,0,0,0,1117196,0,0,0,1023077,0,0,0,1041474,0,0,0,1183148,0,0,0,1102262,0,0,0,1044954,0,0,0,983585,0,0,0,1135988,64,0x7f6344c98ec0,2241,4096,2241,6337,2302,4096,2302,6398,2261,4096,2261,6357,2315,4096,2315,6411,2245,4096,2245,6341,2255,4096,2255,6351,2283,4097,2284,6380,2260,4096,2260,6356,2259,4101,2264,6360,2241,4096,2241,6337,2304,4096,2304,6400,2264,4096,2264,6360,2318,4096,2318,6414,2248,4096,2248,6344,2258,4096,2258,6354,2282,4096,2282,6378,2312,4096,2312,6408,2269,4096,2269,6365,2305,4097,2306,6402,2260,4096,2260,6356,2289,4096,2289,6385,2257,4096,2257,6353,2265,4096,2265,6361,2397,4098,2399,6495,2234,4096,2234,6330,2315,4096,2315,6411,2271,4096,2271,6367,2354,4097,2355,6451,2261,4096,2261,6357,2290,4096,2290,6386,2256,4096,2256,6352,2266,4097,2267,6363,64,0x7fb37110cec0,1219,116932,0,0,65536,63800,56,1680,64,0x7f2bf1eb4ec0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,0,27623,0,0,64,0x7fe24d508ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,11265,0,820,28544,0,73265.0,131072.0,0.0,65568.0,64,0x7fd2fe7f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,199001894935363,199001894955843 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a6c228ec0,4096,0,8,0,4096,0,1480,0,4099,0,749,0,4096,0,973,0,4096,0,28,0,4096,0,18,0,4096,0,504,0,4096,0,681,0,4096,0,0,0,4096,0,529,0,4097,0,423,0,4097,0,171,0,4096,0,123,0,4097,0,14,0,4096,0,361,0,4096,0,333,0,4096,0,859,0,4096,0,277,0,4098,0,0,0,4096,0,34,0,4096,0,917,0,4096,0,482,0,4096,0,149,0,4096,0,1642,0,4096,0,2497,0,4096,0,296,0,4096,0,610,0,4096,0,0,0,4096,0,80,0,4099,0,896,0,4096,0,223,0,4096,0,155,0,64,0x7f2937a68ec0,17442109,16824138,273907,344064,2559829,0,0,163840,0.0,524288.0,0.0,524288.0,473755.0,32768.0,744023,0,0,12076,91469.0,91469.0,0.0,91469.0,64,0x7f94aab9cec0,114688,0,32768,32768,16384,16384,65536,49152,58684283.0,202252507.0,50068835.0,131072.0,0.0,528959.0,0,0,25234,5071.0,131085.0,0.0,24.0,64,0x7f8ec991cec0,0,4053298,2812,2812,0,5308663,2868,2868,0,3454808,2848,2848,0,4348769,2864,2864,0,4297579,2884,2884,0,3439406,2852,2852,0,3286148,2876,2876,0,5347469,2796,2796,0,3999171,2800,2800,0,3171519,2812,2812,0,4247777,2862,2862,0,3552601,2846,2846,0,3383726,2864,2864,0,3929474,2884,2884,0,3974256,2852,2852,0,3298457,2876,2876,0,3671812,2830,2830,0,3699796,2848,2848,0,4266571,2850,2850,0,4211648,2844,2844,0,3904572,2840,2840,0,4286664,2860,2860,0,3192445,2840,2840,0,4691568,2832,2832,0,4205176,2832,2832,0,3857193,2824,2824,0,3382754,2848,2848,0,3428950,2844,2844,0,3600961,2840,2840,0,2908010,2836,2836,0,3081597,2864,2864,0,4344951,2840,2840,64,0x7f29664d0ec0,333392,226065,16384,0,16384,16384,32768,49152,41673,41673,3215463.0,2486094.0,4544.0,386757.0,1698384.0,0.0,2473902.0,2167306.0,333384,235179,41673,0,41673,0,1333536.0,789257.0,0.0,0.0,64,0x7f2a5913cec0,0,0,0,56,0,65536,65536,0,64,0x7fb169968ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2034549.0,64,0x7f5b58528ec0,6274,0,4096,6281,0,4096,6274,0,4096,6273,0,4096,6296,0,4096,6257,0,4096,6300,0,4096,6304,0,4096,6299,0,4096,6275,0,4096,6281,0,4096,6275,0,4096,6273,0,4096,6296,0,4096,6263,0,4096,6300,0,4096,6278,0,4096,6312,0,4096,6295,0,4096,6277,0,4096,6247,0,4096,6291,0,4096,6264,0,4096,6305,0,4096,6309,0,4096,6281,0,4096,6312,0,4096,6293,0,4096,6277,0,4096,6245,0,4096,6295,0,4096,6260,0,4096,64,0x7ffbde45cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,114993725.0,54736282.0,0.0,64,0x7f4f6bc44ec0,0,393216,163840,0,0,0,0,0,30625,0.0,0.0,0.0,32768.0,0.0,0.0,226.0,32768.0,4096,16384,302,42149,2062,0,56.0,12.0,0.0,201132.0,64,0x7f45efd94ec0,32768,32768,0,64,0x7f0432dc4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,113320.0,45613.0,0.0,64,0x7f3368474ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,33476,27568,9679,3091,0,40813,200853.0,0.0,69770.0,131083.0,64,0x7fd115474ec0,0,0,0,1902501,0,0,0,1773219,0,0,0,1828587,125,0,0,1959593,44,0,0,1743737,191,0,0,1928450,0,0,0,1491817,306,0,0,2171414,235,0,0,1964093,0,0,0,1516128,0,0,0,1648016,0,0,0,1666965,117,0,0,1903701,217,0,0,1832230,70,0,0,1665619,0,0,0,1537253,0,0,0,1869651,0,0,0,1490493,0,0,0,2132873,0,0,0,2322381,0,0,0,1982215,0,0,0,1837909,0,0,0,1394897,0,0,0,1823369,0,0,0,1621199,0,0,0,1617817,0,0,0,1515019,0,0,0,1799969,1145,0,0,2655551,0,0,0,1675597,47,0,0,1837476,21,0,0,1871388,64,0x7f6344c98ec0,2177,4096,2177,6273,2186,4096,2186,6282,2154,4096,2154,6250,2177,4097,2178,6274,2227,4096,2227,6323,2216,4096,2216,6312,2165,4097,2166,6262,2157,4096,2157,6253,2160,4100,2164,6260,2180,4096,2180,6276,2186,4096,2186,6282,2152,4096,2152,6248,2180,4096,2180,6276,2232,4096,2232,6328,2224,4096,2224,6320,2165,4096,2165,6261,2163,4096,2163,6259,2188,4096,2188,6284,2204,4099,2207,6303,2172,4096,2172,6268,2165,4096,2165,6261,2195,4096,2195,6291,2204,4096,2204,6300,2197,4096,2197,6293,2190,4096,2190,6286,2160,4096,2160,6256,2191,4096,2191,6287,2265,4097,2266,6362,2177,4097,2178,6274,2166,4096,2166,6262,2197,4096,2197,6293,2211,4097,2212,6308,64,0x7fb37110cec0,0,189319,0,0,65536,63800,56,1680,64,0x7f2bf1eb4ec0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,0,41419,0,0,64,0x7fe24d508ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21917,0,3200,38716,0,70007.0,131072.0,0.0,45614.0,64,0x7fd2fe7f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,199001895045923,199001895062403 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9a6c228ec0,4096,0,0,0,4096,0,61,0,4099,0,39,0,4096,0,598,0,4096,0,0,0,4096,0,603,0,4096,0,1572,0,4096,0,1491,0,4096,0,767,0,4096,0,4,0,4097,0,506,0,4097,0,623,0,4096,0,0,0,4097,0,492,0,4096,0,45,0,4096,0,971,0,4096,0,1309,0,4096,0,689,0,4098,0,104,0,4096,0,110,0,4096,0,0,0,4096,0,26,0,4096,0,642,0,4096,0,969,0,4096,0,753,0,4096,0,285,0,4096,0,180,0,4096,0,294,0,4096,0,124,0,4099,0,316,0,4096,0,0,0,4096,0,277,0,64,0x7f2937a68ec0,19212072,17889234,978774,344064,2828431,0,0,163840,832.0,515156.0,0.0,524288.0,651940.0,32768.0,962483,0,0,14247,91258.0,91258.0,0.0,91258.0,64,0x7f94aab9cec0,114688,0,32768,32768,16384,16384,65536,49152,59012238.0,203962207.0,49799072.0,131072.0,0.0,613464.0,0,0,25520,25605.0,131085.0,0.0,24.0,64,0x7f8ec991cec0,0,3500985,2810,2810,0,4465598,2856,2856,0,3139145,2876,2876,0,4828031,2866,2866,0,4272524,2868,2868,0,4639315,2828,2828,0,3168068,2864,2864,0,3509805,2824,2824,0,4089463,2824,2824,0,2984079,2812,2812,0,3969660,2856,2856,0,2815232,2880,2880,0,3730141,2866,2866,0,3945959,2864,2864,0,4215769,2828,2828,0,3595329,2864,2864,0,3573539,2808,2808,0,4453356,2836,2836,0,3262638,2844,2844,0,4107953,2828,2828,0,3955268,2856,2856,0,3741482,2884,2884,0,4475161,2830,2830,0,4123623,2824,2824,0,3853112,2824,2824,0,2678326,2804,2804,0,3157757,2836,2836,0,3570615,2844,2844,0,3788053,2828,2828,0,3648549,2856,2856,0,3216476,2884,2884,0,4553292,2832,2832,64,0x7f29664d0ec0,332968,225188,16384,0,16384,16384,32768,49152,41620,41620,3204620.0,2435646.0,4679.0,336921.0,1612536.0,0.0,2423654.0,2115789.0,332960,234475,41620,0,41620,0,1331840.0,769041.0,0.0,0.0,64,0x7f2a5913cec0,0,0,0,56,0,65536,65536,0,64,0x7fb169968ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2078739.0,64,0x7f5b58528ec0,6272,0,4096,6271,0,4096,6273,0,4096,6267,0,4096,6265,0,4096,6291,0,4096,6305,0,4096,6259,0,4096,6258,0,4096,6276,0,4096,6275,0,4096,6273,0,4096,6266,0,4096,6268,0,4096,6294,0,4096,6307,0,4096,6317,0,4096,6336,0,4096,6276,0,4096,6264,0,4096,6285,0,4096,6304,0,4096,6270,0,4096,6323,0,4096,6327,0,4096,6317,0,4096,6337,0,4096,6274,0,4096,6265,0,4096,6279,0,4096,6303,0,4096,6270,0,4096,64,0x7ffbde45cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,122720872.0,59508672.0,0.0,64,0x7f4f6bc44ec0,0,393216,163840,0,0,0,0,0,29950,0.0,0.0,0.0,32768.0,0.0,0.0,183.0,32768.0,4096,16384,302,41324,2064,0,56.0,11.0,0.0,200699.0,64,0x7f45efd94ec0,32768,32768,0,64,0x7f0432dc4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,94142.0,45588.0,0.0,64,0x7f3368474ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,33548,28329,9681,2572,0,40307,201246.0,0.0,70161.0,131085.0,64,0x7fd115474ec0,0,0,0,1672867,0,0,0,1772478,0,0,0,1793173,0,0,0,1756705,0,0,0,1692171,16,0,0,2001859,0,0,0,1516869,0,0,0,1582399,0,0,0,1495708,1,0,0,1835980,192,0,0,2154216,0,0,0,1590847,310,0,0,1732891,0,0,0,1537215,0,0,0,1741083,0,0,0,1462858,0,0,0,1421382,51,0,0,1543396,10,0,0,1987202,62,0,0,2046958,0,0,0,1835595,0,0,0,1775664,0,0,0,1532975,0,0,0,1767950,970,0,0,2553432,0,0,0,1723931,0,0,0,1312116,577,0,0,2382098,80,0,0,1948886,0,0,0,1869305,0,0,0,1467726,103,0,0,1725884,64,0x7f6344c98ec0,2170,4096,2170,6266,2190,4096,2190,6286,2146,4096,2146,6242,2170,4097,2171,6267,2205,4096,2205,6301,2174,4096,2174,6270,2155,4097,2156,6252,2164,4096,2164,6260,2169,4101,2174,6270,2170,4096,2170,6266,2192,4096,2192,6288,2144,4096,2144,6240,2168,4096,2168,6264,2207,4096,2207,6303,2177,4096,2177,6273,2157,4096,2157,6253,2153,4096,2153,6249,2199,4096,2199,6295,2163,4099,2166,6262,2180,4096,2180,6276,2154,4096,2154,6250,2161,4096,2161,6257,2222,4096,2222,6318,2200,4096,2200,6296,2198,4096,2198,6294,2156,4096,2156,6252,2194,4096,2194,6290,2222,4097,2223,6319,2183,4097,2184,6280,2159,4096,2159,6255,2160,4096,2160,6256,2227,4097,2228,6324,64,0x7fb37110cec0,0,187457,0,0,65536,63800,56,1680,64,0x7f2bf1eb4ec0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,0,41275,0,0,64,0x7fe24d508ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21559,0,3201,38687,0,69886.0,131072.0,0.0,45669.0,64,0x7fd2fe7f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,199001895083363,199001895098883 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_2,obj_2,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_4,obj_4,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_5,obj_5,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_12,obj_12,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_14,obj_14,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_15,obj_15,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_16,obj_16,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_17,obj_17,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_18,obj_18,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f45e8864ec0,0,0,0,959816,0,0,0,1032511,0,0,0,1027354,0,0,0,1137939,21,0,0,1090811,20,0,0,1141143,0,0,0,1038463,0,0,0,1111903,0,0,0,999958,0,0,0,1019021,0,0,0,1007879,0,0,0,1094171,0,0,0,1139343,0,0,0,1153115,0,0,0,1052603,0,0,0,1122644,0,0,0,1144638,0,0,0,1033489,0,0,0,1054298,0,0,0,1118792,68,0,0,1102882,4,0,0,1168287,0,0,0,1150992,145,0,0,1208644,65,0,0,1123200,0,0,0,1110009,0,0,0,1054530,0,0,0,1113734,0,0,0,1048076,0,0,0,1042633,0,0,0,1199684,0,0,0,1241521,64,0x7f0654f40ec0,224864,125381,16384,0,16384,16384,32768,49152,28107,28107,1908028.0,1339206.0,3354.0,163080.0,1029591.0,0.0,1331594.0,1035287.0,223153,133528,28107,0,28107,0,899424.0,494622.0,0.0,0.0,64,0x7efe10100ec0,32768,32768,0,64,0x7f2d294f8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,989056.0,64,0x7f17fb4a8ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,130,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,130,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,17,0,64,0x7f18f3b9cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,9699,0,815,27949,0,73035.0,131072.0,0.0,65568.0,64,0x7f0fa16e4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12648,19258,7150,545,0,26227,204468.0,0.0,73387.0,131081.0,64,0x7f7063168ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,35115.0,46289.0,19247.0,64,0x7f3084b78ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40107130.0,35056246.0,0.0,64,0x7fe23e274ec0,6380,0,4096,6361,0,4096,6368,0,4096,6398,0,4096,6380,0,4096,6416,0,4096,6407,0,4096,6390,0,4096,6392,0,4096,6382,0,4096,6363,0,4096,6366,0,4096,6397,0,4096,6381,0,4096,6419,0,4096,6410,0,4096,6394,0,4096,6390,0,4096,6367,0,4096,6382,0,4096,6350,0,4096,6383,0,4096,6406,0,4096,6515,0,4096,6346,0,4096,6397,0,4096,6391,0,4096,6370,0,4096,6385,0,4096,6354,0,4096,6385,0,4096,6407,0,4096,64,0x7f3bbf214ec0,0,1048775,4096,4096,0,1412295,4096,4096,0,1098048,4096,4096,0,1328166,4096,4096,0,1305513,4096,4096,0,1551157,4096,4096,0,1137886,4096,4096,0,1668744,4096,4096,0,1058675,4096,4096,0,1176828,4096,4096,0,1346323,4096,4096,0,1118734,4096,4096,0,1168012,4096,4096,0,1440504,4096,4096,0,1275507,4096,4096,0,1314191,4096,4096,0,1360783,4096,4096,0,1149962,4096,4096,0,1249657,4096,4096,0,1403804,4096,4096,0,1334334,4096,4096,0,1338248,4096,4096,0,1164659,4096,4096,0,1309164,4096,4096,0,1329707,4096,4096,0,1063559,4096,4096,0,1158681,4096,4096,0,1304918,4096,4096,0,1341379,4096,4096,0,1044580,4096,4096,0,1026281,4096,4096,0,1363026,4096,4096,64,0x7f280d968ec0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,0,28004,0,0,64,0x7f1291c08ec0,0,393216,163840,0,0,0,0,0,17292,0.0,0.0,0.0,32768.0,0.0,0.0,387.0,32768.0,4096,16384,352,27856,2144,0,56.0,6.0,0.0,204417.0,64,0x7f43d4258ec0,11018966,9879316,795586,344064,1659935,0,0,163840,832.0,515142.0,0.0,524288.0,255027.0,32768.0,520103,0,0,11806,131072.0,131072.0,0.0,131072.0,64,0x7f40c2944ec0,114688,0,32768,32768,16384,16384,65536,49152,27615661.0,86899284.0,39352299.0,131072.0,0.0,197485.0,0,0,14941,340.0,131080.0,0.0,8.0,64,0x7efd878f0ec0,1269,113822,0,0,65536,63800,56,1680,64,0x7fe20b9f8ec0,0,0,0,224,0,65536,64279,56,64,0x7ff861dacec0,2277,4096,2277,6373,2283,4096,2283,6379,2315,4096,2315,6411,2317,4096,2317,6413,2248,4096,2248,6344,2323,4096,2323,6419,2245,4096,2245,6341,2274,4096,2274,6370,2273,4097,2274,6370,2278,4096,2278,6374,2282,4096,2282,6378,2315,4096,2315,6411,2317,4096,2317,6413,2248,4096,2248,6344,2328,4098,2330,6426,2244,4096,2244,6340,2238,4096,2238,6334,2276,4096,2276,6372,2275,4097,2276,6372,2333,4096,2333,6429,2278,4096,2278,6374,2269,4096,2269,6365,2289,4096,2289,6385,2508,4099,2511,6607,2292,4098,2294,6390,2238,4096,2238,6334,2277,4096,2277,6373,2279,4096,2279,6375,2339,4096,2339,6435,2279,4096,2279,6375,2273,4096,2273,6369,2292,4096,2292,6388,64,0x7f8f3aa1cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,1412582414437599,1412582414457599 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f45e8864ec0,1958,0,0,2190946,659,0,0,2390786,251,0,0,2000387,418,0,0,1965535,1465,0,0,2478621,1551,0,0,2629908,961,0,0,2093922,0,0,0,1828696,0,0,0,1862561,481,0,0,2178693,186,0,0,2066939,583,0,0,2012375,388,0,0,2240373,1129,0,0,2347013,421,0,0,2253231,304,0,0,2129376,0,0,0,1800233,3255,0,0,2903220,374,0,0,2030487,4040,0,0,3015260,0,0,0,1868923,371,0,0,2222800,789,0,0,2040544,392,0,0,2010724,208,0,0,1725030,0,0,0,1649937,1511,0,0,2604944,645,0,0,2032011,3175,0,0,2845524,1082,0,0,2214342,704,0,0,2315256,1243,0,0,2307227,64,0x7f0654f40ec0,326280,220152,16384,0,16384,16384,32768,49152,40784,40784,3138787.0,2356052.0,3863.0,329884.0,1734545.0,0.0,2344234.0,2036761.0,326272,229315,40784,0,40784,0,1305088.0,770272.0,0.0,0.0,64,0x7efe10100ec0,32768,32768,0,64,0x7f2d294f8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2016056.0,64,0x7f17fb4a8ec0,4096,0,690,0,4096,0,2007,0,4096,0,342,0,4096,0,80,0,4096,0,465,0,4096,0,1904,0,4096,0,0,0,4097,0,712,0,4096,0,695,0,4096,0,65,0,4096,0,150,0,4096,0,77,0,4099,0,0,0,4098,0,16,0,4096,0,541,0,4096,0,142,0,4096,0,222,0,4096,0,1033,0,4096,0,382,0,4096,0,1107,0,4096,0,151,0,4096,0,222,0,4097,0,312,0,4097,0,243,0,4096,0,376,0,4096,0,154,0,4096,0,283,0,4096,0,254,0,4096,0,95,0,4096,0,140,0,4099,0,127,0,4096,0,729,0,64,0x7f18f3b9cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,16061,0,819,36368,0,69512.0,131072.0,0.0,45724.0,64,0x7f0fa16e4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32624,29146,9689,3129,0,39320,201375.0,0.0,70291.0,131084.0,64,0x7f7063168ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,87493.0,45614.0,0.0,64,0x7f3084b78ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,117369585.0,58816453.0,0.0,64,0x7fe23e274ec0,6264,0,4096,6287,0,4096,6253,0,4096,6298,0,4096,6274,0,4096,6245,0,4096,6293,0,4096,6315,0,4096,6316,0,4096,6268,0,4096,6289,0,4096,6254,0,4096,6297,0,4096,6278,0,4096,6244,0,4096,6299,0,4096,6260,0,4096,6312,0,4096,6255,0,4096,6272,0,4096,6291,0,4096,6264,0,4096,6278,0,4096,6272,0,4096,6275,0,4096,6263,0,4096,6312,0,4096,6260,0,4096,6268,0,4096,6294,0,4096,6263,0,4096,6279,0,4096,64,0x7f3bbf214ec0,0,4683334,2852,2852,0,3278654,2898,2898,0,3174777,2828,2828,0,4436132,2856,2856,0,2891793,2880,2880,0,3908965,2852,2852,0,3305618,2856,2856,0,4200457,2816,2816,0,3311269,2816,2816,0,3158797,2848,2848,0,2781615,2900,2900,0,3140924,2828,2828,0,3666451,2856,2856,0,3039961,2884,2884,0,3084192,2844,2844,0,3100762,2856,2856,0,3462098,2812,2812,0,3731539,2852,2852,0,4482250,2856,2856,0,3859595,2848,2848,0,3297823,2816,2816,0,3298269,2864,2864,0,4979024,2840,2840,0,4226647,2832,2832,0,2855540,2832,2832,0,3878724,2812,2812,0,3751461,2852,2852,0,4042774,2860,2860,0,3624801,2848,2848,0,2574082,2816,2816,0,3226755,2864,2864,0,4349907,2838,2838,64,0x7f280d968ec0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,0,41402,0,0,64,0x7f1291c08ec0,0,393216,163840,0,0,0,0,0,29502,0.0,0.0,0.0,32768.0,0.0,0.0,222.0,32768.0,4096,16384,302,41819,2075,0,56.0,9.0,0.0,200718.0,64,0x7f43d4258ec0,19849945,18380829,1125052,344064,2838809,0,0,163840,832.0,515140.0,0.0,524288.0,566571.0,32768.0,1039119,0,0,13271,90882.0,90882.0,0.0,90882.0,64,0x7f40c2944ec0,114688,0,32768,32768,16384,16384,65536,49152,57714196.0,197999237.0,51088640.0,131072.0,0.0,481350.0,0,0,24387,4936.0,131081.0,0.0,16.0,64,0x7efd878f0ec0,0,180414,0,0,65536,63800,56,1680,64,0x7fe20b9f8ec0,0,0,0,56,0,65536,65536,0,64,0x7ff861dacec0,2157,4096,2157,6253,2185,4096,2185,6281,2161,4096,2161,6257,2165,4096,2165,6261,2163,4096,2163,6259,2162,4096,2162,6258,2160,4096,2160,6256,2176,4096,2176,6272,2179,4097,2180,6276,2162,4096,2162,6258,2185,4096,2185,6281,2160,4096,2160,6256,2172,4096,2172,6268,2158,4096,2158,6254,2162,4098,2164,6260,2156,4096,2156,6252,2161,4096,2161,6257,2190,4096,2190,6286,2203,4097,2204,6300,2188,4096,2188,6284,2172,4096,2172,6268,2168,4097,2169,6265,2168,4096,2168,6264,2226,4097,2227,6323,2175,4098,2177,6273,2164,4096,2164,6260,2188,4096,2188,6284,2202,4096,2202,6298,2197,4096,2197,6293,2168,4099,2171,6267,2166,4096,2166,6262,2165,4096,2165,6261,64,0x7f8f3aa1cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,1412582414476479,1412582414491999 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f45e8864ec0,228,0,0,2315551,468,0,0,2005554,163,0,0,1980016,375,0,0,2175106,503,0,0,2447644,97,0,0,2235355,405,0,0,1939681,1195,0,0,2238939,2626,0,0,2612928,393,0,0,2113645,0,0,0,1478452,0,0,0,1813186,663,0,0,2269235,184,0,0,2114446,197,0,0,1917348,27,0,0,2112419,847,0,0,2063255,363,0,0,2014750,99,0,0,1892862,425,0,0,2329354,1229,0,0,2210069,568,0,0,2107139,2978,0,0,2909551,139,0,0,1845680,1038,0,0,2340219,420,0,0,1716156,2643,0,0,2680459,386,0,0,2104854,1432,0,0,2498215,850,0,0,1972186,941,0,0,2395349,68,0,0,2168088,64,0x7f0654f40ec0,319840,214101,16384,0,16384,16384,32768,49152,39979,39979,3060433.0,2369091.0,4435.0,335869.0,1760239.0,0.0,2355108.0,2044643.0,319832,223369,39979,0,39979,0,1279328.0,770605.0,0.0,0.0,64,0x7efe10100ec0,32768,32768,0,64,0x7f2d294f8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2049435.0,64,0x7f17fb4a8ec0,4096,0,1063,0,4096,0,219,0,4096,0,486,0,4096,0,1878,0,4096,0,1965,0,4096,0,2943,0,4096,0,41,0,4097,0,684,0,4096,0,0,0,4096,0,691,0,4096,0,223,0,4096,0,0,0,4099,0,359,0,4098,0,386,0,4096,0,1138,0,4096,0,296,0,4096,0,185,0,4096,0,921,0,4096,0,615,0,4096,0,204,0,4096,0,172,0,4096,0,200,0,4097,0,353,0,4097,0,2828,0,4096,0,414,0,4096,0,0,0,4096,0,22,0,4096,0,567,0,4096,0,20,0,4096,0,374,0,4099,0,382,0,4096,0,1105,0,64,0x7f18f3b9cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20128,0,3189,37660,0,69790.0,131072.0,0.0,45526.0,64,0x7f0fa16e4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31600,27550,9721,2901,0,39247,200936.0,0.0,69851.0,131085.0,64,0x7f7063168ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,82037.0,45452.0,0.0,64,0x7f3084b78ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118600924.0,60617723.0,0.0,64,0x7fe23e274ec0,6256,0,4096,6274,0,4096,6322,0,4096,6280,0,4096,6284,0,4096,6290,0,4096,6280,0,4096,6245,0,4096,6245,0,4096,6255,0,4096,6280,0,4096,6322,0,4096,6281,0,4096,6284,0,4096,6291,0,4096,6276,0,4096,6281,0,4096,6276,0,4096,6260,0,4096,6272,0,4096,6296,0,4096,6296,0,4096,6291,0,4096,6278,0,4096,6277,0,4096,6286,0,4096,6279,0,4096,6266,0,4096,6273,0,4096,6297,0,4096,6302,0,4096,6292,0,4096,64,0x7f3bbf214ec0,0,3552760,2828,2828,0,3699884,2848,2848,0,3462530,2860,2860,0,4086691,2856,2856,0,3378775,2888,2888,0,4164721,2852,2852,0,3421847,2864,2864,0,4119655,2836,2836,0,3631324,2836,2836,0,3396179,2828,2828,0,3384320,2848,2848,0,3155398,2862,2862,0,4187816,2854,2854,0,4269377,2892,2892,0,3799173,2852,2852,0,3463952,2872,2872,0,4095595,2828,2828,0,3526211,2880,2880,0,4108445,2848,2848,0,3703301,2852,2852,0,4734113,2848,2848,0,3889877,2892,2892,0,4189487,2820,2820,0,3865896,2836,2836,0,3541729,2832,2832,0,3819500,2824,2824,0,3061483,2880,2880,0,3014260,2848,2848,0,3513271,2852,2852,0,4940715,2848,2848,0,3531559,2900,2900,0,4518420,2820,2820,64,0x7f280d968ec0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,0,41065,0,0,64,0x7f1291c08ec0,0,393216,163840,0,0,0,0,0,28932,0.0,0.0,0.0,32768.0,0.0,0.0,227.0,32768.0,4096,16384,302,40235,2081,0,56.0,10.0,0.0,200613.0,64,0x7f43d4258ec0,19314107,17916856,1053187,344064,2814834,0,0,163840,832.0,515153.0,0.0,524288.0,544920.0,32768.0,980390,0,0,13776,91188.0,91188.0,0.0,91188.0,64,0x7f40c2944ec0,114688,0,32768,32768,16384,16384,65536,49152,59218715.0,206589686.0,48005270.0,131072.0,0.0,583994.0,0,0,25028,3500.0,131081.0,0.0,16.0,64,0x7efd878f0ec0,0,183776,0,0,65536,63800,56,1680,64,0x7fe20b9f8ec0,0,0,0,56,0,65536,65536,0,64,0x7ff861dacec0,2169,4096,2169,6265,2203,4096,2203,6299,2173,4096,2173,6269,2207,4096,2207,6303,2161,4096,2161,6257,2199,4096,2199,6295,2150,4096,2150,6246,2182,4096,2182,6278,2185,4097,2186,6282,2172,4096,2172,6268,2205,4096,2205,6301,2176,4096,2176,6272,2209,4096,2209,6305,2169,4096,2169,6265,2206,4098,2208,6304,2156,4096,2156,6252,2158,4096,2158,6254,2193,4096,2193,6289,2208,4097,2209,6305,2201,4096,2201,6297,2157,4096,2157,6253,2192,4097,2193,6289,2203,4096,2203,6299,2231,4097,2232,6328,2178,4098,2180,6276,2157,4096,2157,6253,2195,4096,2195,6291,2209,4096,2209,6305,2202,4096,2202,6298,2156,4099,2159,6255,2192,4096,2192,6288,2201,4096,2201,6297,64,0x7f8f3aa1cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,1412582414551359,1412582414567679 diff --git a/tests/workloads/device_inv_int/MI200/roofline.csv b/tests/workloads/device_inv_int/MI200/roofline.csv index d8d5915d2f..3585d94580 100644 --- a/tests/workloads/device_inv_int/MI200/roofline.csv +++ b/tests/workloads/device_inv_int/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.4407,1387.9556,1388.9258,5012.3818,5009.4272,5015.3364,9220.9736,9220.4082,9221.5391,18048.867,18047.982,18049.752,20929.025,20868.734,20989.316,20262.105,20261.408,20262.803,170368.28,170364.62,170371.94,164833.34,164829.61,164837.08,41411.355,41410.75,41411.961,41471.086,41470.277,41471.895,166320.92,165829.64,166812.2 -1,1388.9957,1388.3947,1389.5968,5027.0874,5024.9897,5029.1851,9231.418,9230.6963,9232.1396,18088.484,18084.846,18092.123,20968.271,20901.262,21035.281,20286.959,20286.332,20287.586,170792.02,170786.41,170797.62,165064.95,165061.06,165068.84,41475.48,41474.453,41476.508,41528.645,41527.684,41529.605,166824.89,166821.84,166827.94 -2,1388.7762,1388.223,1389.3295,5033.8354,5031.5078,5036.1631,9260.0098,9259.3555,9260.6641,18109.824,18108.805,18110.844,21048.404,21047.924,21048.885,20354.592,20354.098,20355.086,171145.12,171140.94,171149.31,165515.59,165511.66,165519.53,41583.41,41582.383,41584.438,41643.316,41641.996,41644.637,166962.69,166359.5,167565.88 -3,1389.2411,1388.7584,1389.7238,5030.2002,5028.9575,5031.4429,9239.7422,9239.1396,9240.3447,18027.953,18024.689,18031.217,21032.553,21032.098,21033.008,20313.242,20312.57,20313.914,171017.05,171013.84,171020.25,165231.08,165227.28,165234.88,41521.387,41520.555,41522.219,41580.211,41579.453,41580.969,167016.34,167014.17,167018.52 +0,1389.1462,1388.6844,1389.608,5017.5005,5014.4473,5020.5537,9228.3779,9227.6279,9229.1279,17717.744,17714.797,17720.691,20946.693,20886.242,21007.145,20272.535,20272.062,20273.008,170499.52,170494.77,170504.27,164933.34,164928.09,164938.59,41436.176,41435.543,41436.809,41492.594,41491.988,41493.199,166403.12,165911.45,166894.8 +1,1389.674,1389.1433,1390.2046,5027.3335,5025.1128,5029.5542,9233.5205,9232.8916,9234.1494,18229.463,18227.5,18231.426,20973.705,20905.861,21041.549,20293.215,20292.557,20293.873,170827.14,170823.33,170830.95,165099.89,165096.33,165103.45,41482.094,41481.465,41482.723,41539.863,41539.215,41540.512,166862.95,166860.66,166865.25 +2,1388.6648,1388.1245,1389.2051,5037.0464,5034.8857,5039.207,9263.9912,9262.6768,9265.3057,18222.869,18221.883,18223.855,21056.984,21056.562,21057.406,20357.533,20356.988,20358.078,171205.48,171201.55,171209.42,165565.27,165560.72,165569.81,41598.941,41597.836,41600.047,41652.184,41651.406,41652.961,167016.72,166423.66,167609.78 +3,1388.9971,1388.3999,1389.5942,5033.2759,5031.7471,5034.8047,9236.5371,9235.832,9237.2422,18325.387,18324.445,18326.328,21031.562,21031.207,21031.918,20305.99,20305.543,20306.438,171012.06,171007.19,171016.94,165121.73,165116.78,165126.69,41423.219,41270.75,41575.688,41557.129,41556.031,41558.227,166901,166896.89,166905.11 diff --git a/tests/workloads/device_inv_int/MI200/sysinfo.csv b/tests/workloads/device_inv_int/MI200/sysinfo.csv index 29a3cdacbe..4ccc6bd554 100644 --- a/tests/workloads/device_inv_int/MI200/sysinfo.csv +++ b/tests/workloads/device_inv_int/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -device_inv_int,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:27:36 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +device_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:33:56 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/device_inv_int/MI200/timestamps.csv b/tests/workloads/device_inv_int/MI200/timestamps.csv index e0b15ace6a..fd31204931 100644 --- a/tests/workloads/device_inv_int/MI200/timestamps.csv +++ b/tests/workloads/device_inv_int/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001894911168,199001894935363,199001894955843,199001894968617 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001894966613,199001895045923,199001895062403,199001895063647 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,325033,325033,1048576,256,0,0,8,0,16,64,0x0,0x7f31a7fccec0,199001895073536,199001895083363,199001895098883,199001895100126 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4149441,4149441,1048576,256,0,0,8,0,16,64,0x0,0x7fc3cc4e4ec0,1412582414412809,1412582414437599,1412582414457599,1412582414473534 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4149441,4149441,1048576,256,0,0,8,0,16,64,0x0,0x7fc3cc4e4ec0,1412582414468815,1412582414476479,1412582414491999,1412582414549858 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4149441,4149441,1048576,256,0,0,8,0,16,64,0x0,0x7fc3cc4e4ec0,1412582414502669,1412582414551359,1412582414567679,1412582414568934 diff --git a/tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv index abd79556f9..badaa2ed6c 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,150756,150756,1048576,256,0,0,8,8,16,64,0x0,0x7f820df66e80,47744,47744,16384,65536,12856,1674844,194204807313230,194218184431477,194218184455957,194204815275476 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1246429,1246429,1048576,256,0,0,8,8,16,64,0x0,0x7fe4492acec0,47968,47968,16384,65536,13609,1730416,1410128918207610,1410140689683045,1410140689707365,1410128925944983 diff --git a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv index 61b0e93dcb..57601f8317 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,150941,150941,1048576,256,0,0,8,8,16,64,0x0,0x7fb5db332e80,0,0,0,194205315685723,194218184431477,194218184455957,194205323317172 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1246616,1246616,1048576,256,0,0,8,8,16,64,0x0,0x7fd526ad0ec0,0,0,0,1410129409181220,1410140689683045,1410140689707365,1410129416783247 diff --git a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv index 972eec206c..5353a4bf80 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151125,151125,1048576,256,0,0,8,8,16,64,0x0,0x7f690a0c0e80,65536,205956,26258976,194205816966838,194218184431477,194218184455957,194205824797164 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1246801,1246801,1048576,256,0,0,8,8,16,64,0x0,0x7f6611660ec0,65536,190502,24371720,1410129893979623,1410140689683045,1410140689707365,1410129901509554 diff --git a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv index 9d543ed6ad..abf925c684 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151312,151312,1048576,256,0,0,8,8,16,64,0x0,0x7fa9adb0ce80,32768,667106,85389576,194206315490934,194218184431477,194218184455957,194206323400790 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1247003,1247003,1048576,256,0,0,8,8,16,64,0x0,0x7f106ce74ec0,32768,667005,85368756,1410130378569022,1410140689683045,1410140689707365,1410130386436229 diff --git a/tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv index 790b97edc7..fe3c00bfc2 100644 --- a/tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,151497,151497,1048576,256,0,0,8,8,16,64,0x0,0x7fd5b2e38e80,48008,48008,17263,384072,16384,24600233,232757,0,98897844,194207844573840,194218184431477,194218184455957,194207852970067 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1247190,1247190,1048576,256,0,0,8,8,16,64,0x0,0x7f14d9abcec0,48766,48766,17302,390136,16384,24586988,235330,0,98882880,1410130866243399,1410140689683045,1410140689707365,1410130873900159 diff --git a/tests/workloads/dispatch_0/MI100/log.txt b/tests/workloads/dispatch_0/MI100/log.txt new file mode 100644 index 0000000000..a377dd64c8 --- /dev/null +++ b/tests/workloads/dispatch_0/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_0/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['0'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155314' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155314_1246269' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155314_1246269/input0_results_240321_155314' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155314_1246269/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155314_1246269/input0_results_240321_155314 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155315' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155315_1246456' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155315_1246456/input0_results_240321_155315' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155315_1246456/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155315_1246456/input0_results_240321_155315 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155315' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155315_1246641' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155315_1246641/input0_results_240321_155315' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155315_1246641/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155315_1246641/input0_results_240321_155315 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155316' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155316_1246843' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155316_1246843/input0_results_240321_155316' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155316_1246843/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155316_1246843/input0_results_240321_155316 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155316' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155316_1247030' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155316_1247030/input0_results_240321_155316' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155316_1247030/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155316_1247030/input0_results_240321_155316 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155317' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155317_1247215' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155317_1247215/input0_results_240321_155317' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155317_1247215/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155317_1247215/input0_results_240321_155317 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155317' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155317_1247399' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155317_1247399/input0_results_240321_155317' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155317_1247399/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155317_1247399/input0_results_240321_155317 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155318' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155318_1247585' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155318_1247585/input0_results_240321_155318' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155318_1247585/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155318_1247585/input0_results_240321_155318 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155318' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155318_1247769' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155318_1247769/input0_results_240321_155318' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155318_1247769/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155318_1247769/input0_results_240321_155318 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155319' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155319_1247953' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155319_1247953/input0_results_240321_155319' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155319_1247953/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155319_1247953/input0_results_240321_155319 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155320' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155320_1248137' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155320_1248137/input0_results_240321_155320' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155320_1248137/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155320_1248137/input0_results_240321_155320 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155320' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155320_1248321' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155320_1248321/input0_results_240321_155320' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155320_1248321/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155320_1248321/input0_results_240321_155320 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155321' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155321_1248508' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155321_1248508/input0_results_240321_155321' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155321_1248508/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155321_1248508/input0_results_240321_155321 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155322' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155322_1248693' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155322_1248693/input0_results_240321_155322' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155322_1248693/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155322_1248693/input0_results_240321_155322 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155322' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155322_1248877' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155322_1248877/input0_results_240321_155322' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155322_1248877/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155322_1248877/input0_results_240321_155322 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155323' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155323_1249063' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155323_1249063/input0_results_240321_155323' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155323_1249063/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155323_1249063/input0_results_240321_155323 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155323' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155323_1249264' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155323_1249264/input0_results_240321_155323' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155323_1249264/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155323_1249264/input0_results_240321_155323 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155324' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155324_1249450' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155324_1249450/input0_results_240321_155324' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155324_1249450/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155324_1249450/input0_results_240321_155324 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155324' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155324_1249642' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155324_1249642/input0_results_240321_155324' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155324_1249642/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155324_1249642/input0_results_240321_155324 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155325' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155325_1249827' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155325_1249827/input0_results_240321_155325' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155325_1249827/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155325_1249827/input0_results_240321_155325 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155325' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155325_1250013' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155325_1250013/input0_results_240321_155325' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155325_1250013/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155325_1250013/input0_results_240321_155325 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155326' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155326_1250199' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155326_1250199/input0_results_240321_155326' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155326_1250199/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155326_1250199/input0_results_240321_155326 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155326' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155326_1250388' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155326_1250388/input0_results_240321_155326' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155326_1250388/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155326_1250388/input0_results_240321_155326 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/dispatch_0/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_0/MI100/pmc_dispatch_info.csv index e90d72a8cf..4a20af5fc0 100644 --- a/tests/workloads/dispatch_0/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/dispatch_0/MI100/pmc_dispatch_info.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/dispatch_0/MI100/pmc_perf.csv b/tests/workloads/dispatch_0/MI100/pmc_perf.csv index 312389d032..a05e3d80a6 100644 --- a/tests/workloads/dispatch_0/MI100/pmc_perf.csv +++ b/tests/workloads/dispatch_0/MI100/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_5,obj_5,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_10,obj_10,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9b7aa06e80,0.0,64,0x7f5584210e80,4096,0,1935,0,4096,0,4,0,4099,0,673,0,4096,0,289,0,4096,0,431,0,4264,0,2540,0,4096,0,200,0,4096,0,6850,0,4096,0,2220,0,4098,0,155,0,4144,0,3511,0,4096,0,4462,0,4096,0,657,0,4096,0,280,0,4096,0,4755,0,4096,0,1052,0,4096,0,1770,0,4096,0,1068,0,4096,0,1662,0,4096,0,676,0,4096,0,2234,0,4096,0,1260,0,4096,0,853,0,4096,0,1203,0,4096,0,1029,0,4096,0,785,0,4096,0,4254,0,4097,0,614,0,4144,0,154,0,4096,0,1122,0,4096,0,2872,0,4096,0,3055,0,64,0x7f2d132cce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86608.0,44464.0,131112.0,0.0,64,0x7f49e98cee80,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,0,48963,0,0,64,0x7f9fb07dce80,131072.0,131072.0,0.0,2605084.0,0.0,0.0,91634054.0,56016744.0,64,0x7f8a5d196e80,1222,0,0,1672592,4137,0,0,2116484,2098,0,0,1855201,2630,0,0,1863877,1290,0,0,1755336,1301,0,0,1712227,1631,0,0,1809381,3344,0,0,1987834,1339,0,0,1790962,5144,0,0,2057655,1010,0,0,1740292,3317,0,0,1921560,4433,0,0,2139790,1177,0,0,1759290,845,0,0,1730331,4724,0,0,2113318,1217,0,0,1798941,1304,0,0,1734767,1490,0,0,1725463,2798,0,0,1882071,986,0,0,1737550,5807,0,0,2258275,2334,0,0,1863442,7724,0,0,2306468,3065,0,0,1909158,1358,0,0,1774221,1211,0,0,1748337,4580,0,0,2026474,977,0,0,1619259,6715,0,0,2261394,679,0,0,1669914,2749,0,0,1841898,64,0x7f7855560e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48592,0,131613.0,131072.0,0.0,131104.0,64,0x7fbcc9bf8e80,0,3744845,4096,4096,0,2419114,4096,4096,0,3527926,4096,4096,0,2991557,4096,4096,0,5028313,4096,4096,0,3041846,4096,4096,0,3725318,4096,4096,0,5222933,4096,4096,0,2765341,4096,4096,0,2604617,4096,4096,0,5094887,4096,4096,0,4430574,4096,4096,0,2585796,4096,4096,0,2774314,4096,4096,0,3775925,4096,4096,0,2776109,4096,4096,0,3241025,4096,4096,0,3624424,4096,4096,0,4396971,4096,4096,0,3841404,4096,4096,0,2863297,4096,4096,0,4437948,4096,4096,0,3158849,4096,4096,0,4356441,4096,4096,0,2607802,4096,4096,0,2700884,4096,4096,0,4086063,4096,4096,0,3906988,4096,4096,0,2954270,4096,4096,0,2865625,4096,4096,0,3464833,4096,4096,0,3219484,4096,4096,64,0x7fc5fb9dce80,385384,235430,3434307,16384,25114810,144,48,0,48172,48172,3883841.0,3057301.0,5938.0,928736.0,2103263.0,0.0,3048047.0,2736387.0,384063,245364,48172,0,48172,0,1541504.0,959387.0,0.0,0.0,64,0x7fe1aa3dce80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f0c9b118e80,0,0,192,0,65536,64468,48,1376,31964,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48151,1769,0,48.0,439.0,0.0,262288.0,64,0x7f1ebae36e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8355,4259,8355,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f7c145dae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,57167.0,122935.0,64,0x7fb464ddae80,191328,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13331,29715,9995,550,0,46439,262620.0,0.0,188.0,262432.0,64,0x7fc82ce98e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131309.0,0.0,466.0,131308.0,64,0x7f93c8fd2e80,2137191,360448,163840,0,0,180224,114688,0,70122419.0,194516738.0,77228435.0,131072.0,0.0,734493.0,0,0,27069,67406.0,0.0,0.0,67406.0,64,0x7f72bbc4ae80,32768,0,0,0,16384,16384,393216,22509426,960.0,513968.0,0.0,524288.0,1033477.0,32768.0,0,0,0,17038,131072.0,131072.0,0.0,131072.0,194218184431477,194218184455957 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_1,obj_1,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_2,obj_2,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_3,obj_3,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_4,obj_4,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_12,obj_12,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_13,obj_13,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_15,obj_15,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_16,obj_16,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fdf16010ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f8fc9004ec0,131072.0,131072.0,0.0,2397012.0,0.0,0.0,118229924.0,60611365.0,64,0x7f9387234ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86470.0,44602.0,131111.0,0.0,64,0x7f160d79cec0,0,4201507,4096,4096,0,4275180,4096,4096,0,4339387,4096,4096,0,3624466,4096,4096,0,3225088,4096,4096,0,3413034,4096,4096,0,3493999,4096,4096,0,3665272,4096,4096,0,3276657,4096,4096,0,4378166,4096,4096,0,3858260,4096,4096,0,3239125,4096,4096,0,4210863,4096,4096,0,3389251,4096,4096,0,3215112,4096,4096,0,3332578,4096,4096,0,3558394,4096,4096,0,3552344,4096,4096,0,3447215,4096,4096,0,3543267,4096,4096,0,3452696,4096,4096,0,3465847,4096,4096,0,2991378,4096,4096,0,3925635,4096,4096,0,3228945,4096,4096,0,5439135,4096,4096,0,3762284,4096,4096,0,3076102,4096,4096,0,3110209,4096,4096,0,3619341,4096,4096,0,3548030,4096,4096,0,3791426,4096,4096,64,0x7f374fcacec0,0,0,192,0,65536,64458,48,1504,32340,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48320,1857,0,48.0,448.0,0.0,262288.0,64,0x7faf6da40ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131413.0,0.0,674.0,131412.0,64,0x7fd84ed68ec0,4096,0,712,0,4096,0,1350,0,4362,0,3040,0,4099,0,8,0,4096,0,2265,0,4097,0,2808,0,4096,0,0,0,4096,0,731,0,4096,0,2016,0,4096,0,2871,0,4096,0,1082,0,4144,0,874,0,4144,0,111,0,4096,0,184,0,4096,0,272,0,4096,0,570,0,4096,0,2602,0,4096,0,3254,0,4096,0,1517,0,4096,0,0,0,4096,0,488,0,4096,0,472,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,2887,0,4096,0,1093,0,4096,0,0,0,4096,0,0,0,4096,0,657,0,4096,0,0,0,4096,0,0,0,64,0x7fcaeb6b8ec0,188440,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11521,27905,10132,588,0,47167,262720.0,0.0,188.0,262532.0,64,0x7f8a99be8ec0,4011333,360448,163840,0,0,180224,114688,0,58721634.0,162567360.0,62352365.0,131072.0,0.0,682000.0,0,0,28030,85249.0,0.0,0.0,85249.0,64,0x7f5ec7ea8ec0,3507,0,0,1903834,3001,0,0,1928027,2022,0,0,1890552,5502,0,0,2189838,1146,0,0,1669504,1874,0,0,1911536,2537,0,0,1955975,1410,0,0,1800306,1000,0,0,1714928,1832,0,0,1808242,2716,0,0,1935299,1154,0,0,1762162,2847,0,0,1960904,4262,0,0,2081584,1446,0,0,1728115,1518,0,0,1829974,3022,0,0,1921410,2371,0,0,1864787,3880,0,0,2023403,1847,0,0,1816545,3588,0,0,1933957,2533,0,0,1899045,5028,0,0,2084741,3061,0,0,2061105,5117,0,0,2143753,1516,0,0,1721184,2754,0,0,1910458,3379,0,0,1940221,1690,0,0,1789275,5594,0,0,2108069,1299,0,0,1780015,1128,0,0,1765851,64,0x7fdad6d10ec0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,0,48203,0,0,64,0x7fce0aff8ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47566,0,131534.0,131072.0,0.0,131104.0,64,0x7f7265e04ec0,32768,0,0,0,16384,16384,393216,21652912,960.0,513962.0,0.0,524288.0,1153963.0,32768.0,0,0,0,18936,131072.0,131072.0,0.0,131072.0,64,0x7f6f9c93cec0,0.0,64,0x7fa9da390ec0,382936,232926,3410882,16384,24816241,144,48,0,47866,47866,3845674.0,3032364.0,5271.0,1033858.0,2135545.0,0.0,3023553.0,2713545.0,381487,242844,47866,0,47866,0,1531712.0,952120.0,0.0,0.0,64,0x7f7c092e0ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8303,4207,8303,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,64,0x7ff9ce288ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,12539.0,122086.0,1410140689683045,1410140689707365 diff --git a/tests/workloads/dispatch_0/MI100/sysinfo.csv b/tests/workloads/dispatch_0/MI100/sysinfo.csv index 54e879b37d..b688f42cd4 100644 --- a/tests/workloads/dispatch_0/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_0/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:49 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:53:14 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_0/MI100/timestamps.csv b/tests/workloads/dispatch_0/MI100/timestamps.csv index fbc023c1d0..92e04815ff 100644 --- a/tests/workloads/dispatch_0/MI100/timestamps.csv +++ b/tests/workloads/dispatch_0/MI100/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,154895,154895,1048576,256,0,0,8,8,16,64,0x0,0x7f26e5422e80,194218184405603,194218184431477,194218184455957,194218184468662 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1250548,1250548,1048576,256,0,0,8,8,16,64,0x0,0x7f5d3a178ec0,1410140689657401,1410140689683045,1410140689707365,1410140689720210 diff --git a/tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv index dda5e22f08..9989044157 100644 --- a/tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306015,306015,1048576,256,0,0,8,0,16,64,0x0,0x7fd36d3a0ec0,27553,27553,16384,65536,14040,1568448,198487811862509,198500539781025,198500539801025,198487828148739 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4129674,4129674,1048576,256,0,0,8,0,16,64,0x0,0x7fd6b0670ec0,27647,27647,16384,65536,15995,1772908,1411974341510867,1411987252061945,1411987252082105,1411974357430774 diff --git a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv index bb1e96b729..276df3af62 100644 --- a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306217,306217,1048576,256,0,0,8,0,16,64,0x0,0x7f1d6cb44ec0,0,0,0,198488296151539,198500539781025,198500539801025,198488312049765 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4129876,4129876,1048576,256,0,0,8,0,16,64,0x0,0x7fe21d564ec0,0,0,0,1411974838805242,1411987252061945,1411987252082105,1411974854611815 diff --git a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv index 7de8913869..e8f8301b1b 100644 --- a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306419,306419,1048576,256,0,0,8,0,16,64,0x0,0x7efbf7208ec0,65536,172952,19460368,198488779287609,198500539781025,198500539801025,198488795365134 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4130063,4130063,1048576,256,0,0,8,0,16,64,0x0,0x7f1d223a4ec0,65536,180788,20162048,1411975328440803,1411987252061945,1411987252082105,1411975344459988 diff --git a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv index d9ca2ff134..faa0c6fea2 100644 --- a/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306621,306621,1048576,256,0,0,8,0,16,64,0x0,0x7f5805234ec0,32768,291597,32660248,198489259151227,198500539781025,198500539801025,198489275062158 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4130265,4130265,1048576,256,0,0,8,0,16,64,0x0,0x7f0353e08ec0,32768,297669,33333264,1411975811818671,1411987252061945,1411987252082105,1411975827995623 diff --git a/tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv index bfc0e93d5e..c9b3040acd 100644 --- a/tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,306807,306807,1048576,256,0,0,8,0,16,64,0x0,0x7fe505304ec0,28097,28097,10788,224784,16384,11140767,132548,0,45073020,198489738658391,198500539781025,198500539801025,198489754777786 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4130456,4130456,1048576,256,0,0,8,0,16,64,0x0,0x7f3ef1724ec0,27505,27505,10822,220048,16384,10699049,127069,0,43312188,1411976295988936,1411987252061945,1411987252082105,1411976312094343 diff --git a/tests/workloads/dispatch_0/MI200/log.txt b/tests/workloads/dispatch_0/MI200/log.txt new file mode 100644 index 0000000000..55e00ac41c --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/log.txt @@ -0,0 +1,764 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_0/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['0'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_162402' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162402_4129514' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162402_4129514/input0_results_240321_162402' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162402_4129514/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162402_4129514/input0_results_240321_162402 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_162402' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162402_4129716' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162402_4129716/input0_results_240321_162402' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162402_4129716/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162402_4129716/input0_results_240321_162402 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_162403' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162403_4129903' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162403_4129903/input0_results_240321_162403' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162403_4129903/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162403_4129903/input0_results_240321_162403 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_162403' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162403_4130105' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162403_4130105/input0_results_240321_162403' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162403_4130105/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162403_4130105/input0_results_240321_162403 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_162404' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162404_4130296' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162404_4130296/input0_results_240321_162404' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162404_4130296/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162404_4130296/input0_results_240321_162404 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_162404' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162404_4130482' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162404_4130482/input0_results_240321_162404' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162404_4130482/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162404_4130482/input0_results_240321_162404 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_162405' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162405_4130666' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162405_4130666/input0_results_240321_162405' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162405_4130666/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162405_4130666/input0_results_240321_162405 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_162405' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162405_4130869' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162405_4130869/input0_results_240321_162405' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162405_4130869/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162405_4130869/input0_results_240321_162405 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_162406' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162406_4131055' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162406_4131055/input0_results_240321_162406' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162406_4131055/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162406_4131055/input0_results_240321_162406 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_162406' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162406_4131241' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162406_4131241/input0_results_240321_162406' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162406_4131241/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162406_4131241/input0_results_240321_162406 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_162407' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162407_4131443' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162407_4131443/input0_results_240321_162407' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162407_4131443/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162407_4131443/input0_results_240321_162407 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_162407' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162407_4131627' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162407_4131627/input0_results_240321_162407' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162407_4131627/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162407_4131627/input0_results_240321_162407 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_162408' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162408_4131830' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162408_4131830/input0_results_240321_162408' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162408_4131830/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162408_4131830/input0_results_240321_162408 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_162409' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162409_4132018' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162409_4132018/input0_results_240321_162409' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162409_4132018/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162409_4132018/input0_results_240321_162409 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_162409' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162409_4132203' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162409_4132203/input0_results_240321_162409' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162409_4132203/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162409_4132203/input0_results_240321_162409 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_162410' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162410_4132405' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162410_4132405/input0_results_240321_162410' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162410_4132405/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162410_4132405/input0_results_240321_162410 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_162411' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162411_4132593' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162411_4132593/input0_results_240321_162411' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162411_4132593/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162411_4132593/input0_results_240321_162411 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_162411' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162411_4132780' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162411_4132780/input0_results_240321_162411' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162411_4132780/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162411_4132780/input0_results_240321_162411 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_162412' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162412_4132967' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162412_4132967/input0_results_240321_162412' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162412_4132967/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162412_4132967/input0_results_240321_162412 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_162412' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162412_4133152' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162412_4133152/input0_results_240321_162412' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162412_4133152/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162412_4133152/input0_results_240321_162412 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_162413' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162413_4133337' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162413_4133337/input0_results_240321_162413' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162413_4133337/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162413_4133337/input0_results_240321_162413 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_162413' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162413_4133523' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162413_4133523/input0_results_240321_162413' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162413_4133523/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162413_4133523/input0_results_240321_162413 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_162414' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162414_4133712' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162414_4133712/input0_results_240321_162414' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162414_4133712/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162414_4133712/input0_results_240321_162414 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_162414' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162414_4133901' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162414_4133901/input0_results_240321_162414' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162414_4133901/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162414_4133901/input0_results_240321_162414 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_162415' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162415_4134089' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162415_4134089/input0_results_240321_162415' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162415_4134089/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162415_4134089/input0_results_240321_162415 + |-> [rocprof] File 'tests/workloads/dispatch_0/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/dispatch_0/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/dispatch_0/MI200/pmc_dispatch_info.csv b/tests/workloads/dispatch_0/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..4a20af5fc0 --- /dev/null +++ b/tests/workloads/dispatch_0/MI200/pmc_dispatch_info.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/dispatch_0/MI200/pmc_perf.csv b/tests/workloads/dispatch_0/MI200/pmc_perf.csv index 961b0ab948..bcc1d11a7e 100644 --- a/tests/workloads/dispatch_0/MI200/pmc_perf.csv +++ b/tests/workloads/dispatch_0/MI200/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_2,obj_2,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_3,obj_3,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_9,obj_9,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_10,obj_10,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_11,obj_11,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_12,obj_12,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_13,obj_13,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_14,obj_14,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_15,obj_15,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_16,obj_16,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_17,obj_17,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_18,obj_18,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f93cfdd4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,43336787.0,35077708.0,0.0,64,0x7f851a7d8ec0,6368,0,4096,6395,0,4096,6376,0,4096,6370,0,4096,6377,0,4096,6414,0,4096,6318,0,4096,6373,0,4096,6372,0,4096,6369,0,4096,6399,0,4096,6369,0,4096,6371,0,4096,6379,0,4096,6419,0,4096,6322,0,4096,6400,0,4096,6361,0,4096,6378,0,4096,6400,0,4096,6363,0,4096,6407,0,4096,6380,0,4096,6571,0,4096,6405,0,4096,6408,0,4096,6362,0,4096,6379,0,4096,6397,0,4096,6363,0,4096,6411,0,4096,6380,0,4096,64,0x7f30ca774ec0,2278,4096,2278,6374,2298,4096,2298,6394,2251,4096,2251,6347,2335,4096,2335,6431,2283,4096,2283,6379,2300,4096,2300,6396,2254,4096,2254,6350,2312,4096,2312,6408,2368,4097,2369,6465,2279,4096,2279,6375,2300,4096,2300,6396,2254,4096,2254,6350,2337,4096,2337,6433,2285,4096,2285,6381,2306,4096,2306,6402,2254,4096,2254,6350,2291,4096,2291,6387,2252,4096,2252,6348,2300,4097,2301,6397,2289,4096,2289,6385,2276,4096,2276,6372,2276,4096,2276,6372,2303,4096,2303,6399,2487,4099,2490,6586,2325,4096,2325,6421,2298,4096,2298,6394,2255,4096,2255,6351,2303,4096,2303,6399,2292,4096,2292,6388,2275,4096,2275,6371,2279,4096,2279,6375,2308,4098,2310,6406,64,0x7f1fd64d0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10545,0,817,28162,0,73375.0,131072.0,0.0,65568.0,64,0x7f6eae674ec0,1289,124666,0,0,65536,63800,56,1680,64,0x7ffbeae70ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,943442.0,64,0x7f742fbbcec0,32768,32768,0,64,0x7fca046d4ec0,0,0,0,1026393,0,0,0,1204489,0,0,0,1050426,0,0,0,1202217,0,0,0,1153510,134,0,0,1242105,0,0,0,1084146,0,0,0,1175538,0,0,0,1125487,0,0,0,1052972,0,0,0,1044219,26,0,0,1160051,0,0,0,1118212,1,0,0,1094801,620,0,0,1347439,0,0,0,1172086,0,0,0,1114829,0,0,0,1071247,0,0,0,1102993,0,0,0,1209273,0,0,0,1120733,0,0,0,1088024,25,0,0,1138228,0,0,0,1072997,0,0,0,1018992,0,0,0,1122267,0,0,0,1102180,0,0,0,1155008,0,0,0,1095474,0,0,0,1048708,0,0,0,1136110,0,0,0,1133187,64,0x7fae6c0c0ec0,0,1062044,4096,4096,0,1407413,4096,4096,0,1209912,4096,4096,0,1354247,4096,4096,0,1300941,4096,4096,0,1380593,4096,4096,0,1183905,4096,4096,0,1504136,4096,4096,0,1202625,4096,4096,0,981032,4096,4096,0,1186111,4096,4096,0,1305893,4096,4096,0,1205538,4096,4096,0,1240714,4096,4096,0,1135766,4096,4096,0,1154158,4096,4096,0,1472010,4096,4096,0,1271905,4096,4096,0,1299419,4096,4096,0,1268868,4096,4096,0,1184696,4096,4096,0,1250092,4096,4096,0,1338418,4096,4096,0,1111864,4096,4096,0,1364313,4096,4096,0,1186114,4096,4096,0,1577678,4096,4096,0,1287611,4096,4096,0,1225532,4096,4096,0,1076946,4096,4096,0,1010342,4096,4096,0,1542983,4096,4096,64,0x7f7bb8440ec0,4096,0,0,0,4096,0,372,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,439,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f88d8c48ec0,0,393216,163840,0,0,0,0,0,18192,0.0,0.0,0.0,32768.0,0.0,0.0,418.0,32768.0,4096,16384,352,28238,1933,0,56.0,7.0,0.0,204299.0,64,0x7fb940cecec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,34210.0,46115.0,19421.0,64,0x7f7efb9c8ec0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,0,27661,0,0,64,0x7f8939398ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f02c9d00ec0,237056,132824,16384,0,16384,16384,32768,49152,29631,29631,2004384.0,1430992.0,3646.0,211725.0,1132729.0,0.0,1423412.0,1125171.0,235345,140962,29631,0,29631,0,948192.0,500665.0,0.0,0.0,64,0x7ff55a6b4ec0,0,0,0,224,0,65536,63760,56,64,0x7f00e95a8ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13240,19683,8487,549,0,27107,204650.0,0.0,73567.0,131083.0,64,0x7f4b21dd0ec0,11035356,9890398,800894,344064,1665326,0,0,163840,832.0,515136.0,0.0,524288.0,275956.0,32768.0,529651,0,0,10877,131072.0,131072.0,0.0,131072.0,64,0x7f258fa24ec0,114688,0,32768,32768,16384,16384,65536,49152,29054970.0,90445211.0,39684969.0,131072.0,0.0,248878.0,0,0,15521,1027.0,131082.0,0.0,12.0,198500539781025,198500539801025 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_1,obj_1,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_2,obj_2,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_4,obj_4,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_5,obj_5,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_6,obj_6,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_7,obj_7,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_8,obj_8,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_9,obj_9,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_10,obj_10,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_13,obj_13,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_14,obj_14,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_15,obj_15,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_16,obj_16,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_17,obj_17,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_18,obj_18,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f4bd8140ec0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,0,27668,0,0,64,0x7f97f7c10ec0,32768,32768,0,64,0x7f58ffa54ec0,0,393216,163840,0,0,0,0,0,18971,0.0,0.0,0.0,32768.0,0.0,0.0,431.0,32768.0,4096,16384,352,29771,2125,0,56.0,6.0,0.0,204356.0,64,0x7f220701cec0,0,1154155,4096,4096,0,1132805,4096,4096,0,1374037,4096,4096,0,1573411,4096,4096,0,1125987,4096,4096,0,1176838,4096,4096,0,1208180,4096,4096,0,1563190,4096,4096,0,1224180,4096,4096,0,1065353,4096,4096,0,1007185,4096,4096,0,1366501,4096,4096,0,1100892,4096,4096,0,1173735,4096,4096,0,1368405,4096,4096,0,1328813,4096,4096,0,1495001,4096,4096,0,1283146,4096,4096,0,906555,4096,4096,0,1514084,4096,4096,0,1348338,4096,4096,0,1321985,4096,4096,0,1121583,4096,4096,0,1085979,4096,4096,0,1066518,4096,4096,0,1228405,4096,4096,0,1233098,4096,4096,0,1170189,4096,4096,0,1516520,4096,4096,0,1359551,4096,4096,0,1475981,4096,4096,0,1154325,4096,4096,64,0x7f6a698d8ec0,0,0,0,1040438,0,0,0,1127061,0,0,0,978940,0,0,0,1090488,0,0,0,1131301,0,0,0,1024733,0,0,0,989481,0,0,0,1078230,0,0,0,1044065,0,0,0,1003526,0,0,0,1036308,0,0,0,1037243,0,0,0,998788,98,0,0,1168561,4,0,0,1099902,0,0,0,1082115,10,0,0,1073014,0,0,0,1009868,0,0,0,1023589,0,0,0,1091845,0,0,0,1123462,0,0,0,1043279,0,0,0,980717,0,0,0,1040034,0,0,0,1015125,52,0,0,1073443,0,0,0,1061215,0,0,0,1074910,0,0,0,1076438,0,0,0,1170878,0,0,0,964103,0,0,0,1148042,64,0x7fc38ef9cec0,4096,0,0,0,4096,0,103,0,4096,0,0,0,4096,0,36,0,4096,0,0,0,4097,0,27,0,4096,0,0,0,4096,0,129,0,4096,0,0,0,4096,0,0,0,4096,0,45,0,4096,0,70,0,4096,0,89,0,4096,0,0,0,4096,0,26,0,4096,0,26,0,4096,0,87,0,4097,0,144,0,4096,0,23,0,4096,0,102,0,4096,0,233,0,4096,0,75,0,4100,0,6,0,4099,0,12,0,4096,0,267,0,4096,0,0,0,4096,0,180,0,4096,0,37,0,4096,0,355,0,4096,0,258,0,4096,0,37,0,4096,0,35,0,64,0x7f854fa90ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,34388.0,46134.0,19402.0,64,0x7ffbc1ce8ec0,6380,0,4096,6338,0,4096,6338,0,4096,6379,0,4096,6368,0,4096,6359,0,4096,6350,0,4096,6380,0,4096,6379,0,4096,6378,0,4096,6343,0,4096,6340,0,4096,6379,0,4096,6370,0,4096,6357,0,4096,6354,0,4096,6360,0,4096,6406,0,4096,6417,0,4096,6380,0,4096,6382,0,4096,6421,0,4096,6372,0,4096,6594,0,4096,6425,0,4096,6358,0,4096,6406,0,4096,6424,0,4096,6379,0,4096,6379,0,4096,6419,0,4096,6376,0,4096,64,0x7fcfde730ec0,11288895,10008133,936698,344064,1702714,0,0,163840,832.0,515136.0,0.0,524288.0,327469.0,32768.0,532008,0,0,10924,131072.0,131072.0,0.0,131072.0,64,0x7f8db66f8ec0,114688,0,32768,32768,16384,16384,65536,49152,28282487.0,86353827.0,39916573.0,131072.0,0.0,226559.0,0,0,15840,329.0,131080.0,0.0,8.0,64,0x7f438ca68ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,11380,0,814,28639,0,73392.0,131072.0,0.0,65568.0,64,0x7f1d22978ec0,2268,4096,2268,6364,2261,4096,2261,6357,2279,4096,2279,6375,2256,4096,2256,6352,2233,4097,2234,6330,2269,4096,2269,6365,2258,4096,2258,6354,2329,4096,2329,6425,2332,4096,2332,6428,2265,4096,2265,6361,2260,4096,2260,6356,2278,4096,2278,6374,2256,4096,2256,6352,2232,4096,2232,6328,2270,4100,2274,6370,2316,4097,2317,6413,2257,4096,2257,6353,2303,4096,2303,6399,2256,4097,2257,6353,2284,4096,2284,6380,2273,4096,2273,6369,2316,4096,2316,6412,2268,4096,2268,6364,2390,4098,2392,6488,2227,4096,2227,6323,2260,4097,2261,6357,2306,4096,2306,6402,2259,4096,2259,6355,2285,4096,2285,6381,2274,4096,2274,6370,2315,4096,2315,6411,2275,4096,2275,6371,64,0x7f4241794ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,955258.0,64,0x7f4243eb4ec0,1212,116311,0,0,65536,63800,56,1680,64,0x7f49646a0ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41690584.0,36097819.0,0.0,64,0x7f06d4278ec0,0,0,0,224,0,65536,64187,56,64,0x7f1380294ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13321,18984,8100,545,0,27099,204116.0,0.0,73037.0,131079.0,64,0x7f4060cbcec0,227200,127301,16384,0,16384,16384,32768,49152,28399,28399,1932520.0,1342467.0,3677.0,156725.0,1047685.0,0.0,1334488.0,1037061.0,225489,135416,28399,0,28399,0,908768.0,487455.0,0.0,0.0,64,0x7f6eaebd8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,1411987252061945,1411987252082105 diff --git a/tests/workloads/dispatch_0/MI200/roofline.csv b/tests/workloads/dispatch_0/MI200/roofline.csv index 1737f5f365..b916e14c4c 100644 --- a/tests/workloads/dispatch_0/MI200/roofline.csv +++ b/tests/workloads/dispatch_0/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.2593,1387.6742,1388.8444,5015.6343,5012.4912,5018.7773,9223.3535,9222.6689,9224.0381,18050.238,18049.146,18051.33,20933.475,20873.053,20993.896,20262.736,20262.088,20263.385,170396.28,170393.2,170399.36,164844.48,164840.03,164848.94,41410.918,41410.391,41411.445,41466.852,41465.879,41467.824,166299.94,165807.45,166792.42 -1,1389.0791,1388.4865,1389.6718,5026.2217,5024.4121,5028.0312,9233.2822,9232.6641,9233.9004,18090.092,18086.539,18093.645,20971.795,20904.992,21038.598,20290.67,20290.035,20291.305,170824.69,170820.02,170829.36,165107.66,165105.09,165110.22,41487.414,41486.652,41488.176,41542.918,41542,41543.836,166879.25,166876.3,166882.2 -2,1388.9591,1388.4004,1389.5178,5035.1958,5033.0864,5037.3052,9261.5215,9260.8203,9262.2227,18107.543,18106.791,18108.295,21047.707,21047.246,21048.168,20351.348,20350.775,20351.92,171110.19,171106.17,171114.2,165507.5,165502.62,165512.38,41583.355,41582.031,41584.68,41637.441,41636.102,41638.781,166941.58,166351.8,167531.36 -3,1389.1071,1388.4954,1389.7188,5030.6714,5029.2788,5032.064,9241.2998,9240.582,9242.0176,18023.967,18020.326,18027.607,21036.178,21035.668,21036.688,20311.578,20310.953,20312.203,171023.28,171018.56,171028,165224.14,165220.2,165228.08,41439.121,41285.898,41592.344,41578.496,41577.977,41579.016,166999.5,166997.89,167001.11 +0,1388.7638,1388.2611,1389.2665,5016.8418,5013.7964,5019.8872,9224.1777,9223.6074,9224.748,17710.416,17707.119,17713.713,20937.773,20877.453,20998.094,20269.176,20268.652,20269.699,170438.3,170435.23,170441.36,164898.08,164893.94,164902.22,41427.383,41426.621,41428.145,41485.637,41485.012,41486.262,166383.89,165891.39,166876.39 +1,1388.9694,1388.4139,1389.5248,5028.8188,5026.9424,5030.6953,9237.1611,9236.4932,9237.8291,18241.684,18239.088,18244.279,20984.367,20916.609,21052.125,20301.172,20300.59,20301.754,170908.77,170904.42,170913.11,165165.75,165162.45,165169.05,41492.887,41492.227,41493.547,41552.719,41551.84,41553.598,166921.41,166918.52,166924.3 +2,1388.7931,1388.2235,1389.3627,5035.6152,5033.5068,5037.7236,9259.1699,9258.3154,9260.0244,18217.061,18216.146,18217.975,21046.363,21045.939,21046.787,20348.338,20347.758,20348.918,171116.91,171113.22,171120.59,165500.02,165496.81,165503.22,41579.711,41579.117,41580.305,41638.535,41637.797,41639.273,166945.91,166353.61,167538.2 +3,1388.9321,1388.3486,1389.5156,5033.4414,5031.8975,5034.9854,9238.9033,9238.1846,9239.6221,18333.842,18332.98,18334.703,21036.322,21036.035,21036.609,20310.521,20309.934,20311.109,171059.27,171054.39,171064.14,165193.59,165187.11,165200.08,41439.648,41286.48,41592.816,41576.109,41574.953,41577.266,166995.31,166989.83,167000.8 diff --git a/tests/workloads/dispatch_0/MI200/sysinfo.csv b/tests/workloads/dispatch_0/MI200/sysinfo.csv index 0bead8f0b0..f74fde750f 100644 --- a/tests/workloads/dispatch_0/MI200/sysinfo.csv +++ b/tests/workloads/dispatch_0/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_0,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:19:14 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +dispatch_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:24:01 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_0/MI200/timestamps.csv b/tests/workloads/dispatch_0/MI200/timestamps.csv index e1869601c3..312e4ccb26 100644 --- a/tests/workloads/dispatch_0/MI200/timestamps.csv +++ b/tests/workloads/dispatch_0/MI200/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,310582,310582,1048576,256,0,0,8,0,16,64,0x0,0x7f0fb9e1cec0,198500539756684,198500539781025,198500539801025,198500539812330 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4134249,4134249,1048576,256,0,0,8,0,16,64,0x0,0x7f2a3a720ec0,1411987252036982,1411987252061945,1411987252082105,1411987252094040 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv index 41b9a35a9c..a3ff5f71b8 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,155261,155261,1048576,256,0,0,8,8,16,64,0x0,0x7fdace5aee80,48843,48843,16384,65536,14557,1859980,194220648419385,194232901432521,194232901456681,194220656370350 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,155261,155261,1048576,256,0,0,8,8,16,64,0x0,0x7fdace5aee80,42042,42042,16384,65536,8064,1048588,194220656392682,194232901551561,194232901570601,194220656709111 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1250911,1250911,1048576,256,0,0,8,8,16,64,0x0,0x7f166b404ec0,48346,48346,16384,65536,13303,1721468,1410143003879101,1410154854825909,1410154854850869,1410143011603459 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1250911,1250911,1048576,256,0,0,8,8,16,64,0x0,0x7f166b404ec0,43911,43911,16384,65536,8117,1048588,1410143011625420,1410154854934389,1410154854953269,1410143011979598 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv index f0dd1bf8e3..e5f8bd957b 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,155449,155449,1048576,256,0,0,8,8,16,64,0x0,0x7f0144e1ee80,0,0,0,194221143127145,194232901432521,194232901456681,194221150750408 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,155449,155449,1048576,256,0,0,8,8,16,64,0x0,0x7f0144e1ee80,0,0,0,194221150769896,194232901551561,194232901570601,194221151079862 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1251095,1251095,1048576,256,0,0,8,8,16,64,0x0,0x7f7a7aa0cec0,0,0,0,1410143493832086,1410154854825909,1410154854850869,1410143501573616 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1251095,1251095,1048576,256,0,0,8,8,16,64,0x0,0x7f7a7aa0cec0,0,0,0,1410143501592832,1410154854934389,1410154854953269,1410143501923235 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv index 264df07706..66a6a65d82 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,155638,155638,1048576,256,0,0,8,8,16,64,0x0,0x7fd3082b2e80,65536,220822,28203128,194221637472508,194232901432521,194232901456681,194221645453088 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,155638,155638,1048576,256,0,0,8,8,16,64,0x0,0x7fd3082b2e80,65536,199286,25574192,194221645471273,194232901551561,194232901570601,194221645910755 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1251284,1251284,1048576,256,0,0,8,8,16,64,0x0,0x7f7f243e8ec0,65536,193338,24849584,1410143974171880,1410154854825909,1410154854850869,1410143981794526 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1251284,1251284,1048576,256,0,0,8,8,16,64,0x0,0x7f7f243e8ec0,65536,172672,22150704,1410143981814644,1410154854934389,1410154854953269,1410143982124227 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv index 7518891d3e..4789929dce 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,155824,155824,1048576,256,0,0,8,8,16,64,0x0,0x7ff8d92c4e80,32768,651728,83429440,194222135704660,194232901432521,194232901456681,194222143498788 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,155824,155824,1048576,256,0,0,8,8,16,64,0x0,0x7ff8d92c4e80,32768,664228,85004888,194222143519427,194232901551561,194232901570601,194222143811741 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1251471,1251471,1048576,256,0,0,8,8,16,64,0x0,0x7f201c50cec0,32768,654915,83820200,1410144454263265,1410154854825909,1410154854850869,1410144462045633 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1251471,1251471,1048576,256,0,0,8,8,16,64,0x0,0x7f201c50cec0,32768,662829,84839104,1410144462066883,1410154854934389,1410154854953269,1410144462370145 diff --git a/tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv index 3059357307..7d5fc510e0 100644 --- a/tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,156011,156011,1048576,256,0,0,8,8,16,64,0x0,0x7f6b448cee80,48616,48616,17826,388936,16384,25474846,236631,0,102389564,194222631809706,194232901432521,194232901456681,194222639570670 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,156011,156011,1048576,256,0,0,8,8,16,64,0x0,0x7f6b448cee80,42631,42631,13289,341056,16384,25728907,236499,0,103400652,194222639598924,194232901551561,194232901570601,194222639909191 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1251655,1251655,1048576,256,0,0,8,8,16,64,0x0,0x7f0a556ccec0,48291,48291,17364,386336,16384,25414292,236101,0,102182372,1410144945077695,1410154854825909,1410154854850869,1410144952673600 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1251655,1251655,1048576,256,0,0,8,8,16,64,0x0,0x7f0a556ccec0,42378,42378,13334,339032,16384,25188655,233462,0,101275544,1410144952703446,1410154854934389,1410154854953269,1410144953024913 diff --git a/tests/workloads/dispatch_0_1/MI100/log.txt b/tests/workloads/dispatch_0_1/MI100/log.txt new file mode 100644 index 0000000000..c13721b337 --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_0_1/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['0:2'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155329' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155329_1250751' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155329_1250751/input0_results_240321_155329' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155329_1250751/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155329_1250751/input0_results_240321_155329 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155329' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155329_1250935' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155329_1250935/input0_results_240321_155329' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155329_1250935/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155329_1250935/input0_results_240321_155329 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155329' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155329_1251119' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155329_1251119/input0_results_240321_155329' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155329_1251119/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155329_1251119/input0_results_240321_155329 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155330' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155330_1251311' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155330_1251311/input0_results_240321_155330' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155330_1251311/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155330_1251311/input0_results_240321_155330 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155330' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155330_1251495' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155330_1251495/input0_results_240321_155330' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155330_1251495/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155330_1251495/input0_results_240321_155330 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155331' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155331_1251682' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155331_1251682/input0_results_240321_155331' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155331_1251682/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155331_1251682/input0_results_240321_155331 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155331' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155331_1251870' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155331_1251870/input0_results_240321_155331' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155331_1251870/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155331_1251870/input0_results_240321_155331 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155332' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155332_1252058' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155332_1252058/input0_results_240321_155332' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155332_1252058/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155332_1252058/input0_results_240321_155332 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155332' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155332_1252244' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155332_1252244/input0_results_240321_155332' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155332_1252244/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155332_1252244/input0_results_240321_155332 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155333' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155333_1252429' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155333_1252429/input0_results_240321_155333' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155333_1252429/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155333_1252429/input0_results_240321_155333 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155334' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155334_1252613' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155334_1252613/input0_results_240321_155334' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155334_1252613/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155334_1252613/input0_results_240321_155334 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155334' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155334_1252797' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155334_1252797/input0_results_240321_155334' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155334_1252797/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155334_1252797/input0_results_240321_155334 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155335' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155335_1252983' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155335_1252983/input0_results_240321_155335' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155335_1252983/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155335_1252983/input0_results_240321_155335 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155336' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155336_1253167' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155336_1253167/input0_results_240321_155336' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155336_1253167/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155336_1253167/input0_results_240321_155336 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155336' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155336_1253354' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155336_1253354/input0_results_240321_155336' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155336_1253354/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155336_1253354/input0_results_240321_155336 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155337' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155337_1253542' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155337_1253542/input0_results_240321_155337' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155337_1253542/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155337_1253542/input0_results_240321_155337 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155337' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155337_1253727' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155337_1253727/input0_results_240321_155337' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155337_1253727/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155337_1253727/input0_results_240321_155337 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155338' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155338_1253912' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155338_1253912/input0_results_240321_155338' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155338_1253912/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155338_1253912/input0_results_240321_155338 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155338' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155338_1254097' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155338_1254097/input0_results_240321_155338' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155338_1254097/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155338_1254097/input0_results_240321_155338 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155339' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155339_1254281' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155339_1254281/input0_results_240321_155339' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155339_1254281/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155339_1254281/input0_results_240321_155339 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155339' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155339_1254470' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155339_1254470/input0_results_240321_155339' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155339_1254470/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155339_1254470/input0_results_240321_155339 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155340' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155340_1254658' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155340_1254658/input0_results_240321_155340' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155340_1254658/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155340_1254658/input0_results_240321_155340 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155340' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155340_1254842' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155340_1254842/input0_results_240321_155340' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155340_1254842/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_155340_1254842/input0_results_240321_155340 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/dispatch_0_1/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_0_1/MI100/pmc_dispatch_info.csv index aef03adc37..930dfccaaa 100644 --- a/tests/workloads/dispatch_0_1/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/dispatch_0_1/MI100/pmc_dispatch_info.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/dispatch_0_1/MI100/pmc_perf.csv b/tests/workloads/dispatch_0_1/MI100/pmc_perf.csv index 0b11068099..2395082690 100644 --- a/tests/workloads/dispatch_0_1/MI100/pmc_perf.csv +++ b/tests/workloads/dispatch_0_1/MI100/pmc_perf.csv @@ -1,3 +1,3 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_3,obj_3,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_5,obj_5,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_16,obj_16,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb7f3d0ce80,32768,0,0,0,16384,16384,393216,22799363,960.0,513857.0,0.0,524288.0,937675.0,32768.0,0,0,0,17815,131072.0,131072.0,0.0,131072.0,64,0x7fec0dfd4e80,2530,0,0,1876463,1318,0,0,1674383,2929,0,0,1846800,1217,0,0,1773852,1883,0,0,1835287,437,0,0,1493268,2967,0,0,1918568,3235,0,0,1967857,1829,0,0,1879028,1904,0,0,1851091,2803,0,0,1999877,812,0,0,1654335,3345,0,0,2041352,997,0,0,1652931,2842,0,0,2041954,972,0,0,1739774,1449,0,0,1836713,1161,0,0,1719512,2556,0,0,1999577,1288,0,0,1632407,7073,0,0,2233833,970,0,0,1679503,2898,0,0,1954081,2192,0,0,1799634,2284,0,0,1894442,1447,0,0,1808942,5278,0,0,2158118,3740,0,0,2014092,3529,0,0,1934980,824,0,0,1671081,1771,0,0,1871654,1645,0,0,1740421,64,0x7f82b4402e80,2428980,360448,163840,0,0,180224,114688,0,70560227.0,201876389.0,77164444.0,131072.0,0.0,662088.0,0,0,27363,83368.0,0.0,0.0,83368.0,64,0x7f20ccc84e80,0,0,192,0,65536,64517,48,1292,31708,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47648,1777,0,48.0,337.0,0.0,262288.0,64,0x7fc7127aae80,4096,0,8709,0,4096,0,852,0,4099,0,0,0,4096,0,691,0,4096,0,0,0,4096,0,118,0,4096,0,516,0,4096,0,550,0,4096,0,0,0,4096,0,136,0,4144,0,19,0,4096,0,602,0,4096,0,597,0,4096,0,1529,0,4096,0,22,0,4096,0,0,0,4096,0,0,0,4144,0,1211,0,4096,0,570,0,4096,0,778,0,4096,0,439,0,4097,0,527,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,58,0,4096,0,14,0,4096,0,1361,0,4215,0,337,0,64,0x7f8fffc3ae80,186813,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13518,29902,9775,550,0,47381,262828.0,0.0,188.0,262640.0,64,0x7fd1e9c0ce80,131072.0,131072.0,0.0,2643188.0,0.0,0.0,125484369.0,59505093.0,64,0x7f9a451d4e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8373,4277,8373,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3bfaa68e80,383200,231552,3387407,16384,24201346,144,48,0,47899,47899,3826016.0,3009789.0,5558.0,1115673.0,2076619.0,0.0,3000511.0,2690377.0,381487,241484,47899,0,47899,0,1532768.0,964572.0,0.0,0.0,64,0x7f3a4c3cae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131384.0,0.0,616.0,131383.0,64,0x7f6e434a0e80,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,64,0x7f0531c0ce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86382.0,44690.0,131111.0,0.0,64,0x7f1f4682ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,38563.0,102086.0,64,0x7fcdd7804e80,0.0,64,0x7fad9aa9ee80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6b1a2aae80,0,3283429,4096,4096,0,4714789,4096,4096,0,2645901,4096,4096,0,3322523,4096,4096,0,3604637,4096,4096,0,3470840,4096,4096,0,3118047,4096,4096,0,3275482,4096,4096,0,3119950,4096,4096,0,3914636,4096,4096,0,5112391,4096,4096,0,3832640,4096,4096,0,5169291,4096,4096,0,4131816,4096,4096,0,3060466,4096,4096,0,3320476,4096,4096,0,4224276,4096,4096,0,4108513,4096,4096,0,3646382,4096,4096,0,4389395,4096,4096,0,4566367,4096,4096,0,4328148,4096,4096,0,2683668,4096,4096,0,3681846,4096,4096,0,3058709,4096,4096,0,4411880,4096,4096,0,4014910,4096,4096,0,3041667,4096,4096,0,3252977,4096,4096,0,3876865,4096,4096,0,3419351,4096,4096,0,3449367,4096,4096,64,0x7f662f32ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46996,0,131485.0,131072.0,0.0,131104.0,194232901432521,194232901456681 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb7f3d0ce80,32768,0,0,0,16384,16384,393216,23156011,960.0,513866.0,0.0,524288.0,1047326.0,32768.0,0,0,0,13390,86481.0,86481.0,0.0,86481.0,64,0x7fec0dfd4e80,1199,0,0,1317635,770,0,0,1308323,5148,0,0,1828726,5232,0,0,1800526,1929,0,0,1418453,1347,0,0,1383143,1508,0,0,1409509,5774,0,0,1874876,1370,0,0,1297879,1891,0,0,1382200,3785,0,0,1765809,3850,0,0,1774111,757,0,0,1232782,4082,0,0,1709004,3538,0,0,1658257,5786,0,0,1805313,539,0,0,1228118,594,0,0,1202674,3376,0,0,1640532,7139,0,0,1907019,1604,0,0,1375297,4852,0,0,1670716,5046,0,0,1773185,5201,0,0,1771851,1636,0,0,1410163,902,0,0,1245278,5480,0,0,1790857,6434,0,0,1815149,1667,0,0,1308244,1039,0,0,1237987,2566,0,0,1578243,4948,0,0,1751575,64,0x7f82b4402e80,1647014,360448,163840,0,0,180224,114688,0,71052221.0,186613591.0,79262691.0,131072.0,0.0,630120.0,0,0,25726,63283.0,0.0,0.0,63283.0,64,0x7f20ccc84e80,0,0,48,0,65536,65536,0,0,30904,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42850,1734,0,48.0,365.0,0.0,262144.0,64,0x7fc7127aae80,4097,0,2082,0,4096,0,985,0,4096,0,3292,0,4096,0,1649,0,4096,0,2981,0,4096,0,5470,0,4096,0,658,0,4097,0,2363,0,4096,0,1736,0,4096,0,4399,0,4144,0,640,0,4096,0,3042,0,4096,0,2005,0,4096,0,990,0,4096,0,3626,0,4096,0,578,0,4096,0,4152,0,4144,0,1210,0,4096,0,1148,0,4096,0,2798,0,4096,0,814,0,4097,0,856,0,4096,0,2375,0,4099,0,2799,0,4096,0,4314,0,4096,0,90,0,4096,0,287,0,4096,0,792,0,4096,0,1252,0,4096,0,4667,0,4096,0,2086,0,4168,0,2320,0,64,0x7f8fffc3ae80,186371,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13277,29661,8692,2426,0,42069,262645.0,0.0,47.0,262598.0,64,0x7fd1e9c0ce80,131072.0,131072.0,0.0,2662368.0,0.0,0.0,124135047.0,46283642.0,64,0x7f9a451d4e80,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8338,4242,8338,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3bfaa68e80,343224,227063,3322094,16384,24227873,0,48,0,42902,42902,3695444.0,3037195.0,5782.0,975253.0,2009754.0,0.0,3028517.0,2717822.0,343216,236379,42902,0,42902,0,1372864.0,813272.0,0.0,0.0,64,0x7f3a4c3cae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131306.0,0.0,466.0,131305.0,64,0x7f6e434a0e80,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,0,41908,0,0,64,0x7f0531c0ce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86500.0,0.0,131118.0,0.0,64,0x7f1f4682ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,72533.0,144651.0,64,0x7fcdd7804e80,0.0,64,0x7fad9aa9ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f6b1a2aae80,0,5390743,2740,2740,0,4529613,2749,2749,0,3030456,2682,2682,0,3267365,2714,2714,0,4057592,2704,2704,0,4616353,2728,2728,0,3500249,2716,2716,0,2628551,2728,2728,0,3855143,2706,2706,0,3803408,2712,2712,0,4310852,2720,2720,0,4853321,2724,2724,0,4445389,2710,2710,0,4393337,2696,2696,0,3989937,2690,2690,0,3824329,2674,2674,0,4690996,2695,2695,0,4979742,2728,2728,0,4405812,2672,2672,0,5443521,2712,2712,0,3302766,2721,2721,0,3386652,2747,2747,0,3291027,2691,2691,0,3068963,2704,2704,0,5033160,2722,2722,0,3759041,2720,2720,0,3146656,2724,2724,0,2792034,2705,2705,0,4447282,2716,2716,0,4002383,2754,2754,0,4432364,2710,2710,0,3805608,2680,2680,64,0x7f662f32ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,2884,45628,6588,131354.0,131072.0,0.0,131103.0,194232901551561,194232901570601 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_5,obj_5,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_6,obj_6,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_7,obj_7,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_8,obj_8,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_9,obj_9,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_10,obj_10,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_11,obj_11,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_12,obj_12,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_13,obj_13,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_14,obj_14,TCC_EA_ATOMIC_LEVEL_sum,wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f75665ccec0,131072.0,131072.0,0.0,2566472.0,0.0,0.0,129911380.0,60971701.0,64,0x7fadb7fe8ec0,3747,0,0,1945704,3846,0,0,1955491,2303,0,0,1805747,1746,0,0,1745576,6261,0,0,2253513,3142,0,0,1902167,1356,0,0,1668201,1506,0,0,1763086,2276,0,0,1785714,2760,0,0,1885912,2120,0,0,1805801,2176,0,0,1867241,2844,0,0,1865657,3257,0,0,1928493,2629,0,0,1864618,5107,0,0,2095598,3246,0,0,1918125,4873,0,0,2055113,1697,0,0,1699409,1166,0,0,1601416,3630,0,0,1924444,4710,0,0,2062798,2635,0,0,1803824,2793,0,0,1827148,4419,0,0,1992861,4173,0,0,1993044,1790,0,0,1736129,1352,0,0,1793500,3962,0,0,2029251,2890,0,0,1786752,2149,0,0,1785826,1338,0,0,1738175,64,0x7fba70fa4ec0,32768,0,0,0,16384,16384,393216,22883669,960.0,513946.0,0.0,524288.0,979409.0,32768.0,0,0,0,17567,131072.0,131072.0,0.0,131072.0,64,0x7fa7b9df8ec0,2954285,360448,163840,0,0,180224,114688,0,59907762.0,160423966.0,72760731.0,131072.0,0.0,546328.0,0,0,26832,161807.0,0.0,0.0,161807.0,64,0x7fdc4c700ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131413.0,0.0,674.0,131412.0,64,0x7f8c7350cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,71694.0,137748.0,64,0x7fb128c58ec0,393240,236808,3432254,16384,25399418,144,48,0,49154,49154,3904320.0,3055242.0,4801.0,1074597.0,2240999.0,0.0,3046025.0,2737207.0,391855,246758,49154,0,49154,0,1572928.0,970299.0,0.0,0.0,64,0x7f2373ab4ec0,0,0,192,0,65536,64449,48,1360,32353,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48485,1863,0,48.0,466.0,0.0,262288.0,64,0x7f2f75968ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47584,0,131650.0,131072.0,0.0,131104.0,64,0x7f5d729c0ec0,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8313,4217,8313,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fe378560ec0,196604,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12868,29252,10064,588,0,47248,262614.0,0.0,188.0,262426.0,64,0x7f5d4acc8ec0,0,3755065,4096,4096,0,3193016,4096,4096,0,3919067,4096,4096,0,2950886,4096,4096,0,3413384,4096,4096,0,3635605,4096,4096,0,4659564,4096,4096,0,3409195,4096,4096,0,3988807,4096,4096,0,3542024,4096,4096,0,3980841,4096,4096,0,3721567,4096,4096,0,3230615,4096,4096,0,4093271,4096,4096,0,3861098,4096,4096,0,3043277,4096,4096,0,3948817,4096,4096,0,4480398,4096,4096,0,3738056,4096,4096,0,3710628,4096,4096,0,4274297,4096,4096,0,3119493,4096,4096,0,4032304,4096,4096,0,2928710,4096,4096,0,3091694,4096,4096,0,3827657,4096,4096,0,4454580,4096,4096,0,3242672,4096,4096,0,3347310,4096,4096,0,3936309,4096,4096,0,3571354,4096,4096,0,4968928,4096,4096,64,0x7f369015cec0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,0,48956,0,0,64,0x7f5ac6cd0ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f87f94a0ec0,0.0,64,0x7f006b4a4ec0,4096,0,1460,0,4224,0,5579,0,4096,0,2349,0,4099,0,127,0,4096,0,0,0,4096,0,583,0,4096,0,2785,0,4096,0,2463,0,4096,0,1642,0,4096,0,2199,0,4097,0,586,0,4144,0,5845,0,4096,0,1655,0,4144,0,1464,0,4096,0,1385,0,4096,0,0,0,4096,0,6217,0,4096,0,4403,0,4096,0,2387,0,4096,0,1557,0,4096,0,667,0,4096,0,3519,0,4096,0,2028,0,4096,0,2610,0,4216,0,787,0,4096,0,767,0,4096,0,1364,0,4096,0,0,0,4096,0,2835,0,4096,0,1061,0,4096,0,1027,0,4096,0,729,0,64,0x7f7ab6bd8ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86847.0,44225.0,131111.0,0.0,1410154854825909,1410154854850869 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f75665ccec0,131072.0,131072.0,0.0,2589168.0,0.0,0.0,121922581.0,46234818.0,64,0x7fadb7fe8ec0,4666,0,0,1676885,762,0,0,1327208,2888,0,0,1570595,5041,0,0,1612327,1073,0,0,1387401,411,0,0,1202161,4788,0,0,1723623,4423,0,0,1712699,602,0,0,1316480,919,0,0,1403132,2219,0,0,1433954,2152,0,0,1489074,727,0,0,1294459,969,0,0,1272769,3845,0,0,1640720,3191,0,0,1496110,1157,0,0,1349003,1063,0,0,1371231,970,0,0,1379136,2423,0,0,1422344,840,0,0,1347893,1261,0,0,1401466,3712,0,0,1595915,2809,0,0,1544899,3581,0,0,1602143,553,0,0,1284073,5456,0,0,1725495,5279,0,0,1688563,1083,0,0,1388976,883,0,0,1255958,1441,0,0,1416678,2621,0,0,1493040,64,0x7fba70fa4ec0,32768,0,0,0,16384,16384,393216,22993230,960.0,513966.0,0.0,524288.0,1146136.0,32768.0,0,0,0,13782,86415.0,86415.0,0.0,86415.0,64,0x7fa7b9df8ec0,2682277,360448,163840,0,0,180224,114688,0,66206398.0,186914417.0,76995031.0,131072.0,0.0,537664.0,0,0,27180,136397.0,0.0,0.0,136397.0,64,0x7fdc4c700ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131492.0,0.0,838.0,131491.0,64,0x7f8c7350cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60891.0,127061.0,64,0x7fb128c58ec0,350920,238194,3467875,16384,25350421,0,48,0,43864,43864,3862661.0,3185520.0,5713.0,1096832.0,2254399.0,0.0,3176335.0,2864207.0,350912,247991,43864,0,43864,0,1403648.0,830490.0,0.0,0.0,64,0x7f2373ab4ec0,0,0,48,0,65536,65536,0,0,31551,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42894,1676,0,48.0,464.0,0.0,262144.0,64,0x7f2f75968ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5182,43579,1088,131887.0,131072.0,0.0,86762.0,64,0x7f5d729c0ec0,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8195,4099,8195,0,8192,4096,8192,0,8240,4144,8240,0,8320,4224,8320,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fe378560ec0,191418,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11854,28238,8586,2408,0,41213,262469.0,0.0,47.0,262422.0,64,0x7f5d4acc8ec0,0,3909973,2664,2664,0,3450966,2676,2676,0,4155061,2684,2684,0,3997865,2717,2717,0,3111313,2662,2662,0,3650843,2688,2688,0,5079735,2726,2726,0,3241954,2724,2724,0,3113374,2696,2696,0,3033050,2652,2652,0,4410884,2724,2724,0,4377417,2732,2732,0,2787161,2688,2688,0,2717633,2680,2680,0,3979685,2706,2706,0,4603288,2702,2702,0,4279233,2686,2686,0,4104284,2678,2678,0,4170041,2700,2700,0,4556886,2714,2714,0,3136833,2686,2686,0,4088008,2721,2721,0,4118790,2708,2708,0,3315225,2700,2700,0,2418541,2666,2666,0,2918816,2667,2667,0,4901610,2748,2748,0,5149454,2716,2716,0,2792756,2672,2672,0,4348866,2683,2683,0,3640140,2732,2732,0,4984111,2712,2712,64,0x7f369015cec0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,0,44447,0,0,64,0x7f5ac6cd0ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f87f94a0ec0,0.0,64,0x7f006b4a4ec0,4096,0,1656,0,4225,0,222,0,4096,0,2498,0,4096,0,42,0,4096,0,4194,0,4096,0,5520,0,4096,0,1288,0,4096,0,434,0,4096,0,2477,0,4096,0,2170,0,4097,0,1729,0,4145,0,233,0,4096,0,3696,0,4146,0,290,0,4096,0,1916,0,4096,0,766,0,4096,0,4408,0,4096,0,7214,0,4096,0,1521,0,4096,0,545,0,4096,0,393,0,4096,0,503,0,4096,0,1963,0,4096,0,958,0,4216,0,5283,0,4097,0,1661,0,4096,0,1361,0,4096,0,0,0,4096,0,799,0,4096,0,1827,0,4096,0,259,0,4096,0,0,0,64,0x7f7ab6bd8ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86428.0,0.0,131112.0,0.0,1410154854934389,1410154854953269 diff --git a/tests/workloads/dispatch_0_1/MI100/sysinfo.csv b/tests/workloads/dispatch_0_1/MI100/sysinfo.csv index ab7cba6645..9523e9c63e 100644 --- a/tests/workloads/dispatch_0_1/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_0_1/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_0_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:05 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_0_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:53:28 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_0_1/MI100/timestamps.csv b/tests/workloads/dispatch_0_1/MI100/timestamps.csv index 91c069428a..c42388c111 100644 --- a/tests/workloads/dispatch_0_1/MI100/timestamps.csv +++ b/tests/workloads/dispatch_0_1/MI100/timestamps.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,159380,159380,1048576,256,0,0,8,8,16,64,0x0,0x7fd3f9e04e80,194232901406934,194232901432521,194232901456681,194232901471346 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,159380,159380,1048576,256,0,0,8,8,16,64,0x0,0x7fd3f9e04e80,194232901470003,194232901551561,194232901570601,194232901571726 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1255002,1255002,1048576,256,0,0,8,8,16,64,0x0,0x7f1e2ca68ec0,1410154854801159,1410154854825909,1410154854850869,1410154854861473 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1255002,1255002,1048576,256,0,0,8,8,16,64,0x0,0x7f1e2ca68ec0,1410154854863637,1410154854934389,1410154854953269,1410154854954889 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv index 936271e619..56df60a413 100644 --- a/tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311135,311135,1048576,256,0,0,8,0,16,64,0x0,0x7f20e5dd0ec0,27333,27333,16384,65536,13914,1566164,198596821057709,198609512940794,198609512961274,198596836842831 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311135,311135,1048576,256,0,0,8,0,16,64,0x0,0x7f20e5dd0ec0,41896,41896,16384,65536,9440,1048676,198596836864582,198609513046074,198609513062554,198596837190358 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4135708,4135708,1048576,256,0,0,8,0,16,64,0x0,0x7f60c4920ec0,27801,27801,16384,65536,13980,1568136,1412176982271587,1412189920581155,1412189920601635,1412176998152690 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4135708,4135708,1048576,256,0,0,8,0,16,64,0x0,0x7f60c4920ec0,42553,42553,16384,65536,9218,1048704,1412176998167588,1412189920620835,1412189920636515,1412176998470521 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv index 76a58ab2cb..68fd7a6df4 100644 --- a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311337,311337,1048576,256,0,0,8,0,16,64,0x0,0x7fef76aa8ec0,0,0,0,198597300509498,198609512940794,198609512961274,198597316434836 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311337,311337,1048576,256,0,0,8,0,16,64,0x0,0x7fef76aa8ec0,0,0,0,198597316453451,198609513046074,198609513062554,198597316756414 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4135910,4135910,1048576,256,0,0,8,0,16,64,0x0,0x7f540aed0ec0,0,0,0,1412177470467990,1412189920581155,1412189920601635,1412177486378819 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4135910,4135910,1048576,256,0,0,8,0,16,64,0x0,0x7f540aed0ec0,0,0,0,1412177486396252,1412189920620835,1412189920636515,1412177486675320 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv index 5478b8f1de..745e211222 100644 --- a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311539,311539,1048576,256,0,0,8,0,16,64,0x0,0x7f00c60b0ec0,65536,178908,19932664,198597783544016,198609512940794,198609512961274,198597799509239 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311539,311539,1048576,256,0,0,8,0,16,64,0x0,0x7f00c60b0ec0,65536,228948,25571704,198597799526401,198609513046074,198609513062554,198597799830967 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4136108,4136108,1048576,256,0,0,8,0,16,64,0x0,0x7f950a7d8ec0,65536,197906,22151624,1412177954983531,1412189920581155,1412189920601635,1412177971006002 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4136108,4136108,1048576,256,0,0,8,0,16,64,0x0,0x7f950a7d8ec0,65536,277686,31031360,1412177971031811,1412189920620835,1412189920636515,1412177971316119 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv index 982e8f2f52..8395efad23 100644 --- a/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311741,311741,1048576,256,0,0,8,0,16,64,0x0,0x7f8f6070cec0,32768,295724,33126508,198598264016216,198609512940794,198609512961274,198598279668286 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311741,311741,1048576,256,0,0,8,0,16,64,0x0,0x7f8f6070cec0,32768,579022,64857248,198598279691300,198609513046074,198609513062554,198598279967252 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4136306,4136306,1048576,256,0,0,8,0,16,64,0x0,0x7f2dc569cec0,32768,288723,32327348,1412178439025999,1412189920581155,1412189920601635,1412178454937981 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4136306,4136306,1048576,256,0,0,8,0,16,64,0x0,0x7f2dc569cec0,32768,583337,65324164,1412178454959211,1412189920620835,1412189920636515,1412178455321756 diff --git a/tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv index 8abec10d1c..1e268b5d5c 100644 --- a/tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,311942,311942,1048576,256,0,0,8,0,16,64,0x0,0x7fecfef2cec0,28002,28002,11107,224024,16384,11099231,131393,0,44906916,198598744115260,198609512940794,198609512961274,198598759705213 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,311942,311942,1048576,256,0,0,8,0,16,64,0x0,0x7fecfef2cec0,42307,42307,13512,338464,16384,20301423,231106,0,81693968,198598759736312,198609513046074,198609513062554,198598760106662 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4136505,4136505,1048576,256,0,0,8,0,16,64,0x0,0x7febaa5a0ec0,27465,27465,10867,219728,16384,10783574,127969,0,43629176,1412178931644254,1412189920581155,1412189920601635,1412178947860341 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4136505,4136505,1048576,256,0,0,8,0,16,64,0x0,0x7febaa5a0ec0,41440,41440,13373,331528,16384,19852449,226122,0,79898484,1412178947889406,1412189920620835,1412189920636515,1412178948181669 diff --git a/tests/workloads/dispatch_0_1/MI200/log.txt b/tests/workloads/dispatch_0_1/MI200/log.txt new file mode 100644 index 0000000000..81ef05a4ec --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/log.txt @@ -0,0 +1,764 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_0_1/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['0:2'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_162724' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162724_4135548' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162724_4135548/input0_results_240321_162724' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162724_4135548/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162724_4135548/input0_results_240321_162724 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_162725' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162725_4135750' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162725_4135750/input0_results_240321_162725' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162725_4135750/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162725_4135750/input0_results_240321_162725 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_162725' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162725_4135948' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162725_4135948/input0_results_240321_162725' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162725_4135948/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162725_4135948/input0_results_240321_162725 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_162726' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162726_4136146' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162726_4136146/input0_results_240321_162726' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162726_4136146/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162726_4136146/input0_results_240321_162726 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_162726' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162726_4136345' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162726_4136345/input0_results_240321_162726' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162726_4136345/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162726_4136345/input0_results_240321_162726 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_162727' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162727_4136531' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162727_4136531/input0_results_240321_162727' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162727_4136531/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162727_4136531/input0_results_240321_162727 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_162727' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162727_4136733' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162727_4136733/input0_results_240321_162727' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162727_4136733/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162727_4136733/input0_results_240321_162727 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_162728' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162728_4136935' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162728_4136935/input0_results_240321_162728' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162728_4136935/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162728_4136935/input0_results_240321_162728 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_162728' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162728_4137121' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162728_4137121/input0_results_240321_162728' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162728_4137121/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162728_4137121/input0_results_240321_162728 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_162729' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162729_4137311' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162729_4137311/input0_results_240321_162729' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162729_4137311/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162729_4137311/input0_results_240321_162729 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_162729' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162729_4137497' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162729_4137497/input0_results_240321_162729' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162729_4137497/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162729_4137497/input0_results_240321_162729 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_162730' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162730_4137689' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162730_4137689/input0_results_240321_162730' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162730_4137689/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162730_4137689/input0_results_240321_162730 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_162731' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162731_4137888' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162731_4137888/input0_results_240321_162731' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162731_4137888/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162731_4137888/input0_results_240321_162731 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_162731' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162731_4138074' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162731_4138074/input0_results_240321_162731' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162731_4138074/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162731_4138074/input0_results_240321_162731 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_162732' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162732_4138275' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162732_4138275/input0_results_240321_162732' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162732_4138275/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162732_4138275/input0_results_240321_162732 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_162733' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162733_4138477' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162733_4138477/input0_results_240321_162733' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162733_4138477/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162733_4138477/input0_results_240321_162733 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_162733' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162733_4138664' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162733_4138664/input0_results_240321_162733' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162733_4138664/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162733_4138664/input0_results_240321_162733 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_162734' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162734_4138852' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162734_4138852/input0_results_240321_162734' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162734_4138852/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162734_4138852/input0_results_240321_162734 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_162734' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162734_4139036' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162734_4139036/input0_results_240321_162734' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162734_4139036/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162734_4139036/input0_results_240321_162734 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_162735' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162735_4139225' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162735_4139225/input0_results_240321_162735' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162735_4139225/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162735_4139225/input0_results_240321_162735 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_162735' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162735_4139427' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162735_4139427/input0_results_240321_162735' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162735_4139427/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162735_4139427/input0_results_240321_162735 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_162736' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162736_4139611' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162736_4139611/input0_results_240321_162736' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162736_4139611/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162736_4139611/input0_results_240321_162736 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_162736' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162736_4139800' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162736_4139800/input0_results_240321_162736' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162736_4139800/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162736_4139800/input0_results_240321_162736 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_162737' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162737_4140003' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162737_4140003/input0_results_240321_162737' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162737_4140003/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162737_4140003/input0_results_240321_162737 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_0_1/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_162737' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_0_1/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162737_4140203' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162737_4140203/input0_results_240321_162737' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162737_4140203/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 0:2 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 2 contexts collected, output directory /tmp/rpl_data_240321_162737_4140203/input0_results_240321_162737 + |-> [rocprof] File 'tests/workloads/dispatch_0_1/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/dispatch_0_1/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/dispatch_0_1/MI200/pmc_dispatch_info.csv b/tests/workloads/dispatch_0_1/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..930dfccaaa --- /dev/null +++ b/tests/workloads/dispatch_0_1/MI200/pmc_dispatch_info.csv @@ -0,0 +1,3 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/dispatch_0_1/MI200/pmc_perf.csv b/tests/workloads/dispatch_0_1/MI200/pmc_perf.csv index 7251d5c895..b323285c8f 100644 --- a/tests/workloads/dispatch_0_1/MI200/pmc_perf.csv +++ b/tests/workloads/dispatch_0_1/MI200/pmc_perf.csv @@ -1,3 +1,3 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_1,obj_1,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_2,obj_2,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_4,obj_4,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_11,obj_11,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_12,obj_12,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_13,obj_13,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_14,obj_14,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_15,obj_15,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_16,obj_16,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_17,obj_17,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_18,obj_18,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4a2fab8ec0,0,393216,163840,0,0,0,0,0,18187,0.0,0.0,0.0,32768.0,0.0,0.0,395.0,32768.0,4096,16384,352,28609,2100,0,56.0,8.0,0.0,204428.0,64,0x7f47e819cec0,114688,0,32768,32768,16384,16384,65536,49152,27519246.0,86577439.0,38720502.0,131072.0,0.0,233918.0,0,0,15372,569.0,131086.0,0.0,20.0,64,0x7f7e08b40ec0,1275,121672,0,0,65536,63800,56,1680,64,0x7fc86bf10ec0,0,0,0,224,0,65536,64213,56,64,0x7f0cb3310ec0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,0,27535,0,0,64,0x7f892acf0ec0,6414,0,4096,6385,0,4096,6373,0,4096,6358,0,4096,6385,0,4096,6411,0,4096,6361,0,4096,6376,0,4096,6378,0,4096,6417,0,4096,6382,0,4096,6375,0,4096,6356,0,4096,6390,0,4096,6413,0,4096,6357,0,4096,6349,0,4096,6381,0,4096,6399,0,4096,6394,0,4096,6388,0,4096,6409,0,4096,6399,0,4096,6535,0,4096,6365,0,4096,6354,0,4096,6381,0,4096,6401,0,4096,6395,0,4096,6392,0,4096,6406,0,4096,6403,0,4096,64,0x7f84b8ac4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13682,19128,8188,551,0,27229,204211.0,0.0,73130.0,131081.0,64,0x7f7f3b020ec0,0,0,0,1060632,13,0,0,1275584,0,0,0,999915,0,0,0,1129505,0,0,0,1096028,0,0,0,1055633,0,0,0,985615,0,0,0,1234953,0,0,0,1032049,0,0,0,1020348,0,0,0,1096685,0,0,0,1088182,0,0,0,1029177,0,0,0,1135761,0,0,0,1135865,0,0,0,1084249,73,0,0,1155288,0,0,0,977888,0,0,0,1141547,15,0,0,1316407,0,0,0,1050000,0,0,0,1195803,0,0,0,1036194,0,0,0,1066018,0,0,0,1046708,0,0,0,1012012,0,0,0,1007663,0,0,0,1164332,26,0,0,1180856,0,0,0,1034428,0,0,0,1023008,0,0,0,1251564,64,0x7f8fb71f8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,34785.0,46209.0,19327.0,64,0x7f2960af4ec0,217216,125479,16384,0,16384,16384,32768,49152,27151,27151,1909016.0,1326876.0,3429.0,167194.0,1033159.0,0.0,1319211.0,1021505.0,215505,133626,27151,0,27151,0,868832.0,480116.0,0.0,0.0,64,0x7f7aa37f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fdf23204ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4098,0,0,0,4097,0,0,0,4096,0,7,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f8f6cdf8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10836,0,819,28703,0,73230.0,131072.0,0.0,65568.0,64,0x7f724b4e8ec0,2253,4096,2253,6349,2274,4096,2274,6370,2315,4097,2316,6412,2279,4096,2279,6375,2244,4096,2244,6340,2300,4096,2300,6396,2258,4096,2258,6354,2285,4096,2285,6381,2286,4096,2286,6382,2253,4096,2253,6349,2271,4096,2271,6367,2261,4096,2261,6357,2281,4096,2281,6377,2246,4096,2246,6342,2300,4096,2300,6396,2262,4096,2262,6358,2263,4096,2263,6359,2288,4097,2289,6385,2283,4097,2284,6380,2277,4096,2277,6373,2303,4096,2303,6399,2239,4096,2239,6335,2290,4096,2290,6386,2469,4098,2471,6567,2297,4096,2297,6393,2265,4096,2265,6361,2287,4096,2287,6383,2287,4098,2289,6385,2283,4096,2283,6379,2305,4096,2305,6401,2245,4096,2245,6341,2290,4096,2290,6386,64,0x7fd8c4d90ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,980822.0,64,0x7f2bf9774ec0,32768,32768,0,64,0x7f18be1d8ec0,11168674,9922713,901897,344064,1680292,0,0,163840,832.0,515136.0,0.0,524288.0,286559.0,32768.0,529152,0,0,10665,131072.0,131072.0,0.0,131072.0,64,0x7efd92da0ec0,0,1112958,4096,4096,0,1464234,4096,4096,0,1294198,4096,4096,0,1321579,4096,4096,0,1193151,4096,4096,0,1435597,4096,4096,0,1087935,4096,4096,0,1413763,4096,4096,0,1090049,4096,4096,0,1189635,4096,4096,0,1151982,4096,4096,0,1187887,4096,4096,0,1147006,4096,4096,0,1183703,4096,4096,0,1322546,4096,4096,0,1114940,4096,4096,0,1336345,4096,4096,0,1001566,4096,4096,0,1160359,4096,4096,0,1503085,4096,4096,0,1283481,4096,4096,0,1245318,4096,4096,0,1255709,4096,4096,0,1139847,4096,4096,0,1292855,4096,4096,0,1204703,4096,4096,0,1037434,4096,4096,0,1174830,4096,4096,0,1143410,4096,4096,0,1185666,4096,4096,0,1136483,4096,4096,0,1513929,4096,4096,64,0x7f029f7e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39362136.0,34460235.0,0.0,198609512940794,198609512961274 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4a2fab8ec0,0,393216,163840,0,0,0,0,0,28273,0.0,0.0,0.0,32768.0,0.0,0.0,264.0,32768.0,4096,16384,302,37505,2061,0,56.0,0.0,0.0,200647.0,64,0x7f47e819cec0,114688,0,32768,32768,16384,16384,65536,49152,58351689.0,199740715.0,47356153.0,131072.0,0.0,608661.0,0,0,25624,25352.0,131085.0,0.0,24.0,64,0x7f7e08b40ec0,0,211412,0,0,65536,63800,56,1680,64,0x7fc86bf10ec0,0,0,0,56,0,65536,65536,0,64,0x7f0cb3310ec0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,0,41834,0,0,64,0x7f892acf0ec0,6290,0,4096,6278,0,4096,6285,0,4096,6258,0,4096,6260,0,4096,6250,0,4096,6296,0,4096,6269,0,4096,6274,0,4096,6289,0,4096,6279,0,4096,6286,0,4096,6262,0,4096,6263,0,4096,6252,0,4096,6299,0,4096,6278,0,4096,6277,0,4096,6276,0,4096,6286,0,4096,6254,0,4096,6236,0,4096,6275,0,4096,6274,0,4096,6274,0,4096,6281,0,4096,6275,0,4096,6278,0,4096,6284,0,4096,6252,0,4096,6246,0,4096,6272,0,4096,64,0x7f84b8ac4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,35266,28104,9579,2829,0,41038,200795.0,0.0,69712.0,131083.0,64,0x7f7f3b020ec0,138,0,0,1807628,0,0,0,1827498,165,0,0,2227358,181,0,0,2120664,0,0,0,1497979,912,0,0,2223527,0,0,0,1933367,176,0,0,2159154,0,0,0,1909110,236,0,0,1643335,0,0,0,1638015,501,0,0,1947456,325,0,0,1837027,0,0,0,1461520,32,0,0,1944737,0,0,0,1874947,0,0,0,1657958,22,0,0,2204591,0,0,0,1540041,399,0,0,1860741,146,0,0,1686425,143,0,0,2245703,0,0,0,1437395,0,0,0,1645404,0,0,0,1619523,0,0,0,1641243,521,0,0,2152628,0,0,0,1950767,64,0,0,1549545,150,0,0,1695926,202,0,0,1685968,0,0,0,1777436,64,0x7f8fb71f8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,92912.0,45614.0,0.0,64,0x7f2960af4ec0,331880,223650,16384,0,16384,16384,32768,49152,41484,41484,3184756.0,2511449.0,4735.0,382351.0,1781220.0,0.0,2499517.0,2190353.0,331872,232947,41484,0,41484,0,1327488.0,796855.0,0.0,0.0,64,0x7f7aa37f8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fdf23204ec0,4096,0,468,0,4096,0,607,0,4096,0,1338,0,4096,0,532,0,4096,0,17,0,4096,0,111,0,4097,0,422,0,4096,0,1350,0,4096,0,1020,0,4096,0,226,0,4096,0,492,0,4097,0,1202,0,4096,0,997,0,4096,0,454,0,4098,0,1599,0,4097,0,1215,0,4096,0,227,0,4096,0,536,0,4097,0,244,0,4096,0,629,0,4096,0,305,0,4096,0,667,0,4096,0,315,0,4096,0,1196,0,4096,0,219,0,4096,0,956,0,4096,0,223,0,4097,0,141,0,4096,0,318,0,4098,0,133,0,4096,0,43,0,4096,0,10,0,64,0x7f8f6cdf8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,15530,0,819,36227,0,69653.0,131072.0,0.0,45684.0,64,0x7f724b4e8ec0,2158,4097,2159,6255,2151,4096,2151,6247,2265,4097,2266,6362,2175,4096,2175,6271,2158,4096,2158,6254,2161,4097,2162,6258,2165,4096,2165,6261,2152,4096,2152,6248,2154,4096,2154,6250,2160,4097,2161,6257,2154,4096,2154,6250,2210,4096,2210,6306,2177,4096,2177,6273,2158,4096,2158,6254,2159,4096,2159,6255,2169,4096,2169,6265,2170,4096,2170,6266,2137,4097,2138,6234,2153,4098,2155,6251,2151,4096,2151,6247,2158,4096,2158,6254,2203,4096,2203,6299,2164,4096,2164,6260,2164,4096,2164,6260,2170,4096,2170,6266,2171,4096,2171,6267,2137,4096,2137,6233,2152,4098,2154,6250,2151,4096,2151,6247,2158,4096,2158,6254,2205,4096,2205,6301,2169,4096,2169,6265,64,0x7fd8c4d90ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2006123.0,64,0x7f2bf9774ec0,32768,32768,0,64,0x7f18be1d8ec0,19514784,18251139,919581,344064,2815906,0,0,163840,832.0,515136.0,0.0,524288.0,603815.0,32768.0,1013862,0,0,13766,91363.0,91363.0,0.0,91363.0,64,0x7efd92da0ec0,0,3426461,2852,2852,0,5196063,2894,2894,0,2808279,2860,2860,0,4040483,2856,2856,0,3772796,2870,2870,0,4040365,2838,2838,0,2840661,2842,2842,0,4380697,2792,2792,0,3625585,2792,2792,0,3694624,2852,2852,0,3192613,2896,2896,0,3174666,2860,2860,0,3270470,2858,2858,0,3538463,2876,2876,0,4660296,2836,2836,0,3792854,2840,2840,0,3855704,2816,2816,0,3029733,2820,2820,0,3888200,2864,2864,0,3951296,2860,2860,0,3411540,2844,2844,0,3724081,2872,2872,0,3666285,2832,2832,0,5354856,2828,2828,0,4530089,2828,2828,0,3023717,2816,2816,0,4697570,2814,2814,0,3849095,2864,2864,0,3167936,2860,2860,0,2773351,2844,2844,0,3706712,2876,2876,0,4062111,2830,2830,64,0x7f029f7e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120455321.0,60544388.0,0.0,198609513046074,198609513062554 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_1,obj_1,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_2,obj_2,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_3,obj_3,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_6,obj_6,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_7,obj_7,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_10,obj_10,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_11,obj_11,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_12,obj_12,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_13,obj_13,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_14,obj_14,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_15,obj_15,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_16,obj_16,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_17,obj_17,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_18,obj_18,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f1570dbcec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,34758.0,45976.0,19560.0,64,0x7fdc1db54ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13444,19343,8358,545,0,27202,204502.0,0.0,73417.0,131085.0,64,0x7f931b1e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39359692.0,35836456.0,0.0,64,0x7f523a854ec0,0,393216,163840,0,0,0,0,0,18303,0.0,0.0,0.0,32768.0,0.0,0.0,393.0,32768.0,4096,16384,352,28428,1946,0,56.0,7.0,0.0,204031.0,64,0x7f3a11414ec0,0,1448230,4096,4096,0,1320647,4096,4096,0,1327106,4096,4096,0,1165103,4096,4096,0,1440333,4096,4096,0,1509519,4096,4096,0,1259467,4096,4096,0,1260905,4096,4096,0,1053199,4096,4096,0,1052202,4096,4096,0,1161616,4096,4096,0,1177706,4096,4096,0,1232425,4096,4096,0,1577487,4096,4096,0,1310715,4096,4096,0,1276195,4096,4096,0,944910,4096,4096,0,1170562,4096,4096,0,1325109,4096,4096,0,1476059,4096,4096,0,1220805,4096,4096,0,1491154,4100,4100,0,1255702,4096,4096,0,1301539,4096,4096,0,1343866,4096,4096,0,1120128,4096,4096,0,1061607,4096,4096,0,1371499,4096,4096,0,1128497,4096,4096,0,1092113,4096,4096,0,1117188,4096,4096,0,1555474,4096,4096,64,0x7f89343bcec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,11,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,3,0,4097,0,0,0,4096,0,0,0,4096,0,49,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f083fe4cec0,11146317,9870223,932030,344064,1655709,0,0,163840,832.0,515149.0,0.0,524288.0,262474.0,32768.0,528709,0,0,11222,131072.0,131072.0,0.0,131072.0,64,0x7f8503d18ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f53cdd50ec0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,0,27842,0,0,64,0x7f3893ad8ec0,2266,4096,2266,6362,2304,4096,2304,6400,2299,4096,2299,6395,2362,4096,2362,6458,2242,4096,2242,6338,2291,4096,2291,6387,2304,4096,2304,6400,2335,4096,2335,6431,2334,4096,2334,6430,2272,4101,2277,6373,2307,4096,2307,6403,2352,4097,2353,6449,2368,4096,2368,6464,2246,4096,2246,6342,2291,4096,2291,6387,2304,4096,2304,6400,2286,4096,2286,6382,2311,4096,2311,6407,2269,4096,2269,6365,2265,4096,2265,6361,2333,4096,2333,6429,2332,4096,2332,6428,2303,4097,2304,6400,2436,4098,2438,6534,2273,4096,2273,6369,2287,4096,2287,6383,2310,4096,2310,6406,2271,4096,2271,6367,2266,4096,2266,6362,2333,4096,2333,6429,2332,4096,2332,6428,2308,4096,2308,6404,64,0x7fdebc5a8ec0,114688,0,32768,32768,16384,16384,65536,49152,28552738.0,87675491.0,39015420.0,131072.0,0.0,238435.0,0,0,15129,1192.0,131081.0,0.0,10.0,64,0x7f4e1b248ec0,0,0,0,224,0,65536,64189,56,64,0x7f7afa4d8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10997,0,818,28056,0,73000.0,131072.0,0.0,65568.0,64,0x7f3778dc4ec0,1868,125231,0,0,65536,63800,56,1680,64,0x7f1a1ee60ec0,0,0,0,979631,0,0,0,1041459,0,0,0,1072208,0,0,0,1214414,0,0,0,1051269,0,0,0,1051062,0,0,0,1161186,66,0,0,1207646,0,0,0,1039979,0,0,0,1013941,0,0,0,1090982,0,0,0,1166864,0,0,0,1067625,0,0,0,1044526,0,0,0,1108504,0,0,0,1055894,1,0,0,1108064,6,0,0,1210489,0,0,0,1043190,99,0,0,1213111,0,0,0,1035661,1,0,0,1173468,98,0,0,1162371,5,0,0,1172342,0,0,0,1076940,0,0,0,1088200,60,0,0,1087921,0,0,0,1094389,0,0,0,1173325,0,0,0,1080090,26,0,0,1082717,0,0,0,1099673,64,0x7fcd5a20cec0,32768,32768,0,64,0x7fdf9e470ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,941639.0,64,0x7fdaa7c38ec0,233720,132943,16384,0,16384,16384,32768,49152,29214,29214,2005996.0,1421899.0,3264.0,172595.0,1130919.0,0.0,1413687.0,1115350.0,232009,141066,29214,0,29214,0,934848.0,504393.0,0.0,0.0,64,0x7fd12b1d8ec0,6363,0,4096,6388,0,4096,6368,0,4096,6401,0,4096,6380,0,4096,6341,0,4096,6380,0,4096,6412,0,4096,6414,0,4096,6360,0,4096,6392,0,4096,6372,0,4096,6399,0,4096,6384,0,4096,6344,0,4096,6380,0,4096,6403,0,4096,6407,0,4096,6404,0,4096,6372,0,4096,6424,0,4096,6420,0,4096,6391,0,4096,6536,0,4096,6372,0,4096,6402,0,4096,6410,0,4096,6405,0,4096,6370,0,4096,6423,0,4096,6421,0,4096,6389,0,4096,1412189920581155,1412189920601635 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f1570dbcec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,85469.0,45456.0,0.0,64,0x7fdc1db54ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31463,27230,9551,2937,0,40426,201004.0,0.0,69917.0,131087.0,64,0x7f931b1e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118801110.0,60068928.0,0.0,64,0x7f523a854ec0,0,393216,163840,0,0,0,0,0,29385,0.0,0.0,0.0,32768.0,0.0,0.0,201.0,32768.0,4096,16384,302,40302,1926,0,56.0,9.0,0.0,200114.0,64,0x7f3a11414ec0,0,3348130,2792,2792,0,3355576,2824,2824,0,4317597,2856,2856,0,4749387,2858,2858,0,2880492,2862,2862,0,3449303,2832,2832,0,3174316,2898,2898,0,3955879,2852,2852,0,3718192,2850,2850,0,2395543,2792,2792,0,3667661,2824,2824,0,5138963,2852,2852,0,2728816,2860,2860,0,3526690,2864,2864,0,3122284,2820,2820,0,4212447,2894,2894,0,4463237,2822,2822,0,4839005,2872,2872,0,2549905,2800,2800,0,3116980,2828,2828,0,5417200,2844,2844,0,3485778,2912,2912,0,2657335,2788,2788,0,3663254,2814,2814,0,3251726,2816,2816,0,4846338,2828,2828,0,3545356,2864,2864,0,2515324,2800,2800,0,3631658,2832,2832,0,3050512,2848,2848,0,3303964,2914,2914,0,3064273,2790,2790,64,0x7f89343bcec0,4096,0,786,0,4096,0,682,0,4096,0,1280,0,4096,0,1703,0,4096,0,629,0,4098,0,894,0,4096,0,657,0,4096,0,892,0,4096,0,297,0,4096,0,437,0,4096,0,979,0,4096,0,756,0,4096,0,567,0,4096,0,128,0,4096,0,584,0,4096,0,517,0,4098,0,230,0,4097,0,487,0,4097,0,1897,0,4096,0,2454,0,4096,0,122,0,4098,0,777,0,4096,0,30,0,4096,0,1312,0,4096,0,83,0,4096,0,462,0,4096,0,1323,0,4096,0,1509,0,4096,0,703,0,4097,0,158,0,4096,0,628,0,4096,0,34,0,64,0x7f083fe4cec0,20369713,18691961,1333688,344064,2903082,0,0,163840,832.0,515154.0,0.0,524288.0,595025.0,32768.0,1070424,0,0,13891,91078.0,91078.0,0.0,91078.0,64,0x7f8503d18ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f53cdd50ec0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,0,42482,0,0,64,0x7f3893ad8ec0,2192,4096,2192,6288,2177,4096,2177,6273,2152,4096,2152,6248,2181,4096,2181,6277,2172,4096,2172,6268,2160,4096,2160,6256,2161,4096,2161,6257,2162,4096,2162,6258,2166,4096,2166,6262,2193,4100,2197,6293,2180,4096,2180,6276,2217,4097,2218,6314,2183,4096,2183,6279,2176,4096,2176,6272,2160,4097,2161,6257,2159,4096,2159,6255,2160,4096,2160,6256,2150,4096,2150,6246,2160,4097,2161,6257,2177,4098,2179,6275,2147,4096,2147,6243,2209,4096,2209,6305,2182,4097,2183,6279,2188,4096,2188,6284,2190,4096,2190,6286,2163,4096,2163,6259,2146,4096,2146,6242,2159,4096,2159,6255,2175,4097,2176,6272,2150,4096,2150,6246,2212,4096,2212,6308,2179,4096,2179,6275,64,0x7fdebc5a8ec0,114688,0,32768,32768,16384,16384,65536,49152,57969890.0,201979280.0,47778440.0,131072.0,0.0,490026.0,0,0,23124,6341.0,131073.0,0.0,0.0,64,0x7f4e1b248ec0,0,0,0,56,0,65536,65536,0,64,0x7f7afa4d8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,19855,0,3132,38216,0,69358.0,131072.0,0.0,45639.0,64,0x7f3778dc4ec0,0,202773,0,0,65536,63800,56,1680,64,0x7f1a1ee60ec0,22,0,0,1535919,110,0,0,1884769,127,0,0,1735477,260,0,0,2110367,0,0,0,1751471,0,0,0,1672668,1293,0,0,2421099,143,0,0,2187979,0,0,0,1769919,0,0,0,1761306,248,0,0,1922908,0,0,0,1723399,15,0,0,1730083,0,0,0,1538376,1318,0,0,2263235,305,0,0,1964295,714,0,0,2210096,118,0,0,2298216,0,0,0,1508423,151,0,0,1776321,154,0,0,1994670,142,0,0,1865177,0,0,0,1878218,0,0,0,1723366,59,0,0,1897778,348,0,0,2164277,0,0,0,1641318,0,0,0,1689327,253,0,0,2237302,0,0,0,1429626,0,0,0,1664500,0,0,0,1779765,64,0x7fcd5a20cec0,32768,32768,0,64,0x7fdf9e470ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2074337.0,64,0x7fdaa7c38ec0,300360,205594,16384,0,16384,16384,32768,49152,37544,37544,2948437.0,2353334.0,4298.0,331931.0,1694164.0,0.0,2341567.0,2032467.0,300352,214577,37544,0,37544,0,1201408.0,775968.0,0.0,0.0,64,0x7fd12b1d8ec0,6253,0,4096,6260,0,4096,6275,0,4096,6268,0,4096,6283,0,4096,6263,0,4096,6286,0,4096,6282,0,4096,6287,0,4096,6249,0,4096,6258,0,4096,6282,0,4096,6271,0,4096,6283,0,4096,6259,0,4096,6290,0,4096,6302,0,4096,6263,0,4096,6252,0,4096,6270,0,4096,6263,0,4096,6283,0,4096,6289,0,4096,6262,0,4096,6258,0,4096,6304,0,4096,6264,0,4096,6257,0,4096,6273,0,4096,6267,0,4096,6288,0,4096,6295,0,4096,1412189920620835,1412189920636515 diff --git a/tests/workloads/dispatch_0_1/MI200/roofline.csv b/tests/workloads/dispatch_0_1/MI200/roofline.csv index 96bfb308a8..0377c64fed 100644 --- a/tests/workloads/dispatch_0_1/MI200/roofline.csv +++ b/tests/workloads/dispatch_0_1/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.0242,1388.5444,1389.5039,5014.0776,5010.7217,5017.4336,9224.2939,9223.6963,9224.8916,18054.982,18054.016,18055.949,20935.725,20875.342,20996.107,20261.689,20260.873,20262.506,170384.81,170381.8,170387.83,164856.69,164853.22,164860.16,41417.711,41417.168,41418.254,41477.18,41476.625,41477.734,166336.23,165848.91,166823.56 -1,1388.8065,1388.214,1389.399,5026.9512,5024.9131,5028.9893,9232.082,9231.4229,9232.7412,18087.27,18083.492,18091.047,20973.012,20906.764,21039.26,20291.207,20290.643,20291.771,170819.16,170814.88,170823.44,165083.95,165080.05,165087.86,41472.68,41471.848,41473.512,41536.34,41535.246,41537.434,166839.25,166835.88,166842.62 -2,1389.42,1388.8044,1390.0356,5035.7383,5033.4888,5037.9878,9261.5166,9260.8115,9262.2217,18109.811,18108.705,18110.916,21049.439,21049.039,21049.84,20352.191,20351.469,20352.914,171119.62,171114.88,171124.38,165490.05,165485.94,165494.16,41580.387,41579.566,41581.207,41639.574,41638.555,41640.594,166942.73,166357.73,167527.73 -3,1388.8628,1388.2523,1389.4733,5032.647,5031.3843,5033.9097,9240.2979,9239.7139,9240.8818,18025.895,18022.496,18029.293,21031.047,21030.645,21031.449,20311.537,20310.795,20312.279,171032.64,171028.23,171037.05,165246.34,165241.59,165251.09,41443.762,41292.008,41595.516,41583.09,41582.52,41583.66,167018.66,167016.94,167020.38 +0,1388.8433,1388.2601,1389.4264,5018.3813,5015.4775,5021.2852,9227.8584,9227.1865,9228.5303,17717.145,17714.176,17720.113,20947.432,20886.881,21007.982,20274.334,20273.65,20275.018,170521.16,170517.47,170524.84,164937.09,164932.44,164941.75,41442.25,41441.645,41442.855,41499.996,41499.133,41500.859,166424.47,165933.94,166915 +1,1389.0067,1388.4509,1389.5625,5028.1904,5026.1631,5030.2178,9237.1016,9236.377,9237.8262,18236.582,18235.619,18237.545,20985.395,20918.506,21052.283,20299.889,20299.375,20300.402,170925.2,170920.88,170929.53,165148.95,165144.98,165152.92,41497.691,41496.844,41498.539,41556.211,41555.07,41557.352,166931.45,166928.2,166934.7 +2,1388.4513,1387.8545,1389.0481,5036.9297,5034.5923,5039.2671,9261.1367,9260.4297,9261.8438,18218.844,18217.791,18219.896,21050.777,21050.377,21051.178,20350.275,20349.711,20350.84,171164.12,171159.02,171169.23,165523.23,165519.78,165526.69,41583.496,41582.508,41584.484,41637.641,41636.84,41638.441,166949.61,166347.86,167551.36 +3,1389.2191,1388.6479,1389.7903,5032.562,5030.8687,5034.2554,9238.0928,9237.4268,9238.7588,18328.943,18327.766,18330.121,21034.297,21033.963,21034.631,20307.766,20307.223,20308.309,171036.94,171032,171041.88,165166.28,165162.23,165170.33,41426.504,41272.871,41580.137,41568.695,41567.602,41569.789,166952.53,166948.02,166957.05 diff --git a/tests/workloads/dispatch_0_1/MI200/sysinfo.csv b/tests/workloads/dispatch_0_1/MI200/sysinfo.csv index 270672d1e6..722ff11d3b 100644 --- a/tests/workloads/dispatch_0_1/MI200/sysinfo.csv +++ b/tests/workloads/dispatch_0_1/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_0_1,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:21:03 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +dispatch_0_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:27:24 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_0_1/MI200/timestamps.csv b/tests/workloads/dispatch_0_1/MI200/timestamps.csv index bd1ea2b4cf..4495771255 100644 --- a/tests/workloads/dispatch_0_1/MI200/timestamps.csv +++ b/tests/workloads/dispatch_0_1/MI200/timestamps.csv @@ -1,3 +1,3 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,315904,315904,1048576,256,0,0,8,0,16,64,0x0,0x7fc0d1ec4ec0,198609512911564,198609512940794,198609512961274,198609512972029 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,315904,315904,1048576,256,0,0,8,0,16,64,0x0,0x7fc0d1ec4ec0,198609512972319,198609513046074,198609513062554,198609513063973 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4140363,4140363,1048576,256,0,0,8,0,16,64,0x0,0x7f3c471c4ec0,1412189920555838,1412189920581155,1412189920601635,1412189920615290 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4140363,4140363,1048576,256,0,0,8,0,16,64,0x0,0x7f3c471c4ec0,1412189920612605,1412189920620835,1412189920636515,1412189920769341 diff --git a/tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv index c2258fd944..11dfc470bf 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,146368,146368,1048576,256,0,0,8,8,16,64,0x0,0x7f9f83152e80,38682,38682,16384,65536,8172,1048640,194190802937007,194203146753468,194203146772188,194190810926274 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242050,1242050,1048576,256,0,0,8,8,16,64,0x0,0x7fc6f4208ec0,38821,38821,16384,65536,8109,1048656,1410114557095333,1410127432590948,1410127432609509,1410114564821895 diff --git a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv index 2c3b7f4e8b..5c339aa156 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,146556,146556,1048576,256,0,0,8,8,16,64,0x0,0x7f9214dece80,0,0,0,194191303483541,194203146753468,194203146772188,194191311114590 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242238,1242238,1048576,256,0,0,8,8,16,64,0x0,0x7fe8146b0ec0,0,0,0,1410115049761835,1410127432590948,1410127432609509,1410115057489720 diff --git a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv index 26562bef9d..d8a7f8f22d 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,146743,146743,1048576,256,0,0,8,8,16,64,0x0,0x7fdb01522e80,65536,83590,10693168,194191799460013,194203146753468,194203146772188,194191807333481 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242423,1242423,1048576,256,0,0,8,8,16,64,0x0,0x7f6929238ec0,65536,91980,11724504,1410115535741786,1410127432590948,1410127432609509,1410115543260466 diff --git a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv index ad075374a8..6d703351f8 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,146928,146928,1048576,256,0,0,8,8,16,64,0x0,0x7fe5463eae80,32768,663275,84884088,194192296631898,194203146753468,194203146772188,194192304449200 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242619,1242619,1048576,256,0,0,8,8,16,64,0x0,0x7fc33f83cec0,32768,653996,83707028,1410116022813727,1410127432590948,1410127432609509,1410116030517617 diff --git a/tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv index 0b70326ee0..d896dd77e7 100644 --- a/tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,147115,147115,1048576,256,0,0,8,8,16,64,0x0,0x7fd659050e80,38457,38457,11850,307664,16384,22285112,212347,0,89633484,194192793995967,194203146753468,194203146772188,194192801697780 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1242805,1242805,1048576,256,0,0,8,8,16,64,0x0,0x7fcc21518ec0,38554,38554,11832,308440,16384,22714635,211906,0,91397252,1410116516938870,1410127432590948,1410127432609509,1410116524589600 diff --git a/tests/workloads/dispatch_2/MI100/log.txt b/tests/workloads/dispatch_2/MI100/log.txt new file mode 100644 index 0000000000..202a91fe54 --- /dev/null +++ b/tests/workloads/dispatch_2/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_2/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['1'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155300' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155300_1241890' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155300_1241890/input0_results_240321_155300' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155300_1241890/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155300_1241890/input0_results_240321_155300 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155301' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155301_1242075' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155301_1242075/input0_results_240321_155301' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155301_1242075/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155301_1242075/input0_results_240321_155301 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155301' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155301_1242263' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155301_1242263/input0_results_240321_155301' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155301_1242263/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155301_1242263/input0_results_240321_155301 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155302' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155302_1242459' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155302_1242459/input0_results_240321_155302' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155302_1242459/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155302_1242459/input0_results_240321_155302 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155302' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155302_1242645' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155302_1242645/input0_results_240321_155302' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155302_1242645/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155302_1242645/input0_results_240321_155302 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155303' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155303_1242829' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155303_1242829/input0_results_240321_155303' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155303_1242829/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155303_1242829/input0_results_240321_155303 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155303' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155303_1243015' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155303_1243015/input0_results_240321_155303' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155303_1243015/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155303_1243015/input0_results_240321_155303 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155303' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155303_1243202' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155303_1243202/input0_results_240321_155303' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155303_1243202/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155303_1243202/input0_results_240321_155303 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155304' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155304_1243388' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155304_1243388/input0_results_240321_155304' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155304_1243388/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155304_1243388/input0_results_240321_155304 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155305_1243574' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155305_1243574/input0_results_240321_155305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155305_1243574/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155305_1243574/input0_results_240321_155305 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155305_1243760' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155305_1243760/input0_results_240321_155305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155305_1243760/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155305_1243760/input0_results_240321_155305 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155306' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155306_1243945' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155306_1243945/input0_results_240321_155306' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155306_1243945/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155306_1243945/input0_results_240321_155306 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155307' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155307_1244129' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155307_1244129/input0_results_240321_155307' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155307_1244129/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155307_1244129/input0_results_240321_155307 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155307' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155307_1244317' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155307_1244317/input0_results_240321_155307' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155307_1244317/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155307_1244317/input0_results_240321_155307 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155308' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155308_1244502' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155308_1244502/input0_results_240321_155308' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155308_1244502/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155308_1244502/input0_results_240321_155308 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155308' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155308_1244689' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155308_1244689/input0_results_240321_155308' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155308_1244689/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155308_1244689/input0_results_240321_155308 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155309' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155309_1244875' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155309_1244875/input0_results_240321_155309' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155309_1244875/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155309_1244875/input0_results_240321_155309 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155309' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155309_1245063' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155309_1245063/input0_results_240321_155309' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155309_1245063/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155309_1245063/input0_results_240321_155309 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155310' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155310_1245250' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155310_1245250/input0_results_240321_155310' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155310_1245250/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155310_1245250/input0_results_240321_155310 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155310' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155310_1245437' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155310_1245437/input0_results_240321_155310' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155310_1245437/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155310_1245437/input0_results_240321_155310 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155311' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155311_1245623' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155311_1245623/input0_results_240321_155311' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155311_1245623/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155311_1245623/input0_results_240321_155311 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155312' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155312_1245809' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155312_1245809/input0_results_240321_155312' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155312_1245809/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155312_1245809/input0_results_240321_155312 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155313' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155313_1245995' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155313_1245995/input0_results_240321_155313' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155313_1245995/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155313_1245995/input0_results_240321_155313 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/dispatch_2/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_2/MI100/pmc_dispatch_info.csv index 16e52923f6..9c396a1067 100644 --- a/tests/workloads/dispatch_2/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/dispatch_2/MI100/pmc_dispatch_info.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID -1,"vecCopy(double*, double*, double*, int, int) ",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/dispatch_2/MI100/pmc_perf.csv b/tests/workloads/dispatch_2/MI100/pmc_perf.csv index e3e986509f..5f3d29bea2 100644 --- a/tests/workloads/dispatch_2/MI100/pmc_perf.csv +++ b/tests/workloads/dispatch_2/MI100/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_2,obj_2,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_10,obj_10,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_11,obj_11,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_15,obj_15,TCC_EA_ATOMIC_LEVEL_sum,wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],Start_Timestamp,End_Timestamp -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f9d2e336e80,32768,0,0,0,16384,16384,393216,22258379,0.0,524288.0,0.0,524288.0,756880.0,32768.0,0,0,0,12033,86279.0,86279.0,0.0,86279.0,64,0x7f1253ca8e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f20f41ace80,267240,360448,163840,0,0,180224,114688,0,73309661.0,192651152.0,76300063.0,131072.0,0.0,600187.0,0,0,23809,55275.0,0.0,0.0,55275.0,64,0x7f50bc202e80,317960,216097,3133375,16384,22276538,0,48,0,39744,39744,3531086.0,2977320.0,6696.0,1072822.0,1885794.0,0.0,2967310.0,2654791.0,316247,224150,39744,0,39744,0,1271808.0,808935.0,0.0,0.0,64,0x7f8b06c84e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131073.0,0.0,0.0,131072.0,64,0x7f0c123c2e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38480,0,131126.0,131072.0,0.0,86403.0,64,0x7f256fbb6e80,131072.0,131072.0,0.0,2611512.0,0.0,0.0,131034005.0,46911848.0,64,0x7fb68d76ce80,0,0,48,0,65536,65536,0,0,29116,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,435,38798,1777,0,48.0,0.0,0.0,262144.0,64,0x7f55af786e80,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,0,39855,0,0,64,0x7fdc0dd62e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70561.0,138571.0,64,0x7f87fb1dce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f4849b32e80,4096,0,639,0,4096,0,1990,0,4096,0,4342,0,4096,0,1328,0,4096,0,674,0,4096,0,4650,0,4096,0,1637,0,4096,0,4116,0,4096,0,4828,0,4096,0,400,0,4096,0,650,0,4096,0,2785,0,4096,0,4298,0,4096,0,56,0,4096,0,1478,0,4096,0,127,0,4096,0,7689,0,4096,0,4903,0,4096,0,1327,0,4096,0,169,0,4096,0,163,0,4096,0,510,0,4096,0,1418,0,4096,0,0,0,4096,0,1185,0,4096,0,6101,0,4096,0,1122,0,4096,0,758,0,4097,0,716,0,4096,0,3010,0,4096,0,1700,0,4096,0,2383,0,64,0x7f4fa15a6e80,0,4894410,2726,2726,0,3735599,2716,2716,0,3847119,2690,2690,0,4285804,2710,2710,0,3743691,2698,2698,0,4600312,2716,2716,0,4220009,2703,2703,0,3217035,2692,2692,0,5324435,2714,2714,0,4578757,2684,2684,0,3933091,2704,2704,0,4572521,2712,2712,0,4129359,2728,2728,0,4140789,2690,2690,0,4354666,2692,2692,0,3454426,2682,2682,0,4292049,2700,2700,0,4759631,2700,2700,0,4778717,2680,2680,0,2982741,2692,2692,0,3944175,2715,2715,0,4022589,2729,2729,0,5063179,2689,2689,0,3075216,2664,2664,0,4223611,2712,2712,0,3661037,2672,2672,0,2900795,2730,2730,0,2757186,2688,2688,0,4017619,2724,2724,0,3787118,2701,2701,0,3161261,2718,2718,0,2854284,2660,2660,64,0x7f28be10ce80,116093,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12455,28839,7554,588,0,36789,262192.0,0.0,47.0,262145.0,64,0x7f2ca5c2ae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86438.0,0.0,131110.0,0.0,64,0x7f8b4e3aae80,0.0,64,0x7f9ba8d88e80,2018,0,0,1494090,2904,0,0,1590602,1370,0,0,1398780,1727,0,0,1448082,1082,0,0,1376646,3171,0,0,1646816,634,0,0,1309077,1517,0,0,1365906,1022,0,0,1270748,1614,0,0,1462726,2741,0,0,1528453,1935,0,0,1498464,2356,0,0,1539245,3489,0,0,1657733,2074,0,0,1507276,783,0,0,1292359,1769,0,0,1414879,805,0,0,1261008,2331,0,0,1535474,1930,0,0,1423285,674,0,0,1275431,2328,0,0,1465495,2186,0,0,1517192,6454,0,0,1801469,2928,0,0,1522074,1410,0,0,1385807,1189,0,0,1385724,1781,0,0,1513774,1289,0,0,1421567,6379,0,0,1868219,2519,0,0,1507660,1482,0,0,1408059,194203146753468,194203146772188 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_2,obj_2,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_4,obj_4,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_5,obj_5,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_6,obj_6,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_7,obj_7,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_8,obj_8,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_11,obj_11,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_12,obj_12,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_13,obj_13,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_16,obj_16,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,Start_Timestamp,End_Timestamp +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f4267d48ec0,0.0,64,0x7f154235cec0,252974,360448,163840,0,0,180224,114688,0,72098156.0,205624058.0,79937933.0,131072.0,0.0,579965.0,0,0,23936,51961.0,0.0,0.0,51961.0,64,0x7fea9f808ec0,113611,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12075,28459,7646,588,0,37215,262192.0,0.0,47.0,262145.0,64,0x7f57301b8ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,67195.0,135446.0,64,0x7f562a114ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86428.0,0.0,131110.0,0.0,64,0x7f6480768ec0,131072.0,131072.0,0.0,2639990.0,0.0,0.0,129626343.0,46793288.0,64,0x7f0d1d088ec0,32768,0,0,0,16384,16384,393216,21692773,0.0,524288.0,0.0,524288.0,745965.0,32768.0,0,0,0,11953,86327.0,86327.0,0.0,86327.0,64,0x7f709c740ec0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,0,38015,0,0,64,0x7f3dad7bcec0,0,0,48,0,65536,65536,0,0,28737,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,435,38380,1668,0,48.0,0.0,0.0,262144.0,64,0x7f51327c8ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,38252,0,131120.0,131072.0,0.0,86600.0,64,0x7f2dbf19cec0,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f32328d4ec0,1797,0,0,1419232,2725,0,0,1492039,3935,0,0,1698918,2133,0,0,1422824,2371,0,0,1516659,319,0,0,1269903,2901,0,0,1561232,613,0,0,1288778,3131,0,0,1613631,1082,0,0,1301401,1835,0,0,1454284,262,0,0,1150553,5583,0,0,1770491,3689,0,0,1619523,1559,0,0,1452131,1140,0,0,1298180,1803,0,0,1420660,1270,0,0,1380046,1325,0,0,1370964,3119,0,0,1588779,3256,0,0,1584324,1943,0,0,1458358,6823,0,0,1844206,3740,0,0,1643762,2742,0,0,1511587,638,0,0,1375747,5997,0,0,1767655,3482,0,0,1500656,6435,0,0,1824708,1905,0,0,1366283,3759,0,0,1678284,231,0,0,1086636,64,0x7f8e65960ec0,4096,0,1207,0,4096,0,346,0,4096,0,480,0,4096,0,993,0,4096,0,0,0,4096,0,2051,0,4096,0,0,0,4096,0,3524,0,4096,0,789,0,4096,0,2526,0,4096,0,4,0,4096,0,3453,0,4096,0,84,0,4096,0,2672,0,4096,0,1875,0,4096,0,39,0,4096,0,94,0,4096,0,8005,0,4096,0,582,0,4096,0,569,0,4096,0,313,0,4096,0,2218,0,4096,0,3213,0,4096,0,434,0,4096,0,3317,0,4096,0,5039,0,4096,0,3262,0,4097,0,673,0,4096,0,0,0,4096,0,1880,0,4096,0,0,0,4096,0,2494,0,64,0x7f72c1b44ec0,0,3201079,2700,2700,0,3371631,2678,2678,0,4928613,2684,2684,0,4270062,2702,2702,0,3939416,2684,2684,0,4497023,2704,2704,0,4015027,2730,2730,0,4928821,2696,2696,0,4131016,2692,2692,0,4591016,2678,2678,0,4711285,2722,2722,0,4914711,2738,2738,0,3425347,2692,2692,0,4898007,2668,2668,0,4910902,2696,2696,0,3536786,2704,2704,0,4246514,2692,2692,0,4570000,2680,2680,0,3563609,2716,2716,0,3558400,2708,2708,0,2726778,2699,2699,0,3473475,2740,2740,0,4627566,2690,2690,0,4380839,2680,2680,0,3783259,2666,2666,0,3729235,2694,2694,0,3732210,2748,2748,0,4496181,2706,2706,0,4362865,2707,2707,0,3315326,2676,2676,0,4634774,2726,2726,0,4549916,2700,2700,64,0x7f3f50d84ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f7969be4ec0,312840,216016,3150696,16384,22290131,0,48,0,39104,39104,3529616.0,3000337.0,7485.0,1427777.0,1942871.0,0.0,2991327.0,2681360.0,311127,224084,39104,0,39104,0,1251328.0,815148.0,0.0,0.0,64,0x7fc051320ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131073.0,0.0,0.0,131072.0,1410127432590948,1410127432609509 diff --git a/tests/workloads/dispatch_2/MI100/sysinfo.csv b/tests/workloads/dispatch_2/MI100/sysinfo.csv index 6f9566da38..6f43e7d3d9 100644 --- a/tests/workloads/dispatch_2/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_2/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:35 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:53:00 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_2/MI100/timestamps.csv b/tests/workloads/dispatch_2/MI100/timestamps.csv index 81c565256e..c647bb7f40 100644 --- a/tests/workloads/dispatch_2/MI100/timestamps.csv +++ b/tests/workloads/dispatch_2/MI100/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,150477,150477,1048576,256,0,0,8,8,16,64,0x0,0x7fb6015c6e80,194203146739938,194203146753468,194203146772188,194203146784432 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1246155,1246155,1048576,256,0,0,8,8,16,64,0x0,0x7fd9c2848ec0,1410127432560491,1410127432590948,1410127432609509,1410127432620744 diff --git a/tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv index bb544dd5e4..da077b405e 100644 --- a/tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301053,301053,1048576,256,0,0,8,0,16,64,0x0,0x7f90d6404ec0,22880,22880,16384,65536,9554,1048680,198381671765204,198394440082212,198394440098052,198381687536921 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4124736,4124736,1048576,256,0,0,8,0,16,64,0x0,0x7f7cc2578ec0,22637,22637,16384,65536,9404,1048700,1411868153949415,1411881076677985,1411881076693505,1411868170088366 diff --git a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv index e1aaf98f5f..810af59096 100644 --- a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301243,301243,1048576,256,0,0,8,0,16,64,0x0,0x7f58b1578ec0,0,0,0,198382158268734,198394440082212,198394440098052,198382174223788 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4124923,4124923,1048576,256,0,0,8,0,16,64,0x0,0x7f10f6d40ec0,0,0,0,1411868641572741,1411881076677985,1411881076693505,1411868657447011 diff --git a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv index d94c75d3ae..404bc00596 100644 --- a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301429,301429,1048576,256,0,0,8,0,16,64,0x0,0x7f7811c08ec0,65536,72322,8038296,198382637273097,198394440082212,198394440098052,198382653420274 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4125108,4125108,1048576,256,0,0,8,0,16,64,0x0,0x7fe12a7b0ec0,65536,76600,8662264,1411869123353968,1411881076677985,1411881076693505,1411869139369646 diff --git a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv index fe95af784a..e637609736 100644 --- a/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301631,301631,1048576,256,0,0,8,0,16,64,0x0,0x7f936d250ec0,32768,283635,31759140,198383117083666,198394440082212,198394440098052,198383132862947 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4125292,4125292,1048576,256,0,0,8,0,16,64,0x0,0x7f4afb100ec0,32768,274852,30773868,1411869608729593,1411881076677985,1411881076693505,1411869624857423 diff --git a/tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv index a800b25c24..0bbda4b07a 100644 --- a/tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,301833,301833,1048576,256,0,0,8,0,16,64,0x0,0x7fceeebd8ec0,22549,22549,8397,180400,16384,8919528,109698,0,36178612,198383600367705,198394440082212,198394440098052,198383616480267 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4125494,4125494,1048576,256,0,0,8,0,16,64,0x0,0x7fb3c4250ec0,23066,23066,8572,184536,16384,9116494,112642,0,36968384,1411870091555386,1411881076677985,1411881076693505,1411870107458090 diff --git a/tests/workloads/dispatch_2/MI200/log.txt b/tests/workloads/dispatch_2/MI200/log.txt new file mode 100644 index 0000000000..7015b6008e --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/log.txt @@ -0,0 +1,764 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_2/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['1'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_162215' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162215_4124576' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162215_4124576/input0_results_240321_162215' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162215_4124576/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162215_4124576/input0_results_240321_162215 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_162216' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162216_4124763' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162216_4124763/input0_results_240321_162216' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162216_4124763/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162216_4124763/input0_results_240321_162216 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_162216' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162216_4124948' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162216_4124948/input0_results_240321_162216' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162216_4124948/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162216_4124948/input0_results_240321_162216 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_162217' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162217_4125132' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162217_4125132/input0_results_240321_162217' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162217_4125132/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162217_4125132/input0_results_240321_162217 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_162217' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162217_4125334' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162217_4125334/input0_results_240321_162217' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162217_4125334/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162217_4125334/input0_results_240321_162217 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_162218' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162218_4125536' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162218_4125536/input0_results_240321_162218' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162218_4125536/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162218_4125536/input0_results_240321_162218 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_162218' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162218_4125738' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162218_4125738/input0_results_240321_162218' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162218_4125738/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162218_4125738/input0_results_240321_162218 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_162219' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162219_4125942' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162219_4125942/input0_results_240321_162219' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162219_4125942/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162219_4125942/input0_results_240321_162219 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_162219' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162219_4126127' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162219_4126127/input0_results_240321_162219' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162219_4126127/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162219_4126127/input0_results_240321_162219 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_162220' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162220_4126312' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162220_4126312/input0_results_240321_162220' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162220_4126312/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162220_4126312/input0_results_240321_162220 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_162220' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162220_4126497' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162220_4126497/input0_results_240321_162220' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162220_4126497/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162220_4126497/input0_results_240321_162220 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_162221' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162221_4126699' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162221_4126699/input0_results_240321_162221' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162221_4126699/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162221_4126699/input0_results_240321_162221 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_162222' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162222_4126886' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162222_4126886/input0_results_240321_162222' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162222_4126886/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162222_4126886/input0_results_240321_162222 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_162222' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162222_4127088' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162222_4127088/input0_results_240321_162222' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162222_4127088/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162222_4127088/input0_results_240321_162222 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_162223' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162223_4127273' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162223_4127273/input0_results_240321_162223' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162223_4127273/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162223_4127273/input0_results_240321_162223 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_162224' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162224_4127460' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162224_4127460/input0_results_240321_162224' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162224_4127460/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162224_4127460/input0_results_240321_162224 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_162224' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162224_4127646' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162224_4127646/input0_results_240321_162224' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162224_4127646/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162224_4127646/input0_results_240321_162224 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_162225' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162225_4127830' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162225_4127830/input0_results_240321_162225' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162225_4127830/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162225_4127830/input0_results_240321_162225 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_162225' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162225_4128014' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162225_4128014/input0_results_240321_162225' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162225_4128014/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162225_4128014/input0_results_240321_162225 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_162226' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162226_4128201' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162226_4128201/input0_results_240321_162226' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162226_4128201/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162226_4128201/input0_results_240321_162226 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_162226' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162226_4128388' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162226_4128388/input0_results_240321_162226' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162226_4128388/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162226_4128388/input0_results_240321_162226 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_162227' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162227_4128575' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162227_4128575/input0_results_240321_162227' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162227_4128575/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162227_4128575/input0_results_240321_162227 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_162227' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162227_4128777' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162227_4128777/input0_results_240321_162227' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162227_4128777/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162227_4128777/input0_results_240321_162227 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_162228' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162228_4128961' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162228_4128961/input0_results_240321_162228' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162228_4128961/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162228_4128961/input0_results_240321_162228 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_2/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_162228' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_2/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162228_4129150' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162228_4129150/input0_results_240321_162228' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162228_4129150/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 1 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_162228_4129150/input0_results_240321_162228 + |-> [rocprof] File 'tests/workloads/dispatch_2/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/dispatch_2/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/dispatch_2/MI200/pmc_dispatch_info.csv b/tests/workloads/dispatch_2/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..9c396a1067 --- /dev/null +++ b/tests/workloads/dispatch_2/MI200/pmc_dispatch_info.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/dispatch_2/MI200/pmc_perf.csv b/tests/workloads/dispatch_2/MI200/pmc_perf.csv index 00119c51e0..0e7cce5979 100644 --- a/tests/workloads/dispatch_2/MI200/pmc_perf.csv +++ b/tests/workloads/dispatch_2/MI200/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_3,obj_3,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_4,obj_4,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_5,obj_5,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_8,obj_8,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_9,obj_9,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_10,obj_10,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_11,obj_11,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_12,obj_12,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_13,obj_13,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_14,obj_14,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_15,obj_15,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_16,obj_16,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_17,obj_17,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_18,obj_18,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],Start_Timestamp,End_Timestamp -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fafae7e8ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,8528,18678,6328,550,0,21756,203809.0,0.0,72736.0,131073.0,64,0x7fc2dd45cec0,8860939,8418214,98661,344064,1390094,0,0,163840,0.0,524288.0,0.0,524288.0,127328.0,32768.0,280006,0,0,8319,92408.0,92408.0,0.0,92408.0,64,0x7f67fb880ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f1be8a7cec0,6379,0,4096,6404,0,4096,6329,0,4096,6380,0,4096,6351,0,4096,6387,0,4096,6388,0,4096,6387,0,4096,6385,0,4096,6379,0,4096,6403,0,4096,6333,0,4096,6375,0,4096,6357,0,4096,6385,0,4096,6394,0,4096,6376,0,4096,6415,0,4096,6372,0,4096,6405,0,4096,6373,0,4096,6349,0,4096,6383,0,4096,6348,0,4096,6349,0,4096,6374,0,4096,6419,0,4096,6372,0,4096,6413,0,4096,6374,0,4096,6350,0,4096,6384,0,4096,64,0x7fe215058ec0,0,0,0,56,0,65536,65536,0,64,0x7f923af74ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,5843,0,819,21683,0,73269.0,131072.0,0.0,46242.0,64,0x7faee6264ec0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,0,22576,0,0,64,0x7f3373cf8ec0,0,1070406,2872,2872,0,1355038,2900,2900,0,1235692,2896,2896,0,1330554,2896,2896,0,1272053,2924,2924,0,1225242,2880,2880,0,1069199,2924,2924,0,1249540,2864,2864,0,1242958,2864,2864,0,1136055,2868,2868,0,1216196,2896,2896,0,1199400,2900,2900,0,1292735,2892,2892,0,1197751,2924,2924,0,1165077,2872,2872,0,1569724,2920,2920,0,1384478,2848,2848,0,1249928,2924,2924,0,1204513,2852,2852,0,1309165,2912,2912,0,1392058,2880,2880,0,1301210,2888,2888,0,1198037,2848,2848,0,1499610,2872,2872,0,1150983,2866,2866,0,1135638,2852,2852,0,1617036,2924,2924,0,1195090,2856,2856,0,1532729,2912,2912,0,1230167,2880,2880,0,1248819,2888,2888,0,1320949,2852,2852,64,0x7f53820d4ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,31,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7fe652204ec0,0,393216,163840,0,0,0,0,0,15953,0.0,0.0,0.0,32768.0,0.0,0.0,428.0,32768.0,4096,16384,302,22694,1286,0,56.0,0.0,0.0,203649.0,64,0x7f0eb4224ec0,0,0,0,932520,0,0,0,942446,0,0,0,883403,0,0,0,995686,0,0,0,999233,0,0,0,942774,0,0,0,882049,11,0,0,1077842,0,0,0,925990,0,0,0,869985,0,0,0,892724,0,0,0,934501,0,0,0,900272,8,0,0,1045353,0,0,0,1001744,0,0,0,989843,0,0,0,872030,0,0,0,1034514,0,0,0,892212,27,0,0,1133017,0,0,0,987952,0,0,0,1014360,0,0,0,943067,0,0,0,1014494,0,0,0,1022817,17,0,0,1032236,0,0,0,941043,0,0,0,949838,2,0,0,1099293,0,0,0,994135,0,0,0,1059857,0,0,0,943916,64,0x7fb3602b8ec0,32768,32768,0,64,0x7fc2ea4d4ec0,180672,110253,16384,0,16384,16384,32768,49152,22583,22583,1711520.0,1291155.0,3385.0,163871.0,955325.0,0.0,1282971.0,984804.0,178961,118388,22583,0,22583,0,722656.0,410389.0,0.0,0.0,64,0x7f6f850e8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,34755.0,46215.0,0.0,64,0x7fcaea368ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,962608.0,64,0x7f33ba568ec0,0,55434,0,0,65536,63800,56,1680,64,0x7f084a7e8ec0,114688,0,32768,32768,16384,16384,65536,49152,27016783.0,85693015.0,39940578.0,131072.0,0.0,179709.0,0,0,12685,601.0,131073.0,0.0,0.0,64,0x7fc70d444ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40346123.0,32083541.0,0.0,64,0x7ffa6c820ec0,2266,4096,2266,6362,2245,4096,2245,6341,2312,4096,2312,6408,2319,4096,2319,6415,2246,4096,2246,6342,2225,4096,2225,6321,2300,4096,2300,6396,2329,4096,2329,6425,2333,4096,2333,6429,2267,4096,2267,6363,2250,4096,2250,6346,2304,4096,2304,6400,2325,4096,2325,6421,2248,4096,2248,6344,2228,4096,2228,6324,2301,4096,2301,6397,2276,4096,2276,6372,2272,4096,2272,6368,2262,4096,2262,6358,2273,4096,2273,6369,2389,4097,2390,6486,2271,4096,2271,6367,2232,4096,2232,6328,2223,4096,2223,6319,2222,4096,2222,6318,2275,4096,2275,6371,2272,4096,2272,6368,2261,4096,2261,6357,2278,4096,2278,6374,2337,4096,2337,6433,2275,4096,2275,6371,2235,4096,2235,6331,198394440082212,198394440098052 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_1,obj_1,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_2,obj_2,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_3,obj_3,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_4,obj_4,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_6,obj_6,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_7,obj_7,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_8,obj_8,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_9,obj_9,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_10,obj_10,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_11,obj_11,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_12,obj_12,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_15,obj_15,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_16,obj_16,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_17,obj_17,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_18,obj_18,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,Start_Timestamp,End_Timestamp +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7efebafd8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,944915.0,64,0x7f86708c0ec0,6417,0,4096,6372,0,4096,6402,0,4096,6332,0,4096,6331,0,4096,6369,0,4096,6365,0,4096,6351,0,4096,6351,0,4096,6427,0,4096,6372,0,4096,6406,0,4096,6330,0,4096,6336,0,4096,6370,0,4096,6369,0,4096,6337,0,4096,6384,0,4096,6369,0,4096,6424,0,4096,6369,0,4096,6305,0,4096,6395,0,4096,6367,0,4096,6369,0,4096,6340,0,4096,6388,0,4096,6368,0,4096,6427,0,4096,6372,0,4096,6308,0,4096,6390,0,4096,64,0x7fe567da0ec0,0,1305247,2868,2868,0,1316087,2910,2910,0,1133763,2892,2892,0,1323392,2912,2912,0,1461555,2906,2906,0,1272160,2872,2872,0,1056585,2916,2916,0,1555222,2868,2868,0,1153443,2868,2868,0,1422061,2864,2864,0,1231897,2908,2908,0,1138501,2890,2890,0,1114596,2908,2908,0,1226306,2908,2908,0,1140703,2872,2872,0,1342372,2920,2920,0,1284726,2852,2852,0,1392265,2920,2920,0,1252372,2880,2880,0,1342354,2896,2896,0,1190961,2870,2870,0,1449392,2914,2914,0,1307186,2844,2844,0,1518720,2852,2852,0,1348712,2856,2856,0,1040913,2848,2848,0,1243213,2916,2916,0,1159537,2880,2880,0,1230968,2896,2896,0,1371349,2880,2880,0,1423808,2920,2920,0,1495034,2840,2840,64,0x7f2ce4f00ec0,32768,32768,0,64,0x7fe4e160cec0,9088013,8653211,90738,344064,1406067,0,0,163840,0.0,524288.0,0.0,524288.0,140097.0,32768.0,294858,0,0,8599,92416.0,92416.0,0.0,92416.0,64,0x7ffa20e9cec0,4096,0,0,0,4096,0,160,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,78,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,150,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f86394a0ec0,2237,4096,2237,6333,2275,4096,2275,6371,2295,4096,2295,6391,2239,4096,2239,6335,2291,4096,2291,6387,2276,4096,2276,6372,2259,4096,2259,6355,2330,4097,2331,6427,2275,4096,2275,6371,2239,4096,2239,6335,2274,4096,2274,6370,2297,4096,2297,6393,2241,4096,2241,6337,2300,4096,2300,6396,2280,4096,2280,6376,2264,4096,2264,6360,2255,4096,2255,6351,2306,4096,2306,6402,2284,4096,2284,6380,2269,4096,2269,6365,2258,4096,2258,6354,2265,4096,2265,6361,2262,4096,2262,6358,2273,4096,2273,6369,2280,4096,2280,6376,2263,4096,2263,6359,2314,4096,2314,6410,2288,4096,2288,6384,2267,4096,2267,6363,2262,4096,2262,6358,2270,4096,2270,6366,2266,4096,2266,6362,64,0x7ff497fd8ec0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,0,23074,0,0,64,0x7f2ae3050ec0,0,55061,0,0,65536,63800,56,1680,64,0x7fc301e34ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,8723,18868,6095,550,0,21691,203933.0,0.0,72860.0,131073.0,64,0x7fd32d1a8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,5658,0,819,21850,0,72400.0,131072.0,0.0,46189.0,64,0x7f22ef11cec0,0,0,0,56,0,65536,65536,0,64,0x7fd570960ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,33737.0,46169.0,0.0,64,0x7f5b2be70ec0,185112,115114,16384,0,16384,16384,32768,49152,23138,23138,1774154.0,1347653.0,3839.0,160727.0,976298.0,0.0,1337788.0,1037493.0,183401,123252,23138,0,23138,0,740416.0,429359.0,0.0,0.0,64,0x7f198440cec0,0,0,0,882500,0,0,0,1003829,0,0,0,918569,115,0,0,1073401,0,0,0,939301,0,0,0,994659,0,0,0,951062,0,0,0,1111406,0,0,0,933245,0,0,0,866873,0,0,0,882619,0,0,0,1021542,0,0,0,980082,0,0,0,1021758,0,0,0,1024193,0,0,0,1043819,0,0,0,934264,0,0,0,1034799,0,0,0,1010530,0,0,0,980052,0,0,0,950794,0,0,0,995393,0,0,0,979215,0,0,0,1029040,0,0,0,863333,0,0,0,905685,0,0,0,944121,2,0,0,1120033,0,0,0,925989,0,0,0,971558,160,0,0,1122978,0,0,0,1019746,64,0x7f08f0c04ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fcfdf754ec0,0,393216,163840,0,0,0,0,0,15502,0.0,0.0,0.0,32768.0,0.0,0.0,419.0,32768.0,4096,16384,302,21993,1319,0,56.0,0.0,0.0,204088.0,64,0x7ff15f008ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41458082.0,30974897.0,0.0,64,0x7fd18625cec0,114688,0,32768,32768,16384,16384,65536,49152,27778989.0,86215948.0,40009211.0,131072.0,0.0,205841.0,0,0,12989,130.0,131073.0,0.0,0.0,1411881076677985,1411881076693505 diff --git a/tests/workloads/dispatch_2/MI200/roofline.csv b/tests/workloads/dispatch_2/MI200/roofline.csv index 9429fe3e22..f1da3203fc 100644 --- a/tests/workloads/dispatch_2/MI200/roofline.csv +++ b/tests/workloads/dispatch_2/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.7772,1388.1665,1389.3879,5014.8452,5011.7578,5017.9326,9224.0459,9223.4287,9224.6631,18051.555,18050.539,18052.57,20931.686,20871.127,20992.244,20262.873,20262.266,20263.48,170395.78,170391.08,170400.48,164867.72,164862.77,164872.67,41417.938,41417.441,41418.434,41473.121,41472.258,41473.984,166331.56,165842,166821.12 -1,1389.5524,1388.957,1390.1477,5027.1084,5025.0698,5029.147,9234.0732,9233.4004,9234.7461,18092.131,18087.773,18096.488,20973.596,20906.982,21040.209,20294.998,20294.43,20295.566,170843.41,170839.48,170847.33,165112.16,165107.75,165116.56,41477.531,41476.762,41478.301,41536.461,41535.434,41537.488,166856.12,166850.86,166861.39 -2,1388.4222,1387.8956,1388.9489,5037.208,5034.7656,5039.6504,9260.0596,9259.3047,9260.8145,18102.715,18101.805,18103.625,21046.008,21045.592,21046.424,20349.283,20348.805,20349.762,171121.91,171118.34,171125.47,165485.56,165482.52,165488.61,41581.629,41580.355,41582.902,41641.801,41640.477,41643.125,166935.38,166323.91,167546.84 -3,1388.8452,1388.2465,1389.444,5033.5464,5032.2622,5034.8306,9242.0127,9241.4883,9242.5371,18025.061,18021.33,18028.791,21038.613,21038.105,21039.121,20313.775,20313.098,20314.453,171038.38,171034.86,171041.89,165235.06,165230.89,165239.23,41442.316,41286.215,41598.418,41584.824,41584.324,41585.324,167033.81,167031.94,167035.69 +0,1388.9821,1388.3459,1389.6182,5017.0518,5014.043,5020.0605,9225.3008,9224.6426,9225.959,17712.033,17708.768,17715.299,20941.537,20881.26,21001.814,20271.555,20270.965,20272.145,170485.56,170481.81,170489.31,164931.84,164927.7,164935.98,41439.031,41438.484,41439.578,41494.887,41494.223,41495.551,166397.41,165908.08,166886.73 +1,1389.0138,1388.5118,1389.5157,5029.3579,5027.1226,5031.5933,9236.9922,9236.375,9237.6094,18238.225,18236.686,18239.764,20985.932,20919.07,21052.793,20303.445,20302.893,20303.998,170925.2,170920.75,170929.66,165159.62,165154.52,165164.73,41500.129,41499.258,41501,41555.73,41554.668,41556.793,166913.81,166910.55,166917.08 +2,1389.1837,1388.6691,1389.6984,5035.3047,5033.166,5037.4434,9260.9502,9260.4004,9261.5,18218.328,18217.295,18219.361,21047.867,21047.35,21048.385,20349.314,20348.729,20349.9,171130.08,171126.06,171134.09,165529.66,165526.56,165532.75,41583.043,41582.23,41583.855,41637.773,41636.875,41638.672,166949.05,166354.7,167543.39 +3,1388.8503,1388.3158,1389.3849,5032.9028,5031.438,5034.3677,9236.6445,9235.8213,9237.4678,18328.186,18327.355,18329.016,21030.797,21030.383,21031.211,20304.969,20304.414,20305.523,171054.72,171048.48,171060.95,165145.41,165140,165150.81,41432.672,41279.039,41586.305,41571.406,41568.879,41573.934,166963.53,166959.94,166967.12 diff --git a/tests/workloads/dispatch_2/MI200/sysinfo.csv b/tests/workloads/dispatch_2/MI200/sysinfo.csv index bea3faa52a..f8cdcd5c3d 100644 --- a/tests/workloads/dispatch_2/MI200/sysinfo.csv +++ b/tests/workloads/dispatch_2/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_2,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:17:28 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +dispatch_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:22:15 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_2/MI200/timestamps.csv b/tests/workloads/dispatch_2/MI200/timestamps.csv index 2e35c2631c..8a1c7ede3c 100644 --- a/tests/workloads/dispatch_2/MI200/timestamps.csv +++ b/tests/workloads/dispatch_2/MI200/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,305597,305597,1048576,256,0,0,8,0,16,64,0x0,0x7fadb1cc0ec0,198394440065730,198394440082212,198394440098052,198394440111888 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4129310,4129310,1048576,256,0,0,8,0,16,64,0x0,0x7f8a7d178ec0,1411881076659751,1411881076677985,1411881076693505,1411881076706139 diff --git a/tests/workloads/dispatch_6_8/MI100/log.txt b/tests/workloads/dispatch_6_8/MI100/log.txt new file mode 100644 index 0000000000..ea6af3929f --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_6_8/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['6:8'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155459' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155459_1280292' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155459_1280292/input0_results_240321_155459' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155459_1280292/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155459_1280292/input0_results_240321_155459 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155459' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155459_1280476' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155459_1280476/input0_results_240321_155459' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155459_1280476/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155459_1280476/input0_results_240321_155459 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155500' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155500_1280660' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155500_1280660/input0_results_240321_155500' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155500_1280660/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155500_1280660/input0_results_240321_155500 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155500' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155500_1280846' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155500_1280846/input0_results_240321_155500' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155500_1280846/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155500_1280846/input0_results_240321_155500 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155501' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155501_1281033' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155501_1281033/input0_results_240321_155501' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155501_1281033/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155501_1281033/input0_results_240321_155501 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155501' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155501_1281234' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155501_1281234/input0_results_240321_155501' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155501_1281234/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155501_1281234/input0_results_240321_155501 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155502' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155502_1281431' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155502_1281431/input0_results_240321_155502' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155502_1281431/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155502_1281431/input0_results_240321_155502 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155502' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155502_1281615' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155502_1281615/input0_results_240321_155502' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155502_1281615/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155502_1281615/input0_results_240321_155502 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155503' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155503_1281803' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155503_1281803/input0_results_240321_155503' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155503_1281803/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155503_1281803/input0_results_240321_155503 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155503' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155503_1281990' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155503_1281990/input0_results_240321_155503' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155503_1281990/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155503_1281990/input0_results_240321_155503 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155504' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155504_1282174' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155504_1282174/input0_results_240321_155504' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155504_1282174/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155504_1282174/input0_results_240321_155504 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155505' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155505_1282361' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155505_1282361/input0_results_240321_155505' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155505_1282361/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155505_1282361/input0_results_240321_155505 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155506' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155506_1282545' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155506_1282545/input0_results_240321_155506' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155506_1282545/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155506_1282545/input0_results_240321_155506 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155506' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155506_1282729' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155506_1282729/input0_results_240321_155506' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155506_1282729/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155506_1282729/input0_results_240321_155506 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155507' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155507_1282913' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155507_1282913/input0_results_240321_155507' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155507_1282913/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155507_1282913/input0_results_240321_155507 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155507' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155507_1283100' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155507_1283100/input0_results_240321_155507' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155507_1283100/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155507_1283100/input0_results_240321_155507 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155508' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155508_1283285' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155508_1283285/input0_results_240321_155508' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155508_1283285/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155508_1283285/input0_results_240321_155508 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155508' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155508_1283473' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155508_1283473/input0_results_240321_155508' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155508_1283473/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155508_1283473/input0_results_240321_155508 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155509' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155509_1283659' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155509_1283659/input0_results_240321_155509' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155509_1283659/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155509_1283659/input0_results_240321_155509 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155509' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155509_1283845' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155509_1283845/input0_results_240321_155509' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155509_1283845/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155509_1283845/input0_results_240321_155509 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155510' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155510_1284029' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155510_1284029/input0_results_240321_155510' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155510_1284029/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155510_1284029/input0_results_240321_155510 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155510' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155510_1284213' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155510_1284213/input0_results_240321_155510' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155510_1284213/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155510_1284213/input0_results_240321_155510 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155511' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155511_1284397' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155511_1284397/input0_results_240321_155511' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155511_1284397/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155511_1284397/input0_results_240321_155511 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/dispatch_6_8/MI100/sysinfo.csv b/tests/workloads/dispatch_6_8/MI100/sysinfo.csv index 5285a1da29..2c4893682f 100644 --- a/tests/workloads/dispatch_6_8/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_6_8/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_6_8,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:11:04 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_6_8,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:54:58 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_6_8/MI200/log.txt b/tests/workloads/dispatch_6_8/MI200/log.txt new file mode 100644 index 0000000000..6a14a25bb4 --- /dev/null +++ b/tests/workloads/dispatch_6_8/MI200/log.txt @@ -0,0 +1,762 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_6_8/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['6:8'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_164800' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164800_4173540' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164800_4173540/input0_results_240321_164800' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164800_4173540/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164800_4173540/input0_results_240321_164800 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_164800' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164800_4173741' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164800_4173741/input0_results_240321_164800' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164800_4173741/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164800_4173741/input0_results_240321_164800 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_164801' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164801_4173929' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164801_4173929/input0_results_240321_164801' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164801_4173929/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164801_4173929/input0_results_240321_164801 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_164801' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164801_4174121' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164801_4174121/input0_results_240321_164801' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164801_4174121/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164801_4174121/input0_results_240321_164801 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_164802' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164802_4174333' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164802_4174333/input0_results_240321_164802' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164802_4174333/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164802_4174333/input0_results_240321_164802 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_164802' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164802_4174535' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164802_4174535/input0_results_240321_164802' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164802_4174535/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164802_4174535/input0_results_240321_164802 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_164803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164803_4174725' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164803_4174725/input0_results_240321_164803' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164803_4174725/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164803_4174725/input0_results_240321_164803 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_164803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164803_4174910' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164803_4174910/input0_results_240321_164803' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164803_4174910/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164803_4174910/input0_results_240321_164803 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_164804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164804_4175114' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164804_4175114/input0_results_240321_164804' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164804_4175114/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164804_4175114/input0_results_240321_164804 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_164804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164804_4175316' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164804_4175316/input0_results_240321_164804' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164804_4175316/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164804_4175316/input0_results_240321_164804 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_164805' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164805_4175518' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164805_4175518/input0_results_240321_164805' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164805_4175518/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164805_4175518/input0_results_240321_164805 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_164805' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164805_4175706' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164805_4175706/input0_results_240321_164805' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164805_4175706/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164805_4175706/input0_results_240321_164805 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_164806' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164806_4175909' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164806_4175909/input0_results_240321_164806' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164806_4175909/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164806_4175909/input0_results_240321_164806 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_164807' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164807_4176093' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164807_4176093/input0_results_240321_164807' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164807_4176093/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164807_4176093/input0_results_240321_164807 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_164807' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164807_4176282' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164807_4176282/input0_results_240321_164807' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164807_4176282/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164807_4176282/input0_results_240321_164807 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_164808' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164808_4176480' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164808_4176480/input0_results_240321_164808' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164808_4176480/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164808_4176480/input0_results_240321_164808 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_164809' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164809_4176667' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164809_4176667/input0_results_240321_164809' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164809_4176667/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164809_4176667/input0_results_240321_164809 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_164809' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164809_4176869' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164809_4176869/input0_results_240321_164809' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164809_4176869/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164809_4176869/input0_results_240321_164809 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_164810' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164810_4177071' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164810_4177071/input0_results_240321_164810' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164810_4177071/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164810_4177071/input0_results_240321_164810 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_164810' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164810_4177256' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164810_4177256/input0_results_240321_164810' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164810_4177256/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164810_4177256/input0_results_240321_164810 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_164810' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164810_4177458' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164810_4177458/input0_results_240321_164810' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164810_4177458/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164810_4177458/input0_results_240321_164810 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_164811' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164811_4177660' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164811_4177660/input0_results_240321_164811' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164811_4177660/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164811_4177660/input0_results_240321_164811 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_164811' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164811_4177846' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164811_4177846/input0_results_240321_164811' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164811_4177846/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164811_4177846/input0_results_240321_164811 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_164812' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164812_4178048' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164812_4178048/input0_results_240321_164812' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164812_4178048/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164812_4178048/input0_results_240321_164812 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_6_8/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_164812' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_6_8/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164812_4178234' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164812_4178234/input0_results_240321_164812' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164812_4178234/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 6:8 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_164812_4178234/input0_results_240321_164812 + |-> [rocprof] File 'tests/workloads/dispatch_6_8/MI200/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/dispatch_6_8/MI200/sysinfo.csv b/tests/workloads/dispatch_6_8/MI200/sysinfo.csv index dac3ef144e..e1554780b5 100644 --- a/tests/workloads/dispatch_6_8/MI200/sysinfo.csv +++ b/tests/workloads/dispatch_6_8/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_6_8,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:52:17 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +dispatch_6_8,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:47:59 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_7/MI100/log.txt b/tests/workloads/dispatch_7/MI100/log.txt new file mode 100644 index 0000000000..96c0ea0e6e --- /dev/null +++ b/tests/workloads/dispatch_7/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_7/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['7'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155247' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155247_1237531' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155247_1237531/input0_results_240321_155247' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155247_1237531/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155247_1237531/input0_results_240321_155247 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155248' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155248_1237715' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155248_1237715/input0_results_240321_155248' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155248_1237715/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155248_1237715/input0_results_240321_155248 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155248' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155248_1237900' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155248_1237900/input0_results_240321_155248' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155248_1237900/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155248_1237900/input0_results_240321_155248 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155248' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155248_1238087' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155248_1238087/input0_results_240321_155248' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155248_1238087/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155248_1238087/input0_results_240321_155248 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155249' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155249_1238273' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155249_1238273/input0_results_240321_155249' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155249_1238273/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155249_1238273/input0_results_240321_155249 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155249' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155249_1238458' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155249_1238458/input0_results_240321_155249' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155249_1238458/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155249_1238458/input0_results_240321_155249 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155250' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155250_1238645' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155250_1238645/input0_results_240321_155250' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155250_1238645/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155250_1238645/input0_results_240321_155250 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155250' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155250_1238830' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155250_1238830/input0_results_240321_155250' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155250_1238830/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155250_1238830/input0_results_240321_155250 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155251' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155251_1239014' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155251_1239014/input0_results_240321_155251' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155251_1239014/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155251_1239014/input0_results_240321_155251 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155252' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155252_1239201' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155252_1239201/input0_results_240321_155252' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155252_1239201/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155252_1239201/input0_results_240321_155252 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155252' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155252_1239391' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155252_1239391/input0_results_240321_155252' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155252_1239391/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155252_1239391/input0_results_240321_155252 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155253' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155253_1239576' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155253_1239576/input0_results_240321_155253' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155253_1239576/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155253_1239576/input0_results_240321_155253 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155254' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155254_1239763' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155254_1239763/input0_results_240321_155254' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155254_1239763/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155254_1239763/input0_results_240321_155254 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155254' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155254_1239947' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155254_1239947/input0_results_240321_155254' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155254_1239947/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155254_1239947/input0_results_240321_155254 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155255' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155255_1240131' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155255_1240131/input0_results_240321_155255' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155255_1240131/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155255_1240131/input0_results_240321_155255 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155255' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155255_1240317' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155255_1240317/input0_results_240321_155255' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155255_1240317/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155255_1240317/input0_results_240321_155255 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155256' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155256_1240502' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155256_1240502/input0_results_240321_155256' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155256_1240502/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155256_1240502/input0_results_240321_155256 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155256' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155256_1240687' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155256_1240687/input0_results_240321_155256' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155256_1240687/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155256_1240687/input0_results_240321_155256 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155257' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155257_1240873' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155257_1240873/input0_results_240321_155257' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155257_1240873/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155257_1240873/input0_results_240321_155257 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155257' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155257_1241057' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155257_1241057/input0_results_240321_155257' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155257_1241057/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155257_1241057/input0_results_240321_155257 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155258' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155258_1241241' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155258_1241241/input0_results_240321_155258' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155258_1241241/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155258_1241241/input0_results_240321_155258 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155258' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155258_1241427' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155258_1241427/input0_results_240321_155258' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155258_1241427/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155258_1241427/input0_results_240321_155258 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155259' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155259_1241612' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155259_1241612/input0_results_240321_155259' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155259_1241612/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155259_1241612/input0_results_240321_155259 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/dispatch_7/MI100/sysinfo.csv b/tests/workloads/dispatch_7/MI100/sysinfo.csv index a35070f152..67532231bb 100644 --- a/tests/workloads/dispatch_7/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_7/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_7,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:22 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_7,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:52:47 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_7/MI200/log.txt b/tests/workloads/dispatch_7/MI200/log.txt new file mode 100644 index 0000000000..f09dd520b6 --- /dev/null +++ b/tests/workloads/dispatch_7/MI200/log.txt @@ -0,0 +1,762 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_7/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['7'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_162201' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162201_4119660' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162201_4119660/input0_results_240321_162201' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162201_4119660/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162201_4119660/input0_results_240321_162201 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_162202' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162202_4119862' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162202_4119862/input0_results_240321_162202' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162202_4119862/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162202_4119862/input0_results_240321_162202 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_162202' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162202_4120064' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162202_4120064/input0_results_240321_162202' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162202_4120064/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162202_4120064/input0_results_240321_162202 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_162203' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162203_4120251' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162203_4120251/input0_results_240321_162203' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162203_4120251/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162203_4120251/input0_results_240321_162203 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_162203' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162203_4120454' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162203_4120454/input0_results_240321_162203' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162203_4120454/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162203_4120454/input0_results_240321_162203 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_162204' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162204_4120658' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162204_4120658/input0_results_240321_162204' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162204_4120658/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162204_4120658/input0_results_240321_162204 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_162204' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162204_4120842' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162204_4120842/input0_results_240321_162204' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162204_4120842/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162204_4120842/input0_results_240321_162204 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_162205' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162205_4121045' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162205_4121045/input0_results_240321_162205' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162205_4121045/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162205_4121045/input0_results_240321_162205 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_162205' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162205_4121233' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162205_4121233/input0_results_240321_162205' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162205_4121233/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162205_4121233/input0_results_240321_162205 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_162206' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162206_4121419' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162206_4121419/input0_results_240321_162206' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162206_4121419/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162206_4121419/input0_results_240321_162206 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_162206' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162206_4121607' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162206_4121607/input0_results_240321_162206' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162206_4121607/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162206_4121607/input0_results_240321_162206 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_162207' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162207_4121807' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162207_4121807/input0_results_240321_162207' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162207_4121807/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162207_4121807/input0_results_240321_162207 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_162208' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162208_4121993' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162208_4121993/input0_results_240321_162208' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162208_4121993/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162208_4121993/input0_results_240321_162208 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_162208' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162208_4122179' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162208_4122179/input0_results_240321_162208' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162208_4122179/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162208_4122179/input0_results_240321_162208 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_162209' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162209_4122384' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162209_4122384/input0_results_240321_162209' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162209_4122384/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162209_4122384/input0_results_240321_162209 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_162210' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162210_4122568' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162210_4122568/input0_results_240321_162210' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162210_4122568/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162210_4122568/input0_results_240321_162210 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_162210' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162210_4122756' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162210_4122756/input0_results_240321_162210' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162210_4122756/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162210_4122756/input0_results_240321_162210 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_162211' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162211_4122940' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162211_4122940/input0_results_240321_162211' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162211_4122940/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162211_4122940/input0_results_240321_162211 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_162211' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162211_4123142' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162211_4123142/input0_results_240321_162211' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162211_4123142/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162211_4123142/input0_results_240321_162211 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_162212' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162212_4123331' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162212_4123331/input0_results_240321_162212' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162212_4123331/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162212_4123331/input0_results_240321_162212 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_162212' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162212_4123521' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162212_4123521/input0_results_240321_162212' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162212_4123521/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162212_4123521/input0_results_240321_162212 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_162213' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162213_4123724' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162213_4123724/input0_results_240321_162213' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162213_4123724/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162213_4123724/input0_results_240321_162213 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_162213' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162213_4123910' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162213_4123910/input0_results_240321_162213' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162213_4123910/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162213_4123910/input0_results_240321_162213 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_162213' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162213_4124115' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162213_4124115/input0_results_240321_162213' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162213_4124115/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162213_4124115/input0_results_240321_162213 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_7/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_162214' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_7/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162214_4124301' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162214_4124301/input0_results_240321_162214' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162214_4124301/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = 7 + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_162214_4124301/input0_results_240321_162214 + |-> [rocprof] File 'tests/workloads/dispatch_7/MI200/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/dispatch_7/MI200/sysinfo.csv b/tests/workloads/dispatch_7/MI200/sysinfo.csv index 7915957950..6a2b895ba0 100644 --- a/tests/workloads/dispatch_7/MI200/sysinfo.csv +++ b/tests/workloads/dispatch_7/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_7,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:17:14 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +dispatch_7,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:22:01 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv index c18b695a2a..f92a8ab6b9 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100378,100378,1048576,256,0,0,8,8,16,64,0x0,0x7f626043ce80,47668,47668,16384,65536,29010,1854504,194051411496730,194063713519257,194063713543257,194051419980944 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1196025,1196025,1048576,256,0,0,8,8,16,64,0x0,0x7f3d8c718ec0,48770,48770,16384,65536,14340,1831132,1409981308951962,1409993151479981,1409993151504461,1409981316706246 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv index 1f7bb3d9e6..d560633314 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100568,100568,1048576,256,0,0,8,8,16,64,0x0,0x7fd4ec17ce80,0,0,0,194051899565198,194063713519257,194063713543257,194051907560356 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1196228,1196228,1048576,256,0,0,8,8,16,64,0x0,0x7fde5b1e8ec0,0,0,0,1409981797196754,1409993151479981,1409993151504461,1409981804835661 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv index f8fbd94be0..a0dfc700b5 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100757,100757,1048576,256,0,0,8,8,16,64,0x0,0x7f9039444e80,65536,381816,24432184,194052393039211,194063713519257,194063713543257,194052400779427 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1196431,1196431,1048576,256,0,0,8,8,16,64,0x0,0x7f4aa38c8ec0,65536,241224,30840808,1409982278411950,1409993151479981,1409993151504461,1409982286062829 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv index 861cd8a132..c0a524d57d 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,100958,100958,1048576,256,0,0,8,8,16,64,0x0,0x7f1524968e80,32768,1335366,85465152,194052885720815,194063713519257,194063713543257,194052895100074 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1196615,1196615,1048576,256,0,0,8,8,16,64,0x0,0x7f9060c34ec0,32768,613680,78559712,1409982759228172,1409993151479981,1409993151504461,1409982766976496 diff --git a/tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv index d0e389b494..3535d04f25 100644 --- a/tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,101159,101159,1048576,256,0,0,8,8,16,64,0x0,0x7f37e15b8e80,48091,48091,17290,384736,16384,25334875,235204,0,101833412,194053385787391,194063713519257,194063713543257,194053393562893 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1196818,1196818,1048576,256,0,0,8,8,16,64,0x0,0x7f782cf40ec0,49166,49166,17906,393336,16384,25994718,243072,0,104504564,1409983239161961,1409993151479981,1409993151504461,1409983246839460 diff --git a/tests/workloads/dispatch_inv/MI100/log.txt b/tests/workloads/dispatch_inv/MI100/log.txt new file mode 100644 index 0000000000..03351f4afe --- /dev/null +++ b/tests/workloads/dispatch_inv/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_inv/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['invalid'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155047' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155047_1195865' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155047_1195865/input0_results_240321_155047' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155047_1195865/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155047_1195865/input0_results_240321_155047 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155047' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155047_1196068' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155047_1196068/input0_results_240321_155047' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155047_1196068/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155047_1196068/input0_results_240321_155047 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155048' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155048_1196271' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155048_1196271/input0_results_240321_155048' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155048_1196271/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155048_1196271/input0_results_240321_155048 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155048' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155048_1196455' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155048_1196455/input0_results_240321_155048' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155048_1196455/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155048_1196455/input0_results_240321_155048 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155049' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155049_1196658' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155049_1196658/input0_results_240321_155049' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155049_1196658/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155049_1196658/input0_results_240321_155049 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155049' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155049_1196843' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155049_1196843/input0_results_240321_155049' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155049_1196843/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155049_1196843/input0_results_240321_155049 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155050' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155050_1197044' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155050_1197044/input0_results_240321_155050' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155050_1197044/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155050_1197044/input0_results_240321_155050 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155050' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155050_1197247' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155050_1197247/input0_results_240321_155050' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155050_1197247/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155050_1197247/input0_results_240321_155050 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155051' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155051_1197449' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155051_1197449/input0_results_240321_155051' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155051_1197449/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155051_1197449/input0_results_240321_155051 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155051' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155051_1197651' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155051_1197651/input0_results_240321_155051' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155051_1197651/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155051_1197651/input0_results_240321_155051 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155052' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155052_1197852' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155052_1197852/input0_results_240321_155052' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155052_1197852/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155052_1197852/input0_results_240321_155052 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155053' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155053_1198055' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155053_1198055/input0_results_240321_155053' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155053_1198055/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155053_1198055/input0_results_240321_155053 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155053' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155053_1198258' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155053_1198258/input0_results_240321_155053' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155053_1198258/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155053_1198258/input0_results_240321_155053 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155054' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155054_1198460' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155054_1198460/input0_results_240321_155054' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155054_1198460/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155054_1198460/input0_results_240321_155054 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155055' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155055_1198662' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155055_1198662/input0_results_240321_155055' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155055_1198662/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155055_1198662/input0_results_240321_155055 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155055' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155055_1198863' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155055_1198863/input0_results_240321_155055' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155055_1198863/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155055_1198863/input0_results_240321_155055 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155056' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155056_1199051' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155056_1199051/input0_results_240321_155056' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155056_1199051/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155056_1199051/input0_results_240321_155056 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155056' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155056_1199253' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155056_1199253/input0_results_240321_155056' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155056_1199253/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155056_1199253/input0_results_240321_155056 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155057' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155057_1199438' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155057_1199438/input0_results_240321_155057' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155057_1199438/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155057_1199438/input0_results_240321_155057 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155057' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155057_1199640' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155057_1199640/input0_results_240321_155057' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155057_1199640/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155057_1199640/input0_results_240321_155057 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155058' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155058_1199843' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155058_1199843/input0_results_240321_155058' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155058_1199843/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155058_1199843/input0_results_240321_155058 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155058' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155058_1200045' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155058_1200045/input0_results_240321_155058' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155058_1200045/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155058_1200045/input0_results_240321_155058 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155059' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155059_1200248' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155059_1200248/input0_results_240321_155059' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155059_1200248/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_155059_1200248/input0_results_240321_155059 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/dispatch_inv/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_inv/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..4a20af5fc0 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI100/pmc_dispatch_info.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/dispatch_inv/MI100/pmc_perf.csv b/tests/workloads/dispatch_inv/MI100/pmc_perf.csv index b396c4a573..0276bf4ad5 100644 --- a/tests/workloads/dispatch_inv/MI100/pmc_perf.csv +++ b/tests/workloads/dispatch_inv/MI100/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_1,obj_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_5,obj_5,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_8,obj_8,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_9,obj_9,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_10,obj_10,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_11,obj_11,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_12,obj_12,TCC_EA_ATOMIC_LEVEL_sum,wave_size_13,obj_13,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_14,obj_14,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_15,obj_15,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_16,obj_16,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fa86d120e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,57017.0,120687.0,64,0x7fbfe2004e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47480,0,131499.0,131072.0,0.0,131104.0,64,0x7fc025a5ce80,1331,0,0,1684615,1241,0,0,1660687,1861,0,0,1651803,1145,0,0,1701557,779,0,0,1603459,1214,0,0,1779568,1791,0,0,1722197,1832,0,0,1746386,715,0,0,1601501,1056,0,0,1576397,2605,0,0,1829070,609,0,0,1633407,1118,0,0,1606097,2322,0,0,1832044,1545,0,0,1725820,802,0,0,1603711,5865,0,0,2224904,1079,0,0,1625376,1339,0,0,1639921,981,0,0,1632177,959,0,0,1632226,2710,0,0,1930909,1542,0,0,1744930,1033,0,0,1629899,1622,0,0,1709431,1967,0,0,1933344,861,0,0,1560684,3022,0,0,1896124,1288,0,0,1695077,1541,0,0,1653531,2553,0,0,1852185,1531,0,0,1712096,64,0x7f9a0950ee80,32768,0,0,0,16384,16384,393216,23411804,960.0,513882.0,0.0,524288.0,1104969.0,32768.0,0,0,0,17404,131072.0,131072.0,0.0,131072.0,64,0x7f3bd8102e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131413.0,0.0,674.0,131412.0,64,0x7f87862f6e80,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,0,47644,0,0,64,0x7feec4b7ce80,4096,0,3368,0,4096,0,983,0,4099,0,1076,0,4096,0,159,0,4096,0,7475,0,4096,0,640,0,4096,0,4327,0,4096,0,1982,0,4096,0,1633,0,4096,0,3389,0,4144,0,2946,0,4096,0,4008,0,4144,0,2380,0,4096,0,4305,0,4096,0,4854,0,4097,0,212,0,4096,0,1122,0,4096,0,4725,0,4096,0,1599,0,4096,0,969,0,4243,0,3018,0,4096,0,1414,0,4096,0,3916,0,4096,0,88,0,4096,0,8,0,4096,0,1848,0,4096,0,3864,0,4096,0,262,0,4096,0,584,0,4096,0,241,0,4096,0,3987,0,4096,0,478,0,64,0x7fb6658f2e80,389200,234648,3409750,16384,24946073,144,48,0,48649,48649,3872532.0,3028791.0,7437.0,1264821.0,2119053.0,0.0,3019823.0,2707922.0,387743,244598,48649,0,48649,0,1556768.0,967322.0,0.0,0.0,64,0x7f04567b8e80,0,8192,4096,8192,0,8192,4096,8192,141,8360,4405,8501,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f17bbfa6e80,131072.0,131072.0,0.0,2548822.0,0.0,0.0,128759174.0,59741309.0,64,0x7fac5829ae80,188449,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14082,30466,9744,550,0,46533,262608.0,0.0,188.0,262420.0,64,0x7f43c8166e80,2045156,360448,163840,0,0,180224,114688,0,71011798.0,209930567.0,81329775.0,131072.0,0.0,607422.0,0,0,26574,94204.0,0.0,0.0,94204.0,64,0x7fa533b2ee80,0.0,64,0x7fd9dc9dae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86444.0,44628.0,131112.0,0.0,64,0x7fa5e3444e80,0,0,192,0,65536,64485,48,1331,31457,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47483,1743,0,48.0,217.0,0.0,262288.0,64,0x7f6085844e80,0,3832605,4096,4096,0,3673784,4096,4096,0,3430738,4096,4096,0,3047997,4096,4096,0,5111374,4096,4096,0,3169517,4096,4096,0,3393920,4096,4096,0,3171252,4096,4096,0,3174715,4096,4096,0,4944689,4096,4096,0,3154798,4096,4096,0,3357818,4096,4096,0,3551138,4096,4096,0,4680239,4096,4096,0,2972474,4096,4096,0,3066952,4096,4096,0,3638371,4096,4096,0,4823148,4096,4096,0,3171402,4096,4096,0,3988047,4096,4096,0,5341242,4096,4096,0,4995249,4096,4096,0,3162568,4096,4096,0,2538109,4096,4096,0,2928889,4096,4096,0,3593153,4096,4096,0,3589396,4096,4096,0,3559980,4096,4096,0,3306367,4096,4096,0,3918173,4096,4096,0,2929314,4096,4096,0,4015677,4096,4096,64,0x7f3857fdae80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,194063713519257,194063713543257 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_3,obj_3,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_6,obj_6,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_7,obj_7,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_11,obj_11,TCC_EA_ATOMIC_LEVEL_sum,wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_14,obj_14,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_15,obj_15,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_16,obj_16,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fa22a004ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f478c34cec0,4096,0,765,0,4096,0,3440,0,4096,0,1296,0,4099,0,528,0,4096,0,1152,0,4096,0,106,0,4096,0,881,0,4096,0,2427,0,4096,0,1517,0,4096,0,3573,0,4096,0,1221,0,4144,0,1606,0,4096,0,5223,0,4096,0,106,0,4096,0,4104,0,4096,0,0,0,4096,0,1679,0,4096,0,5054,0,4096,0,3492,0,4096,0,725,0,4096,0,3074,0,4144,0,1095,0,4096,0,3917,0,4096,0,7,0,4096,0,2566,0,4288,0,5630,0,4096,0,350,0,4096,0,3437,0,4097,0,231,0,4096,0,4475,0,4096,0,31,0,4096,0,56,0,64,0x7fbe76474ec0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,0,48507,0,0,64,0x7f6ecc420ec0,1729535,360448,163840,0,0,180224,114688,0,70012064.0,187334626.0,72886718.0,131072.0,0.0,603890.0,0,0,26400,69380.0,0.0,0.0,69380.0,64,0x7f52a4ef0ec0,391664,238734,3500948,16384,26241102,144,48,0,48957,48957,3933416.0,3057266.0,6511.0,902457.0,2076964.0,0.0,3048535.0,2737340.0,389951,248676,48957,0,48957,0,1566624.0,958701.0,0.0,0.0,64,0x7f5127a28ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,22011.0,109569.0,64,0x7f9ab0fb8ec0,0,8327,4231,8327,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,64,0x7f85fd81cec0,193054,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12965,29349,10087,588,0,46749,262641.0,0.0,188.0,262453.0,64,0x7fa2fa068ec0,32768,0,0,0,16384,16384,393216,21613133,960.0,513889.0,0.0,524288.0,1179883.0,32768.0,0,0,0,17056,131072.0,131072.0,0.0,131072.0,64,0x7fa6fe658ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47522,0,131524.0,131072.0,0.0,131104.0,64,0x7f619ce74ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131455.0,0.0,758.0,131454.0,64,0x7f2fe581cec0,0.0,64,0x7f2e53cc4ec0,0,3833573,4096,4096,0,3375924,4096,4096,0,3331661,4096,4096,0,2308447,4096,4096,0,3480687,4096,4096,0,3405481,4096,4096,0,4966104,4096,4096,0,2577587,4096,4096,0,4699814,4096,4096,0,3071284,4096,4096,0,4019899,4096,4096,0,3187550,4096,4096,0,4925213,4096,4096,0,3286298,4096,4096,0,4638931,4096,4096,0,2523663,4096,4096,0,4408569,4096,4096,0,4136354,4096,4096,0,3765224,4096,4096,0,4371592,4096,4096,0,5153936,4096,4096,0,4066775,4096,4096,0,2660018,4096,4096,0,3078938,4096,4096,0,4267584,4096,4096,0,4855882,4096,4096,0,3088643,4096,4096,0,2214320,4096,4096,0,3544727,4096,4096,0,5160553,4096,4096,0,2895821,4096,4096,0,3264725,4096,4096,64,0x7ff7eb0dcec0,0,0,192,0,65536,64452,48,1527,32735,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48818,1874,0,48.0,516.0,0.0,262288.0,64,0x7fe2c7868ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87144.0,43928.0,131111.0,0.0,64,0x7fdf91da8ec0,3079,0,0,1941936,1254,0,0,1671342,3056,0,0,1918075,3001,0,0,1986871,1317,0,0,1759408,977,0,0,1732965,1640,0,0,1781650,3159,0,0,1987810,3714,0,0,2067399,2649,0,0,1925924,1207,0,0,1746800,1711,0,0,1756736,2097,0,0,1904413,582,0,0,1650175,1971,0,0,1782720,4295,0,0,2170774,4338,0,0,2068077,777,0,0,1649095,4682,0,0,2029158,2758,0,0,1836946,2416,0,0,1932048,1588,0,0,1875728,4332,0,0,2038422,4996,0,0,2123458,3189,0,0,1938225,2988,0,0,1939298,2278,0,0,1880470,3908,0,0,2002698,2113,0,0,1824891,1977,0,0,1843405,2002,0,0,1852311,4111,0,0,2077903,64,0x7f0b85954ec0,131072.0,131072.0,0.0,2436135.0,0.0,0.0,110499901.0,63612200.0,1409993151479981,1409993151504461 diff --git a/tests/workloads/dispatch_inv/MI100/sysinfo.csv b/tests/workloads/dispatch_inv/MI100/sysinfo.csv index fc0cb7d78a..8ca917541c 100644 --- a/tests/workloads/dispatch_inv/MI100/sysinfo.csv +++ b/tests/workloads/dispatch_inv/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_inv,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:05:16 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +dispatch_inv,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:50:46 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/dispatch_inv/MI100/timestamps.csv b/tests/workloads/dispatch_inv/MI100/timestamps.csv index f95c9946ad..83a7434116 100644 --- a/tests/workloads/dispatch_inv/MI100/timestamps.csv +++ b/tests/workloads/dispatch_inv/MI100/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,104717,104717,1048576,256,0,0,8,8,16,64,0x0,0x7fa555e9ee80,194063713493885,194063713519257,194063713543257,194063713554520 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1200408,1200408,1048576,256,0,0,8,8,16,64,0x0,0x7f761fe58ec0,1409993151454587,1409993151479981,1409993151504461,1409993151517756 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv index a71e5dcad7..486c3c00eb 100644 --- a/tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,248270,248270,1048576,256,0,0,8,0,16,64,0x0,0x7fee6c1e8ec0,28159,28159,16384,65536,18528,2096508,197314699318636,197327446943430,197327446964070,197314715555093 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4070883,4070883,1048576,256,0,0,8,0,16,64,0x0,0x7f3290b00ec0,27605,27605,16384,65536,13878,1517264,1410706212315522,1410719177571898,1410719177592538,1410706228473689 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv index 281f7bfecd..a9c516ec17 100644 --- a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,248472,248472,1048576,256,0,0,8,0,16,64,0x0,0x7f335e55cec0,0,0,0,197315182575180,197327446943430,197327446964070,197315198215128 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4071085,4071085,1048576,256,0,0,8,0,16,64,0x0,0x7fc0c4880ec0,0,0,0,1410706705601444,1410719177571898,1410719177592538,1410706721607704 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv index 7356929c4a..6ac2a0eb13 100644 --- a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,248674,248674,1048576,256,0,0,8,0,16,64,0x0,0x7f09405d0ec0,65536,187198,20922392,197315663370888,197327446943430,197327446964070,197315679715439 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4071277,4071277,1048576,256,0,0,8,0,16,64,0x0,0x7f48680b0ec0,65536,207168,23284944,1410707198038150,1410719177571898,1410719177592538,1410707213906169 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv index 463ea58766..07b40a9c89 100644 --- a/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,248877,248877,1048576,256,0,0,8,0,16,64,0x0,0x7f819db68ec0,32768,293897,32918400,197316140235970,197327446943430,197327446964070,197316156066459 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4071462,4071462,1048576,256,0,0,8,0,16,64,0x0,0x7f949b134ec0,32768,296236,33173792,1410707687433184,1410719177571898,1410719177592538,1410707703242482 diff --git a/tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv index fdc4eedb25..6b8245d724 100644 --- a/tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,249077,249077,1048576,256,0,0,8,0,16,64,0x0,0x7f2a00ac0ec0,27945,27945,11402,223568,16384,10871098,128273,0,43994300,197316621462013,197327446943430,197327446964070,197316637162384 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4071665,4071665,1048576,256,0,0,8,0,16,64,0x0,0x7fb260a8cec0,28141,28141,11099,225136,16384,11221694,132697,0,45401376,1410708182655689,1410719177571898,1410719177592538,1410708199397810 diff --git a/tests/workloads/dispatch_inv/MI200/log.txt b/tests/workloads/dispatch_inv/MI200/log.txt new file mode 100644 index 0000000000..b3a5d5cab5 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/log.txt @@ -0,0 +1,764 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/dispatch_inv/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: ['invalid'] +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_160253' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160253_4070723' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160253_4070723/input0_results_240321_160253' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160253_4070723/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160253_4070723/input0_results_240321_160253 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_160254' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160254_4070925' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160254_4070925/input0_results_240321_160254' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160254_4070925/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160254_4070925/input0_results_240321_160254 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_160254' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160254_4071117' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160254_4071117/input0_results_240321_160254' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160254_4071117/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160254_4071117/input0_results_240321_160254 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_160255' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160255_4071302' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160255_4071302/input0_results_240321_160255' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160255_4071302/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160255_4071302/input0_results_240321_160255 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_160255' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160255_4071505' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160255_4071505/input0_results_240321_160255' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160255_4071505/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160255_4071505/input0_results_240321_160255 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_160256' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160256_4071704' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160256_4071704/input0_results_240321_160256' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160256_4071704/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160256_4071704/input0_results_240321_160256 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_160256' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160256_4071889' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160256_4071889/input0_results_240321_160256' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160256_4071889/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160256_4071889/input0_results_240321_160256 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_160257' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160257_4072074' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160257_4072074/input0_results_240321_160257' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160257_4072074/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160257_4072074/input0_results_240321_160257 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_160257' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160257_4072259' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160257_4072259/input0_results_240321_160257' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160257_4072259/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160257_4072259/input0_results_240321_160257 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_160258' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160258_4072456' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160258_4072456/input0_results_240321_160258' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160258_4072456/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160258_4072456/input0_results_240321_160258 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_160258' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160258_4072642' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160258_4072642/input0_results_240321_160258' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160258_4072642/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160258_4072642/input0_results_240321_160258 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_160259' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160259_4072850' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160259_4072850/input0_results_240321_160259' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160259_4072850/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160259_4072850/input0_results_240321_160259 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_160300' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160300_4073035' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160300_4073035/input0_results_240321_160300' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160300_4073035/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160300_4073035/input0_results_240321_160300 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_160301' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160301_4073239' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160301_4073239/input0_results_240321_160301' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160301_4073239/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160301_4073239/input0_results_240321_160301 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_160301' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160301_4073460' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160301_4073460/input0_results_240321_160301' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160301_4073460/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160301_4073460/input0_results_240321_160301 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_160302' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160302_4073655' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160302_4073655/input0_results_240321_160302' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160302_4073655/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160302_4073655/input0_results_240321_160302 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_160303' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160303_4073839' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160303_4073839/input0_results_240321_160303' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160303_4073839/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160303_4073839/input0_results_240321_160303 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_160303' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160303_4074032' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160303_4074032/input0_results_240321_160303' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160303_4074032/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160303_4074032/input0_results_240321_160303 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_160304' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160304_4074228' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160304_4074228/input0_results_240321_160304' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160304_4074228/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160304_4074228/input0_results_240321_160304 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_160304' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160304_4074428' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160304_4074428/input0_results_240321_160304' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160304_4074428/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160304_4074428/input0_results_240321_160304 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_160305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160305_4074630' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160305_4074630/input0_results_240321_160305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160305_4074630/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160305_4074630/input0_results_240321_160305 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_160305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160305_4074832' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160305_4074832/input0_results_240321_160305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160305_4074832/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160305_4074832/input0_results_240321_160305 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_160305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160305_4075016' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160305_4075016/input0_results_240321_160305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160305_4075016/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160305_4075016/input0_results_240321_160305 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_160306' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160306_4075219' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160306_4075219/input0_results_240321_160306' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160306_4075219/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160306_4075219/input0_results_240321_160306 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/dispatch_inv/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_160306' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/dispatch_inv/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160306_4075410' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160306_4075410/input0_results_240321_160306' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160306_4075410/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = invalid + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 1 contexts collected, output directory /tmp/rpl_data_240321_160306_4075410/input0_results_240321_160306 + |-> [rocprof] File 'tests/workloads/dispatch_inv/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/dispatch_inv/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/dispatch_inv/MI200/pmc_dispatch_info.csv b/tests/workloads/dispatch_inv/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..4a20af5fc0 --- /dev/null +++ b/tests/workloads/dispatch_inv/MI200/pmc_dispatch_info.csv @@ -0,0 +1,2 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/dispatch_inv/MI200/pmc_perf.csv b/tests/workloads/dispatch_inv/MI200/pmc_perf.csv index c0fd6a1e47..4c780180ce 100644 --- a/tests/workloads/dispatch_inv/MI200/pmc_perf.csv +++ b/tests/workloads/dispatch_inv/MI200/pmc_perf.csv @@ -1,2 +1,2 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_1,obj_1,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_11,obj_11,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_12,obj_12,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_15,obj_15,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_16,obj_16,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_17,obj_17,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_18,obj_18,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fe1bb20cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f3874a74ec0,0,1097200,4096,4096,0,1199653,4096,4096,0,1028773,4096,4096,0,1561528,4096,4096,0,1266742,4096,4096,0,1456356,4096,4096,0,1307832,4096,4096,0,1630491,4096,4096,0,1333695,4096,4096,0,1087211,4096,4096,0,1214691,4096,4096,0,1050612,4096,4096,0,1321283,4096,4096,0,1281606,4096,4096,0,1485071,4096,4096,0,1169175,4096,4096,0,1605275,4096,4096,0,1232186,4096,4096,0,1212127,4096,4096,0,1359730,4096,4096,0,1365995,4096,4096,0,1242651,4096,4096,0,1467441,4096,4096,0,1411604,4096,4096,0,1274583,4096,4096,0,1379246,4096,4096,0,1079984,4096,4096,0,1140860,4096,4096,0,1238929,4096,4096,0,1245134,4096,4096,0,1255696,4096,4096,0,1377782,4096,4096,64,0x7f9e7c560ec0,32768,32768,0,64,0x7f67ef650ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12433,19287,8428,550,0,26694,204653.0,0.0,73573.0,131080.0,64,0x7f1d33dc4ec0,11223900,10020405,859431,344064,1675711,0,0,163840,832.0,515136.0,0.0,524288.0,269911.0,32768.0,519167,0,0,11712,131072.0,131072.0,0.0,131072.0,64,0x7f831b6acec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40613004.0,34430496.0,0.0,64,0x7f8694874ec0,1305,119483,0,0,65536,63800,56,1680,64,0x7f406e490ec0,4096,0,0,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,25,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,134,0,4096,0,352,0,4097,0,0,0,4097,0,17,0,4098,0,0,0,4096,0,0,0,4096,0,4,0,4099,0,0,0,4096,0,0,0,4096,0,120,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f74523b8ec0,6364,0,4096,6418,0,4096,6326,0,4096,6344,0,4096,6356,0,4096,6421,0,4096,6362,0,4096,6376,0,4096,6374,0,4096,6362,0,4096,6419,0,4096,6324,0,4096,6343,0,4096,6364,0,4096,6425,0,4096,6369,0,4096,6387,0,4096,6349,0,4096,6380,0,4096,6410,0,4096,6363,0,4096,6356,0,4096,6382,0,4096,6576,0,4096,6410,0,4096,6390,0,4096,6351,0,4096,6380,0,4096,6412,0,4096,6365,0,4096,6356,0,4096,6381,0,4096,64,0x7f179fe04ec0,0,0,0,944777,0,0,0,984414,0,0,0,1149505,0,0,0,1084910,0,0,0,1159461,0,0,0,1123970,0,0,0,1014104,164,0,0,1262814,0,0,0,1002301,0,0,0,1037667,0,0,0,1039564,0,0,0,1144267,0,0,0,1013199,0,0,0,1143132,0,0,0,1106921,0,0,0,1114293,0,0,0,1145664,0,0,0,987066,0,0,0,989777,0,0,0,1089378,0,0,0,1094827,0,0,0,1128129,0,0,0,1066917,0,0,0,1072102,0,0,0,1056696,0,0,0,1072245,0,0,0,978155,0,0,0,1034294,0,0,0,1018866,0,0,0,1058529,0,0,0,1077004,0,0,0,1163029,64,0x7fd999f10ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,947648.0,64,0x7f569def8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,35137.0,46179.0,19357.0,64,0x7fcc4f2e8ec0,2273,4096,2273,6369,2229,4096,2229,6325,2292,4096,2292,6388,2280,4096,2280,6376,2222,4096,2222,6318,2238,4096,2238,6334,2274,4096,2274,6370,2317,4096,2317,6413,2315,4096,2315,6411,2271,4096,2271,6367,2234,4096,2234,6330,2292,4096,2292,6388,2281,4096,2281,6377,2218,4096,2218,6314,2240,4096,2240,6336,2275,4096,2275,6371,2268,4096,2268,6364,2350,4097,2351,6447,2242,4099,2245,6341,2254,4096,2254,6350,2291,4096,2291,6387,2271,4096,2271,6367,2233,4096,2233,6329,2389,4098,2391,6487,2224,4096,2224,6320,2272,4096,2272,6368,2299,4096,2299,6395,2240,4096,2240,6336,2253,4096,2253,6349,2292,4096,2292,6388,2274,4096,2274,6370,2236,4096,2236,6332,64,0x7fd3b30ccec0,232872,131873,16384,0,16384,16384,32768,49152,29108,29108,1991774.0,1410302.0,3617.0,174286.0,1102732.0,0.0,1402036.0,1103813.0,231161,139992,29108,0,29108,0,931456.0,496992.0,0.0,0.0,64,0x7f1147b28ec0,0,393216,163840,0,0,0,0,0,17968,0.0,0.0,0.0,32768.0,0.0,0.0,383.0,32768.0,4096,16384,352,28036,1892,0,56.0,5.0,0.0,204641.0,64,0x7ffb609c0ec0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,0,28203,0,0,64,0x7fab2506cec0,0,0,0,224,0,65536,64260,56,64,0x7f4b84fe8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,9202,0,814,27754,0,73211.0,131072.0,0.0,65568.0,64,0x7fdfed6d4ec0,114688,0,32768,32768,16384,16384,65536,49152,27679468.0,87536879.0,40795347.0,131072.0,0.0,196124.0,0,0,15278,1812.0,131084.0,0.0,16.0,197327446943430,197327446964070 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_1,obj_1,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_5,obj_5,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_8,obj_8,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_9,obj_9,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_11,obj_11,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_12,obj_12,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_13,obj_13,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_15,obj_15,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_16,obj_16,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_17,obj_17,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_18,obj_18,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fb78b514ec0,232184,132524,16384,0,16384,16384,32768,49152,29022,29022,2000562.0,1355482.0,3486.0,167562.0,1063199.0,0.0,1347853.0,1048239.0,230473,140668,29022,0,29022,0,928704.0,492149.0,0.0,0.0,64,0x7f1bb7d14ec0,0,0,0,224,0,65536,64178,56,64,0x7f3133154ec0,0,0,0,1036117,0,0,0,1094537,36,0,0,1192209,0,0,0,1126731,4,0,0,1118421,0,0,0,1108148,0,0,0,1086341,0,0,0,1207668,84,0,0,1140084,0,0,0,1035818,0,0,0,1010443,0,0,0,1154747,0,0,0,1095875,0,0,0,1067665,0,0,0,1111596,0,0,0,1138316,0,0,0,1058656,0,0,0,1089833,0,0,0,1108959,11,0,0,1193113,0,0,0,1089519,0,0,0,1152319,0,0,0,1155820,69,0,0,1207999,6,0,0,1160926,0,0,0,1072509,0,0,0,1139149,0,0,0,1202594,0,0,0,1100672,0,0,0,1045325,0,0,0,1061840,0,0,0,1202978,64,0x7fe005968ec0,0,393216,163840,0,0,0,0,0,17744,0.0,0.0,0.0,32768.0,0.0,0.0,401.0,32768.0,4096,16384,352,28253,2177,0,56.0,6.0,0.0,203913.0,64,0x7f56adc48ec0,1279,116213,0,0,65536,63800,56,1680,64,0x7ffa55a68ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11862,19486,7948,545,0,26300,204668.0,0.0,73587.0,131081.0,64,0x7f95f2d00ec0,6364,0,4096,6367,0,4096,6360,0,4096,6374,0,4096,6385,0,4096,6447,0,4096,6403,0,4096,6387,0,4096,6387,0,4096,6364,0,4096,6369,0,4096,6363,0,4096,6378,0,4096,6383,0,4096,6446,0,4096,6403,0,4096,6392,0,4096,6407,0,4096,6374,0,4096,6376,0,4096,6372,0,4096,6369,0,4096,6433,0,4096,6554,0,4096,6393,0,4096,6396,0,4096,6409,0,4096,6375,0,4096,6380,0,4096,6375,0,4096,6371,0,4096,6433,0,4096,64,0x7f0ca72ecec0,0,1069921,4096,4096,0,1095589,4096,4096,0,1295193,4096,4096,0,1159427,4096,4096,0,1179417,4096,4096,0,1262126,4096,4096,0,1396144,4096,4096,0,1337395,4096,4096,0,1103274,4096,4096,0,1094250,4096,4096,0,1057064,4096,4096,0,1183053,4096,4096,0,1156049,4096,4096,0,1234524,4096,4096,0,1491640,4096,4096,0,1067587,4096,4096,0,1175568,4096,4096,0,1216253,4096,4096,0,1032202,4096,4096,0,1245920,4096,4096,0,1181607,4096,4096,0,1531794,4096,4096,0,1202416,4096,4096,0,1161356,4096,4096,0,1085599,4096,4096,0,1198413,4096,4096,0,1080975,4096,4096,0,1265200,4096,4096,0,1179958,4096,4096,0,1255183,4096,4096,0,1347116,4096,4096,0,1253605,4096,4096,64,0x7fd648c30ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,81,0,4100,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,180,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,110,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f9944d94ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,9855,0,814,27586,0,73540.0,131072.0,0.0,65568.0,64,0x7efe05d90ec0,114688,0,32768,32768,16384,16384,65536,49152,28139046.0,87412959.0,39538625.0,131072.0,0.0,213739.0,0,0,15398,401.0,131082.0,0.0,12.0,64,0x7fe3a8be8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f2d7f3e8ec0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,0,27657,0,0,64,0x7f6448bc4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39631613.0,34878571.0,0.0,64,0x7f5dea3d8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,977934.0,64,0x7f63dd00cec0,32768,32768,0,64,0x7f4743c18ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,36080.0,46230.0,19306.0,64,0x7fd82ebe8ec0,2266,4096,2266,6362,2295,4096,2295,6391,2312,4096,2312,6408,2338,4096,2338,6434,2268,4096,2268,6364,2308,4096,2308,6404,2303,4096,2303,6399,2300,4096,2300,6396,2305,4096,2305,6401,2265,4096,2265,6361,2301,4096,2301,6397,2368,4097,2369,6465,2338,4096,2338,6434,2270,4096,2270,6366,2306,4096,2306,6402,2303,4096,2303,6399,2266,4100,2270,6366,2334,4096,2334,6430,2286,4097,2287,6383,2312,4096,2312,6408,2286,4096,2286,6382,2346,4096,2346,6442,2307,4096,2307,6403,2433,4098,2435,6531,2268,4096,2268,6364,2267,4096,2267,6363,2338,4096,2338,6434,2292,4096,2292,6388,2320,4096,2320,6416,2288,4096,2288,6384,2347,4096,2347,6443,2305,4096,2305,6401,64,0x7fa2a0168ec0,11196555,9983645,868846,344064,1660641,0,0,163840,832.0,515150.0,0.0,524288.0,289384.0,32768.0,519280,0,0,11031,131072.0,131072.0,0.0,131072.0,1410719177571898,1410719177592538 diff --git a/tests/workloads/dispatch_inv/MI200/roofline.csv b/tests/workloads/dispatch_inv/MI200/roofline.csv index 556e1ee880..efd0420b9a 100644 --- a/tests/workloads/dispatch_inv/MI200/roofline.csv +++ b/tests/workloads/dispatch_inv/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.5352,1387.9612,1389.1091,5015.9067,5012.9795,5018.834,9222.8076,9222.2178,9223.3975,18052.672,18051.719,18053.625,20935.363,20875.119,20995.607,20266.707,20265.77,20267.645,170447.69,170443.23,170452.14,164876.22,164871.3,164881.14,41420.414,41419.844,41420.984,41477.77,41477.254,41478.285,166338.45,165842.38,166834.53 -1,1389.2339,1388.7003,1389.7675,5027.8267,5025.6963,5029.957,9235.0215,9234.4062,9235.6367,18093.281,18089.494,18097.068,20974.221,20906.723,21041.719,20295.463,20294.809,20296.117,170853.08,170848.84,170857.31,165136.75,165133,165140.5,41495.602,41494.711,41496.492,41552.312,41551.637,41552.988,166910.98,166908.33,166913.64 -2,1388.1539,1387.5933,1388.7146,5035.959,5033.6694,5038.2485,9263.0859,9262.3916,9263.7803,18110.701,18109.838,18111.564,21052.15,21051.787,21052.514,20358.631,20358.045,20359.217,171151.48,171147.84,171155.12,165561.08,165557.56,165564.59,41593.766,41592.574,41594.957,41652.289,41651.02,41653.559,167010.91,166416.05,167605.77 -3,1388.6646,1388.1143,1389.2148,5031.4497,5030.1416,5032.7578,9240.3379,9239.8271,9240.8486,18023.123,18019.518,18026.729,21031.461,21031.051,21031.871,20311.738,20311.039,20312.438,171003.95,171001.52,171006.39,165217.39,165214.22,165220.56,41438.289,41279.395,41597.184,41580.961,41580.465,41581.457,167015.88,167013.78,167017.97 +0,1388.9141,1388.3721,1389.4561,5017.4395,5014.228,5020.6509,9226.0234,9225.335,9226.7119,17713.227,17710.121,17716.332,20948.057,20887.705,21008.408,20275.275,20274.727,20275.824,170525.36,170521.61,170529.11,164925.19,164920.83,164929.55,41434.961,41434.453,41435.469,41492.777,41492.191,41493.363,166378.45,165887.44,166869.47 +1,1388.9977,1388.3805,1389.6149,5029.1138,5027.1401,5031.0874,9236.625,9235.9473,9237.3027,18235.252,18234.104,18236.4,20982.668,20915.91,21049.426,20298.568,20298.055,20299.082,170906.36,170901.52,170911.2,165152.56,165148.75,165156.38,41497.047,41496.234,41497.859,41549.789,41548.727,41550.852,166915.34,166911.5,166919.19 +2,1388.4413,1387.9117,1388.9708,5036.0142,5033.8271,5038.2012,9260.9375,9260.2217,9261.6533,18218.748,18217.816,18219.68,21050.432,21049.973,21050.891,20353.637,20353.145,20354.129,171133.27,171129.09,171137.44,165528.48,165525.61,165531.36,41586.836,41585.996,41587.676,41640.574,41639.734,41641.414,166959.62,166363.45,167555.8 +3,1389.6438,1388.9714,1390.3162,5031.4707,5029.8926,5033.0488,9237.8076,9237.0107,9238.6045,18328.922,18328.092,18329.752,21031.645,21031.092,21032.197,20307.449,20306.998,20307.9,171022.23,171016.14,171028.33,165129.09,165124.02,165134.17,41416.918,41262.441,41571.395,41555.602,41554.879,41556.324,166912.22,166909.77,166914.67 diff --git a/tests/workloads/dispatch_inv/MI200/sysinfo.csv b/tests/workloads/dispatch_inv/MI200/sysinfo.csv index 7137cbc9ac..63bd297bf4 100644 --- a/tests/workloads/dispatch_inv/MI200/sysinfo.csv +++ b/tests/workloads/dispatch_inv/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_inv,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 01:59:41 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +dispatch_inv,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:02:53 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/dispatch_inv/MI200/timestamps.csv b/tests/workloads/dispatch_inv/MI200/timestamps.csv index 5aaa68b29b..0d6e53e8cd 100644 --- a/tests/workloads/dispatch_inv/MI200/timestamps.csv +++ b/tests/workloads/dispatch_inv/MI200/timestamps.csv @@ -1,2 +1,2 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,253003,253003,1048576,256,0,0,8,0,16,64,0x0,0x7f70cdd84ec0,197327446918845,197327446943430,197327446964070,197327446982486 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4075570,4075570,1048576,256,0,0,8,0,16,64,0x0,0x7ff93b844ec0,1410719177547494,1410719177571898,1410719177592538,1410719177604342 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/dispatch_invalid/MI100/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index bde2388710..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,2 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,235868,235868,1048576,256,0,0,8,8,16,64,0x0,0x7fa08c19ce80,47992,47992,16384,65536,14610,1850384,194751940599758,194763952869715,194763952893715,194751948360141 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 86c8a94481..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,2 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,236069,236069,1048576,256,0,0,8,8,16,64,0x0,0x7f19a09bee80,0,0,0,194752433427577,194763952869715,194763952893715,194752441182349 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index 99af56290d..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,2 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,236254,236254,1048576,256,0,0,8,8,16,64,0x0,0x7f3dd32c0e80,65536,192118,24640568,194752919496971,194763952869715,194763952893715,194752927094886 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index c54d56d6c4..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,2 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,236454,236454,1048576,256,0,0,8,8,16,64,0x0,0x7f29ec3dce80,32768,665139,85136644,194753406350358,194763952869715,194763952893715,194753414100392 diff --git a/tests/workloads/dispatch_invalid/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/dispatch_invalid/MI100/SQ_LEVEL_WAVES.csv deleted file mode 100644 index d8c91d740c..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,2 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,236656,236656,1048576,256,0,0,8,8,16,64,0x0,0x7fcf4a7b8e80,46920,46920,16723,375368,16384,24359669,227526,0,97931704,194753896286713,194763952869715,194763952893715,194753903968578 diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index e7209bdada..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 67fb5049bc..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 81efe0fd5b..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index bbf5c9dbb7..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 1422b5f0d7..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index 3e26d7a583..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index d1e6a809cc..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_10.txt deleted file mode 100644 index 8e2c2857d8..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_11.txt deleted file mode 100644 index aa172720a9..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_12.txt deleted file mode 100644 index 2ebfdba4b4..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_13.txt deleted file mode 100644 index 595907c8e9..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_14.txt deleted file mode 100644 index 3abef42045..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_15.txt deleted file mode 100644 index 82a4b5dce2..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_16.txt deleted file mode 100644 index 4a07aa911c..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 63514f75ef..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_3.txt deleted file mode 100644 index 09f18f4397..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_4.txt deleted file mode 100644 index 7bf6cb865e..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_5.txt deleted file mode 100644 index 659841f973..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_6.txt deleted file mode 100644 index 40bc861ecc..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_7.txt deleted file mode 100644 index 997395a3ee..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_8.txt deleted file mode 100644 index 224a8eed8a..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_9.txt deleted file mode 100644 index 8a86116b3d..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/perfmon/timestamps.txt b/tests/workloads/dispatch_invalid/MI100/perfmon/timestamps.txt deleted file mode 100644 index 6a128303a2..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: invalid -kernel: diff --git a/tests/workloads/dispatch_invalid/MI100/pmc_dispatch_info.csv b/tests/workloads/dispatch_invalid/MI100/pmc_dispatch_info.csv deleted file mode 100644 index e90d72a8cf..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/pmc_dispatch_info.csv +++ /dev/null @@ -1,2 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/dispatch_invalid/MI100/pmc_perf.csv b/tests/workloads/dispatch_invalid/MI100/pmc_perf.csv deleted file mode 100644 index acccd717d8..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/pmc_perf.csv +++ /dev/null @@ -1,2 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_8,obj_8,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_10,obj_10,TCC_EA_ATOMIC_LEVEL_sum,wave_size_11,obj_11,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_14,obj_14,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_15,obj_15,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_16,obj_16,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f932ed18e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86444.0,44628.0,131111.0,0.0,64,0x7fb884960e80,0,0,192,0,65536,64492,48,1180,32095,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,47886,1649,0,48.0,300.0,0.0,262288.0,64,0x7f70fde78e80,3624,0,0,2027059,1930,0,0,1795507,1572,0,0,1778103,1260,0,0,1670342,2111,0,0,1797791,548,0,0,1501244,7175,0,0,2289519,1730,0,0,1803850,1427,0,0,1777066,969,0,0,1766055,2674,0,0,1936612,1751,0,0,1738916,1684,0,0,1802919,1370,0,0,1808370,3044,0,0,2014769,5489,0,0,2245401,3806,0,0,1970282,1450,0,0,1735832,2352,0,0,1934472,1168,0,0,1645610,2176,0,0,1855537,1892,0,0,1897209,2248,0,0,1867928,753,0,0,1588095,1643,0,0,1740035,939,0,0,1674593,2460,0,0,1827118,4250,0,0,1965289,1759,0,0,1818903,1223,0,0,1672257,2870,0,0,1929807,1965,0,0,1814369,64,0x7f9c67a96e80,32768,0,0,0,16384,16384,393216,22905363,960.0,513925.0,0.0,524288.0,949484.0,32768.0,0,0,0,17834,131072.0,131072.0,0.0,131072.0,64,0x7f9bc4660e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,47,8193,4144,8240,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f5d76cace80,131072.0,131072.0,0.0,2560703.0,0.0,0.0,126347271.0,63177897.0,64,0x7fd1e44dae80,4096,0,1265,0,4096,0,2988,0,4096,0,1992,0,4096,0,0,0,4096,0,5957,0,4096,0,415,0,4096,0,2908,0,4096,0,699,0,4096,0,1312,0,4096,0,4511,0,4351,0,3263,0,4147,0,584,0,4096,0,869,0,4097,0,236,0,4096,0,5208,0,4096,0,6002,0,4096,0,2293,0,4096,0,2183,0,4144,0,1370,0,4096,0,0,0,4096,0,1145,0,4096,0,417,0,4096,0,444,0,4096,0,0,0,4096,0,496,0,4096,0,1350,0,4096,0,2558,0,4096,0,49,0,4096,0,233,0,4096,0,0,0,4096,0,690,0,4096,0,0,0,64,0x7f65d5404e80,381968,234772,3430126,16384,25372852,144,48,0,47745,47745,3874301.0,3047202.0,5817.0,1076068.0,2188474.0,0.0,3037288.0,2725229.0,380255,244700,47745,0,47745,0,1527840.0,976120.0,0.0,0.0,64,0x7fecc7b96e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131298.0,0.0,444.0,131297.0,64,0x7fb9d7a3ce80,1625171,360448,163840,0,0,180224,114688,0,68823734.0,192270368.0,77516831.0,131072.0,0.0,695444.0,0,0,26431,142095.0,0.0,0.0,142095.0,64,0x7fed1c430e80,0.0,64,0x7f60d8a64e80,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,0,47839,0,0,64,0x7f518cfa4e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,82342.0,163167.0,64,0x7fc1e78c4e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48080,0,131535.0,131072.0,0.0,131104.0,64,0x7feb37616e80,0,3839398,4096,4096,0,3265058,4096,4096,0,4015402,4096,4096,0,3097596,4096,4096,0,3637199,4096,4096,0,3361265,4096,4096,0,3873696,4096,4096,0,3228194,4096,4096,0,4071125,4096,4096,0,4435600,4096,4096,0,3367730,4096,4096,0,3651688,4096,4096,0,3546183,4096,4096,0,3641431,4096,4096,0,4158548,4096,4096,0,2914552,4096,4096,0,5315537,4096,4096,0,4008013,4096,4096,0,4215771,4096,4096,0,3301663,4096,4096,0,4636662,4096,4096,0,3650563,4096,4096,0,4564222,4096,4096,0,2891708,4096,4096,0,4190911,4096,4096,0,3226044,4096,4096,0,4150036,4096,4096,0,2861234,4096,4096,0,3815145,4096,4096,0,3534716,4096,4096,0,4072909,4096,4096,0,5085333,4096,4096,64,0x7fdd88ad4e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fa998a84e80,116195,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13502,29886,9653,550,0,46167,262600.0,0.0,188.0,262412.0,194763952869715,194763952893715 diff --git a/tests/workloads/dispatch_invalid/MI100/timestamps.csv b/tests/workloads/dispatch_invalid/MI100/timestamps.csv deleted file mode 100644 index 596ddc5950..0000000000 --- a/tests/workloads/dispatch_invalid/MI100/timestamps.csv +++ /dev/null @@ -1,2 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,240105,240105,1048576,256,0,0,8,8,16,64,0x0,0x7f43ccdc4e80,194763952839587,194763952869715,194763952893715,194763952904830 diff --git a/tests/workloads/ipblocks_CPC/MI100/log.txt b/tests/workloads/ipblocks_CPC/MI100/log.txt new file mode 100644 index 0000000000..620c970fd7 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI100/log.txt @@ -0,0 +1,215 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_CPC/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['cpc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155348' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155348_1257160' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155348_1257160/input0_results_240321_155348' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155348_1257160/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155348_1257160/input0_results_240321_155348 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155349' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155349_1257344' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155349_1257344/input0_results_240321_155349' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155349_1257344/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155349_1257344/input0_results_240321_155349 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155349' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155349_1257535' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155349_1257535/input0_results_240321_155349' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155349_1257535/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155349_1257535/input0_results_240321_155349 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155350' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155350_1257718' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155350_1257718/input0_results_240321_155350' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155350_1257718/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155350_1257718/input0_results_240321_155350 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155350' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155350_1257901' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155350_1257901/input0_results_240321_155350' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155350_1257901/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155350_1257901/input0_results_240321_155350 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155351' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155351_1258084' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155351_1258084/input0_results_240321_155351' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155351_1258084/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] CPC_ME1_DC0_SPI_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155351_1258084/input0_results_240321_155351 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155351' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155351_1258267' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155351_1258267/input0_results_240321_155351' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155351_1258267/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155351_1258267/input0_results_240321_155351 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_CPC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_CPC/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_CPC/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_CPC/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv index c312e5c0fc..d047126545 100644 --- a/tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_CPC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_1,obj_1,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_2,obj_2,CPC_ME1_DC0_SPI_BUSY,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_4,obj_4,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_5,obj_5,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff316284e80,0,18032,64,0x7f4d85fa8e80,538,47251,64,0x7f887490ee80,25840,64,0x7fd18aa26e80,383384,233291,16384,47922,47922,47922,0,64,0x7f0b8a080e80,913,47882,64,0x7f7df1112e80,9974,550,194244245026424,194244245050584 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff316284e80,0,13536,64,0x7f4d85fa8e80,456,42172,64,0x7f887490ee80,25547,64,0x7fd18aa26e80,338240,231210,16384,42279,42279,42279,0,64,0x7f0b8a080e80,3255,39736,64,0x7f7df1112e80,8663,2404,194244245150904,194244245169784 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7ff316284e80,0,13950,64,0x7f4d85fa8e80,455,41957,64,0x7f887490ee80,25075,64,0x7fd18aa26e80,336192,231870,16384,42023,42023,42023,0,64,0x7f0b8a080e80,3266,39317,64,0x7f7df1112e80,8698,2399,194244245191704,194244245210584 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPC_ME1_DC0_SPI_BUSY,wave_size_1,obj_1,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_2,obj_2,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_3,obj_3,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_5,obj_5,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f26c8f68ec0,27244,64,0x7fa844184ec0,9992,588,64,0x7f4adfb18ec0,537,48439,64,0x7ff2f49f8ec0,0,17224,64,0x7f9ff7938ec0,399896,240199,16384,49986,49986,49986,0,64,0x7fe035960ec0,913,48249,1410165736116474,1410165736140474 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f26c8f68ec0,25766,64,0x7fa844184ec0,8593,1517,64,0x7f4adfb18ec0,457,43849,64,0x7ff2f49f8ec0,0,14005,64,0x7f9ff7938ec0,345064,232450,16384,43132,43132,43132,0,64,0x7fe035960ec0,2781,39820,1410165736234714,1410165736253594 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f26c8f68ec0,25829,64,0x7fa844184ec0,8625,1501,64,0x7f4adfb18ec0,457,42576,64,0x7ff2f49f8ec0,0,13513,64,0x7f9ff7938ec0,352280,240643,16384,44034,44034,44034,0,64,0x7fe035960ec0,2740,41163,1410165736274074,1410165736293114 diff --git a/tests/workloads/ipblocks_CPC/MI100/sysinfo.csv b/tests/workloads/ipblocks_CPC/MI100/sysinfo.csv index b90598d910..02ac37cca6 100644 --- a/tests/workloads/ipblocks_CPC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_CPC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,cpc,Thu 07 Mar 2024 01:08:26 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,cpc,Thu 21 Mar 2024 03:53:48 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_CPC/MI100/timestamps.csv b/tests/workloads/ipblocks_CPC/MI100/timestamps.csv index 931b9903c4..88e6f785f9 100644 --- a/tests/workloads/ipblocks_CPC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_CPC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,162824,162824,1048576,256,0,0,8,8,16,64,0x0,0x7f59dfa84e80,194244245000970,194244245026424,194244245050584,194244245063608 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,162824,162824,1048576,256,0,0,8,8,16,64,0x0,0x7f59dfa84e80,194244245063318,194244245150904,194244245169784,194244245171282 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,162824,162824,1048576,256,0,0,8,8,16,64,0x0,0x7f59dfa84e80,194244245182744,194244245191704,194244245210584,194244245211729 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1258427,1258427,1048576,256,0,0,8,8,16,64,0x0,0x7fb625d78ec0,1410165736090823,1410165736116474,1410165736140474,1410165736152099 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1258427,1258427,1048576,256,0,0,8,8,16,64,0x0,0x7fb625d78ec0,1410165736153431,1410165736234714,1410165736253594,1410165736255003 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1258427,1258427,1048576,256,0,0,8,8,16,64,0x0,0x7fb625d78ec0,1410165736265723,1410165736274074,1410165736293114,1410165736294337 diff --git a/tests/workloads/ipblocks_CPC/MI200/log.txt b/tests/workloads/ipblocks_CPC/MI200/log.txt new file mode 100644 index 0000000000..7c74562363 --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/log.txt @@ -0,0 +1,217 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_CPC/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['cpc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_163221' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163221_4142988' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163221_4142988/input0_results_240321_163221' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163221_4142988/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163221_4142988/input0_results_240321_163221 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_163221' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163221_4143189' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163221_4143189/input0_results_240321_163221' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163221_4143189/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163221_4143189/input0_results_240321_163221 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_163222' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163222_4143377' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163222_4143377/input0_results_240321_163222' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163222_4143377/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163222_4143377/input0_results_240321_163222 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_163222' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163222_4143561' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163222_4143561/input0_results_240321_163222' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163222_4143561/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163222_4143561/input0_results_240321_163222 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_163223' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163223_4143763' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163223_4143763/input0_results_240321_163223' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163223_4143763/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163223_4143763/input0_results_240321_163223 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_163223' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163223_4143964' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163223_4143964/input0_results_240321_163223' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163223_4143964/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] CPC_ME1_DC0_SPI_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163223_4143964/input0_results_240321_163223 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPC/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_163224' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPC/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163224_4144164' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163224_4144164/input0_results_240321_163224' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163224_4144164/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163224_4144164/input0_results_240321_163224 + |-> [rocprof] File 'tests/workloads/ipblocks_CPC/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_CPC/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_CPC/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_CPC/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_CPC/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv index d488a210b4..744ae00113 100644 --- a/tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_CPC/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_2,obj_2,CPC_ME1_DC0_SPI_BUSY,wave_size_3,obj_3,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_4,obj_4,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_5,obj_5,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7b5b620ec0,7061,549,64,0x7f34dac88ec0,220344,128760,16384,27542,27542,27542,0,64,0x7f1388c50ec0,16121,64,0x7f2e75dd8ec0,352,27046,64,0x7fa7ccc7cec0,814,26808,64,0x7f8a762b0ec0,0,11071,198895939495862,198895939516022 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7b5b620ec0,9533,2476,64,0x7f34dac88ec0,332232,225531,16384,41528,41528,41528,0,64,0x7f1388c50ec0,25649,64,0x7f2e75dd8ec0,302,42817,64,0x7fa7ccc7cec0,2628,39892,64,0x7f8a762b0ec0,0,14417,198895939535222,198895939551062 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7b5b620ec0,9545,2467,64,0x7f34dac88ec0,330008,224905,16384,41250,41250,41250,0,64,0x7f1388c50ec0,26412,64,0x7f2e75dd8ec0,302,41569,64,0x7fa7ccc7cec0,2652,39346,64,0x7f8a762b0ec0,0,13685,198895939606582,198895939622742 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_1,obj_1,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_2,obj_2,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_3,obj_3,CPC_ME1_DC0_SPI_BUSY,wave_size_4,obj_4,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa0ac0f4ec0,7126,545,64,0x7fcff6cd4ec0,352,27629,64,0x7fbd1ab90ec0,0,11028,64,0x7f5ce8ae4ec0,14761,64,0x7f1ccc82cec0,814,27458,64,0x7f942b880ec0,222064,128814,16384,27757,27757,27757,0,1412476247039736,1412476247059896 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa0ac0f4ec0,9627,1447,64,0x7fcff6cd4ec0,302,40476,64,0x7fbd1ab90ec0,0,12941,64,0x7f5ce8ae4ec0,24736,64,0x7f1ccc82cec0,2702,38485,64,0x7f942b880ec0,335104,230810,16384,41887,41887,41887,0,1412476247079416,1412476247094776 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa0ac0f4ec0,9620,1449,64,0x7fcff6cd4ec0,302,39970,64,0x7fbd1ab90ec0,0,13086,64,0x7f5ce8ae4ec0,25487,64,0x7f1ccc82cec0,2691,38569,64,0x7f942b880ec0,333584,232998,16384,41697,41697,41697,0,1412476247159896,1412476247176376 diff --git a/tests/workloads/ipblocks_CPC/MI200/roofline.csv b/tests/workloads/ipblocks_CPC/MI200/roofline.csv index 9faaaeff5b..396f72f1d7 100644 --- a/tests/workloads/ipblocks_CPC/MI200/roofline.csv +++ b/tests/workloads/ipblocks_CPC/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.0835,1388.5491,1389.6179,5013.0107,5010.002,5016.0195,9220.1738,9219.5938,9220.7539,18045.086,18044.184,18045.988,20923.201,20862.568,20983.834,20256.529,20255.801,20257.258,170333.5,170329.88,170337.12,164808.95,164805.06,164812.84,41402.754,41402.188,41403.32,41460.305,41459.68,41460.93,166272.33,165780.62,166764.03 -1,1389.6497,1389.1088,1390.1906,5027.5049,5025.3521,5029.6577,9230.7354,9230.0459,9231.4248,18088.08,18084.049,18092.111,20970.324,20903.604,21037.045,20290.588,20290.08,20291.096,170824.3,170819.86,170828.73,165087.86,165084.22,165091.5,41482.344,41481.582,41483.105,41541.422,41540.449,41542.395,166888.75,166885.91,166891.59 -2,1388.6713,1388.0886,1389.2539,5035.397,5033.2314,5037.5625,9258.9023,9258.1445,9259.6602,18103.68,18102.697,18104.662,21045.385,21044.947,21045.822,20346.889,20346.314,20347.463,171077.52,171073.62,171081.41,165468.52,165464.36,165472.67,41573.086,41571.988,41574.184,41629.473,41628.504,41630.441,166937.44,166346.31,167528.56 -3,1388.4886,1387.973,1389.0043,5032.6201,5031.2354,5034.0049,9240.5059,9239.9424,9241.0693,18025.992,18022.287,18029.697,21037.256,21036.428,21038.084,20312.686,20312.051,20313.32,171059.08,171053,171065.16,165231.14,165224.91,165237.38,41435.23,41273.004,41597.457,41580.984,41580.523,41581.445,167021.8,167019.53,167024.06 +0,1389.0884,1388.5453,1389.6315,5017.8765,5014.9863,5020.7666,9227.8506,9227.083,9228.6182,17716.215,17713.145,17719.285,20946.453,20886.109,21006.797,20275.99,20275.48,20276.5,170538.34,170535.03,170541.66,164943.27,164938.83,164947.7,41438.703,41438.082,41439.324,41493.109,41492.445,41493.773,166411.69,165919.97,166903.41 +1,1389.5769,1388.9772,1390.1766,5028.1221,5025.9307,5030.3135,9232.9844,9232.3828,9233.5859,18229.717,18227.943,18231.49,20972.973,20906.303,21039.643,20292.105,20291.439,20292.771,170805.23,170801.34,170809.12,165081.27,165077.09,165085.44,41478.801,41478.168,41479.434,41535.371,41534.641,41536.102,166847.2,166844.67,166849.73 +2,1388.7632,1388.2323,1389.2941,5037.6533,5035.4893,5039.8174,9261.7959,9261.0645,9262.5273,18219.971,18218.975,18220.967,21055.248,21054.838,21055.658,20357.908,20357.379,20358.438,171163.77,171160.05,171167.48,165547.56,165542.89,165552.23,41593.344,41592.41,41594.277,41654.23,41653.16,41655.301,167004.84,166413.62,167596.06 +3,1389.2833,1388.6674,1389.8993,5034.1963,5032.6582,5035.7344,9238.5703,9237.8506,9239.29,18331.064,18330.256,18331.873,21034.537,21034.311,21034.764,20310.283,20309.748,20310.818,171032.86,171028.69,171037.03,165152.52,165148.45,165156.58,41426.637,41272.566,41580.707,41566.5,41565.137,41567.863,166953.94,166949.55,166958.33 diff --git a/tests/workloads/ipblocks_CPC/MI200/sysinfo.csv b/tests/workloads/ipblocks_CPC/MI200/sysinfo.csv index c047bef687..923b77ce74 100644 --- a/tests/workloads/ipblocks_CPC/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_CPC/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_CPC,./sample/vcopy -n 1048576 -b 256 -i 3,cpc|roofline,Thu 07 Mar 2024 02:26:00 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,cpc|roofline,Thu 21 Mar 2024 04:32:20 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_CPC/MI200/timestamps.csv b/tests/workloads/ipblocks_CPC/MI200/timestamps.csv index 8c99cef564..69e7faef7b 100644 --- a/tests/workloads/ipblocks_CPC/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_CPC/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,319954,319954,1048576,256,0,0,8,0,16,64,0x0,0x7fea700a8ec0,198895939470975,198895939495862,198895939516022,198895939529786 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,319954,319954,1048576,256,0,0,8,0,16,64,0x0,0x7fea700a8ec0,198895939527111,198895939535222,198895939551062,198895939604708 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,319954,319954,1048576,256,0,0,8,0,16,64,0x0,0x7fea700a8ec0,198895939561627,198895939606582,198895939622742,198895939623964 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4144324,4144324,1048576,256,0,0,8,0,16,64,0x0,0x7f15a0ac4ec0,1412476247014679,1412476247039736,1412476247059896,1412476247073571 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4144324,4144324,1048576,256,0,0,8,0,16,64,0x0,0x7f15a0ac4ec0,1412476247070976,1412476247079416,1412476247094776,1412476247156397 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4144324,4144324,1048576,256,0,0,8,0,16,64,0x0,0x7f15a0ac4ec0,1412476247105210,1412476247159896,1412476247176376,1412476247177277 diff --git a/tests/workloads/ipblocks_CPF/MI100/log.txt b/tests/workloads/ipblocks_CPF/MI100/log.txt new file mode 100644 index 0000000000..de2ee268f0 --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI100/log.txt @@ -0,0 +1,157 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_CPF/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['cpf'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155345' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155345_1256135' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155345_1256135/input0_results_240321_155345' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155345_1256135/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, GRBM_COUNT, GRBM_GUI_ACTIVE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155345_1256135/input0_results_240321_155345 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155346' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155346_1256319' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155346_1256319/input0_results_240321_155346' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155346_1256319/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155346_1256319/input0_results_240321_155346 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155346' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155346_1256503' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155346_1256503/input0_results_240321_155346' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155346_1256503/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155346_1256503/input0_results_240321_155346 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155347' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155347_1256704' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155347_1256704/input0_results_240321_155347' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155347_1256704/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] CPF_CMP_UTCL1_STALL_ON_TRANSLATION + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155347_1256704/input0_results_240321_155347 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155347' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155347_1256887' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155347_1256887/input0_results_240321_155347' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155347_1256887/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155347_1256887/input0_results_240321_155347 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_CPF/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_CPF/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_CPF/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_CPF/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv b/tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv index f1740ac568..752498aebe 100644 --- a/tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_CPF/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,wave_size_1,obj_1,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,wave_size_2,obj_2,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,wave_size_3,obj_3,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5b9070ee80,384264,232290,16384,48032,48032,48032,0,64,0x7f4350c04e80,0,47628,64,0x7f4004e74e80,1262,0,64,0x7fca1214ce80,0,194239843235063,194239843259383 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5b9070ee80,313216,216625,16384,39151,39151,39151,0,64,0x7f4350c04e80,0,41835,64,0x7f4004e74e80,1310,0,64,0x7fca1214ce80,0,194239843423223,194239843442103 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5b9070ee80,307328,212139,16384,38415,38415,38415,0,64,0x7f4350c04e80,0,42075,64,0x7f4004e74e80,1278,0,64,0x7fca1214ce80,0,194239843463863,194239843482903 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,wave_size_1,obj_1,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,wave_size_3,obj_3,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f25d5c04ec0,2672,0,64,0x7fe9ddae4ec0,0,64,0x7f23573e8ec0,393504,242831,16384,49187,49187,49187,0,64,0x7f9917344ec0,0,47793,1410161514175118,1410161514198958 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f25d5c04ec0,1329,0,64,0x7fe9ddae4ec0,0,64,0x7f23573e8ec0,352856,243644,16384,44106,44106,44106,0,64,0x7f9917344ec0,0,42843,1410161514289038,1410161514307918 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f25d5c04ec0,1294,0,64,0x7fe9ddae4ec0,0,64,0x7f23573e8ec0,347160,236186,16384,43394,43394,43394,0,64,0x7f9917344ec0,0,42099,1410161514328398,1410161514347118 diff --git a/tests/workloads/ipblocks_CPF/MI100/sysinfo.csv b/tests/workloads/ipblocks_CPF/MI100/sysinfo.csv index 0db40d9513..d457074075 100644 --- a/tests/workloads/ipblocks_CPF/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_CPF/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,cpf,Thu 07 Mar 2024 01:08:22 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,cpf,Thu 21 Mar 2024 03:53:45 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_CPF/MI100/timestamps.csv b/tests/workloads/ipblocks_CPF/MI100/timestamps.csv index a0e0a3e8c8..0d3a5a3b9e 100644 --- a/tests/workloads/ipblocks_CPF/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_CPF/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,161422,161422,1048576,256,0,0,8,8,16,64,0x0,0x7f152d9b8e80,194239843210061,194239843235063,194239843259383,194239843271157 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,161422,161422,1048576,256,0,0,8,8,16,64,0x0,0x7f152d9b8e80,194239843272410,194239843423223,194239843442103,194239843443864 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,161422,161422,1048576,256,0,0,8,8,16,64,0x0,0x7f152d9b8e80,194239843454464,194239843463863,194239843482903,194239843484351 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1257047,1257047,1048576,256,0,0,8,8,16,64,0x0,0x7fa7973d8ec0,1410161514147450,1410161514175118,1410161514198958,1410161514212272 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1257047,1257047,1048576,256,0,0,8,8,16,64,0x0,0x7fa7973d8ec0,1410161514211190,1410161514289038,1410161514307918,1410161514309275 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1257047,1257047,1048576,256,0,0,8,8,16,64,0x0,0x7fa7973d8ec0,1410161514320256,1410161514328398,1410161514347118,1410161514348519 diff --git a/tests/workloads/ipblocks_CPF/MI200/log.txt b/tests/workloads/ipblocks_CPF/MI200/log.txt new file mode 100644 index 0000000000..11f409b893 --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/log.txt @@ -0,0 +1,159 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_CPF/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['cpf'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_163046' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163046_4141852' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163046_4141852/input0_results_240321_163046' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163046_4141852/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, GRBM_COUNT, GRBM_GUI_ACTIVE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163046_4141852/input0_results_240321_163046 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_163046' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163046_4142035' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163046_4142035/input0_results_240321_163046' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163046_4142035/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163046_4142035/input0_results_240321_163046 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_163047' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163047_4142236' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163047_4142236/input0_results_240321_163047' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163047_4142236/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163047_4142236/input0_results_240321_163047 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_163047' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163047_4142424' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163047_4142424/input0_results_240321_163047' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163047_4142424/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] CPF_CMP_UTCL1_STALL_ON_TRANSLATION + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163047_4142424/input0_results_240321_163047 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_CPF/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_163047' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_CPF/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163047_4142622' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163047_4142622/input0_results_240321_163047' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163047_4142622/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163047_4142622/input0_results_240321_163047 + |-> [rocprof] File 'tests/workloads/ipblocks_CPF/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_CPF/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_CPF/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_CPF/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_CPF/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv b/tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv index bef8a4a588..0e895b159d 100644 --- a/tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_CPF/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,wave_size_2,obj_2,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,wave_size_3,obj_3,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7c305a4ec0,0,64,0x7f5ee8368ec0,218152,127865,16384,27268,27268,27268,0,64,0x7f820dfc0ec0,873,0,64,0x7fd9c8d68ec0,0,26928,198799859549427,198799859569907 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7c305a4ec0,0,64,0x7f5ee8368ec0,319392,221459,16384,39923,39923,39923,0,64,0x7f820dfc0ec0,1600,0,64,0x7fd9c8d68ec0,0,40230,198799859589747,198799859605587 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7c305a4ec0,0,64,0x7f5ee8368ec0,318480,219809,16384,39809,39809,39809,0,64,0x7f820dfc0ec0,1622,0,64,0x7fd9c8d68ec0,0,39292,198799859659827,198799859676147 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,wave_size_1,obj_1,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,wave_size_3,obj_3,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f20155d8ec0,0,64,0x7fede7368ec0,0,26715,64,0x7f969a720ec0,223480,130048,16384,27934,27934,27934,0,64,0x7f75253e8ec0,840,0,1412380193915065,1412380193935385 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f20155d8ec0,0,64,0x7fede7368ec0,0,39712,64,0x7f969a720ec0,331624,226566,16384,41452,41452,41452,0,64,0x7f75253e8ec0,1585,0,1412380193954585,1412380193970425 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f20155d8ec0,0,64,0x7fede7368ec0,0,39948,64,0x7f969a720ec0,328776,221084,16384,41096,41096,41096,0,64,0x7f75253e8ec0,1585,0,1412380194024985,1412380194041145 diff --git a/tests/workloads/ipblocks_CPF/MI200/roofline.csv b/tests/workloads/ipblocks_CPF/MI200/roofline.csv index 0d4f131c18..e7eb6c279c 100644 --- a/tests/workloads/ipblocks_CPF/MI200/roofline.csv +++ b/tests/workloads/ipblocks_CPF/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.7466,1388.1986,1389.2946,5014.8066,5011.9419,5017.6714,9225.3555,9224.6377,9226.0732,18055.795,18054.943,18056.646,20937.562,20876.969,20998.156,20264.434,20263.588,20265.279,170425.69,170421.42,170429.95,164873.91,164868.66,164879.16,41419.789,41419.301,41420.277,41477.148,41476.148,41478.148,166317.8,165829.28,166806.31 -1,1389.0984,1388.5691,1389.6277,5028.8921,5027.0518,5030.7324,9235.1348,9234.4424,9235.8271,18099.438,18094.338,18104.537,20974.891,20908.201,21041.58,20295.033,20294.365,20295.701,170832.44,170829.27,170835.61,165091.3,165087.86,165094.73,41479.668,41478.977,41480.359,41534.102,41533.008,41535.195,166847.27,166844.38,166850.16 -2,1389.2231,1388.6008,1389.8455,5035.1265,5032.791,5037.4619,9260.9941,9260.3633,9261.625,18105.355,18104.672,18106.039,21044.99,21044.596,21045.385,20348.387,20347.891,20348.883,171090.92,171086.39,171095.45,165474.55,165470.22,165478.88,41575.297,41574.309,41576.285,41629.754,41628.738,41630.77,166909.95,166320.81,167499.09 -3,1388.8466,1388.299,1389.3942,5031.3447,5029.9229,5032.7666,9240.5459,9239.9502,9241.1416,18025.242,18021.904,18028.58,21033.998,21033.4,21034.596,20311.389,20310.717,20312.061,171009.09,171004.06,171014.12,165229.42,165225.45,165233.39,41444.457,41290.074,41598.84,41585.707,41585.25,41586.164,167035.59,167033.86,167037.33 +0,1389.1534,1388.4714,1389.8354,5018.3794,5015.4609,5021.2979,9228.5664,9228.0088,9229.124,17721.293,17718.41,17724.176,20945.578,20885.205,21005.951,20273.395,20272.682,20274.107,170502.2,170499.06,170505.34,164922.83,164919.06,164926.59,41438.156,41437.648,41438.664,41496.379,41495.773,41496.984,166392.47,165897.34,166887.59 +1,1389.4541,1388.8754,1390.0328,5028.895,5026.8662,5030.9238,9235.7529,9235.0195,9236.4863,18234.283,18232.305,18236.262,20980.355,20913.15,21047.561,20297.268,20296.75,20297.785,170863.92,170859.95,170867.89,165115.69,165111.22,165120.16,41489.91,41488.992,41490.828,41540.152,41539.473,41540.832,166875.67,166872.88,166878.47 +2,1388.239,1387.7046,1388.7734,5036.7676,5034.5942,5038.9409,9261.8691,9261.2012,9262.5371,18218.227,18217.342,18219.111,21052.92,21052.293,21053.547,20354.873,20354.258,20355.488,171164.81,171158.64,171170.98,165559,165555.25,165562.75,41590.734,41589.809,41591.66,41651.711,41650.637,41652.785,166999.31,166405.95,167592.67 +3,1389.7377,1389.1644,1390.3109,5032.1274,5030.5596,5033.6953,9234.5498,9233.7832,9235.3164,18322.113,18321.26,18322.967,21026.182,21025.814,21026.549,20301.002,20300.465,20301.539,170947.27,170944.02,170950.52,165083.67,165078.75,165088.59,41405.027,41251.172,41558.883,41545.441,41544.66,41546.223,166912.02,166907.78,166916.25 diff --git a/tests/workloads/ipblocks_CPF/MI200/sysinfo.csv b/tests/workloads/ipblocks_CPF/MI200/sysinfo.csv index a28721cb0e..cc4e1a516a 100644 --- a/tests/workloads/ipblocks_CPF/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_CPF/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_CPF,./sample/vcopy -n 1048576 -b 256 -i 3,cpf|roofline,Thu 07 Mar 2024 02:24:25 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,cpf|roofline,Thu 21 Mar 2024 04:30:45 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_CPF/MI200/timestamps.csv b/tests/workloads/ipblocks_CPF/MI200/timestamps.csv index b05a9a13c8..27d6da500c 100644 --- a/tests/workloads/ipblocks_CPF/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_CPF/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,318314,318314,1048576,256,0,0,8,0,16,64,0x0,0x7f2c64ab0ec0,198799859525291,198799859549427,198799859569907,198799859583632 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,318314,318314,1048576,256,0,0,8,0,16,64,0x0,0x7f2c64ab0ec0,198799859580946,198799859589747,198799859605587,198799859655908 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,318314,318314,1048576,256,0,0,8,0,16,64,0x0,0x7f2c64ab0ec0,198799859615842,198799859659827,198799859676147,198799859677038 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4142782,4142782,1048576,256,0,0,8,0,16,64,0x0,0x7fbb56b10ec0,1412380193889768,1412380193915065,1412380193935385,1412380193948920 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4142782,4142782,1048576,256,0,0,8,0,16,64,0x0,0x7fbb56b10ec0,1412380193946355,1412380193954585,1412380193970425,1412380194021547 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4142782,4142782,1048576,256,0,0,8,0,16,64,0x0,0x7fbb56b10ec0,1412380193980710,1412380194024985,1412380194041145,1412380194042336 diff --git a/tests/workloads/ipblocks_SPI/MI100/log.txt b/tests/workloads/ipblocks_SPI/MI100/log.txt new file mode 100644 index 0000000000..c2c323e363 --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI100/log.txt @@ -0,0 +1,302 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SPI/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['spi'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155516' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155516_1285210' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155516_1285210/input0_results_240321_155516' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155516_1285210/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, GRBM_COUNT, GRBM_GUI_ACTIVE, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155516_1285210/input0_results_240321_155516 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155516' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155516_1285393' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155516_1285393/input0_results_240321_155516' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155516_1285393/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] GRBM_SPI_BUSY, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155516_1285393/input0_results_240321_155516 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155517' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155517_1285576' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155517_1285576/input0_results_240321_155517' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155517_1285576/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155517_1285576/input0_results_240321_155517 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155517' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155517_1285763' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155517_1285763/input0_results_240321_155517' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155517_1285763/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155517_1285763/input0_results_240321_155517 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155518' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155518_1285952' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155518_1285952/input0_results_240321_155518' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155518_1285952/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155518_1285952/input0_results_240321_155518 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155518' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155518_1286137' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155518_1286137/input0_results_240321_155518' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155518_1286137/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155518_1286137/input0_results_240321_155518 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155518' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155518_1286320' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155518_1286320/input0_results_240321_155518' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155518_1286320/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155518_1286320/input0_results_240321_155518 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155519' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155519_1286503' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155519_1286503/input0_results_240321_155519' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155519_1286503/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155519_1286503/input0_results_240321_155519 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155519' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155519_1286686' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155519_1286686/input0_results_240321_155519' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155519_1286686/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155519_1286686/input0_results_240321_155519 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155520' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155520_1286870' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155520_1286870/input0_results_240321_155520' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155520_1286870/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155520_1286870/input0_results_240321_155520 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_SPI/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SPI/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_SPI/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_SPI/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv index 1ee8ee9d54..82eb6fb152 100644 --- a/tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SPI/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_1,obj_1,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_2,obj_2,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_4,obj_4,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_5,obj_5,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_6,obj_6,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_7,obj_7,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_8,obj_8,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3acecb2e80,0,0,64,0x7f05f5c54e80,16384,0,64,0x7f2e42c44e80,31956,4096,16384,64,0x7f7994d1ae80,381736,231428,16384,47716,47716,380023,241372,64,0x7f775c162e80,0,0,64,0x7fb00f7d2e80,0,0,64,0x7f2008b14e80,0,81920,64,0x7fd452f12e80,13179,29563,64,0x7f657ac3ae80,0,0,194434963621537,194434963646337 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3acecb2e80,0,0,64,0x7f05f5c54e80,16384,0,64,0x7f2e42c44e80,30474,4096,16384,64,0x7f7994d1ae80,342736,228907,16384,42841,42841,342728,238673,64,0x7f775c162e80,0,0,64,0x7fb00f7d2e80,0,0,64,0x7f2008b14e80,0,81920,64,0x7fd452f12e80,12801,29185,64,0x7f657ac3ae80,0,0,194434963736257,194434963754977 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f3acecb2e80,0,0,64,0x7f05f5c54e80,16384,0,64,0x7f2e42c44e80,30469,4096,16384,64,0x7f7994d1ae80,339216,227589,16384,42401,42401,339208,237363,64,0x7f775c162e80,0,0,64,0x7fb00f7d2e80,0,0,64,0x7f2008b14e80,0,81920,64,0x7fd452f12e80,11173,27557,64,0x7f657ac3ae80,0,0,194434963776577,194434963795777 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_1,obj_1,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_2,obj_2,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_3,obj_3,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_5,obj_5,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_6,obj_6,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_7,obj_7,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_8,obj_8,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f49669d8ec0,0,0,64,0x7f807dc40ec0,10699,27083,64,0x7f5096bc8ec0,16384,0,64,0x7f9bcce44ec0,0,81920,64,0x7f4da03c0ec0,386736,236385,16384,48341,48341,385023,246338,64,0x7f9e0bfd0ec0,0,0,64,0x7f5be16a0ec0,0,0,64,0x7f3888a9cec0,31700,4096,16384,64,0x7f3bba1bcec0,0,0,1410254377530050,1410254377555170 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f49669d8ec0,0,0,64,0x7f807dc40ec0,12902,29286,64,0x7f5096bc8ec0,16384,0,64,0x7f9bcce44ec0,0,81920,64,0x7f4da03c0ec0,338048,229455,16384,42255,42255,338040,239237,64,0x7f9e0bfd0ec0,0,0,64,0x7f5be16a0ec0,0,0,64,0x7f3888a9cec0,31493,4096,16384,64,0x7f3bba1bcec0,0,0,1410254377653250,1410254377672290 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f49669d8ec0,0,0,64,0x7f807dc40ec0,12358,28742,64,0x7f5096bc8ec0,16384,0,64,0x7f9bcce44ec0,0,81920,64,0x7f4da03c0ec0,340880,231327,16384,42609,42609,340872,241091,64,0x7f9e0bfd0ec0,0,0,64,0x7f5be16a0ec0,0,0,64,0x7f3888a9cec0,31498,4096,16384,64,0x7f3bba1bcec0,0,0,1410254377693730,1410254377712610 diff --git a/tests/workloads/ipblocks_SPI/MI100/sysinfo.csv b/tests/workloads/ipblocks_SPI/MI100/sysinfo.csv index cd04524e93..0d32662af6 100644 --- a/tests/workloads/ipblocks_SPI/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SPI/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,spi,Thu 07 Mar 2024 01:11:35 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,spi,Thu 21 Mar 2024 03:55:15 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SPI/MI100/timestamps.csv b/tests/workloads/ipblocks_SPI/MI100/timestamps.csv index 0ffe3fd8dd..72b6884048 100644 --- a/tests/workloads/ipblocks_SPI/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SPI/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,221987,221987,1048576,256,0,0,8,8,16,64,0x0,0x7ffb63778e80,194434963596381,194434963621537,194434963646337,194434963659661 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,221987,221987,1048576,256,0,0,8,8,16,64,0x0,0x7ffb63778e80,194434963658889,194434963736257,194434963754977,194434963756154 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,221987,221987,1048576,256,0,0,8,8,16,64,0x0,0x7ffb63778e80,194434963767816,194434963776577,194434963795777,194434963797031 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1287030,1287030,1048576,256,0,0,8,8,16,64,0x0,0x7eff5ca9cec0,1410254377504547,1410254377530050,1410254377555170,1410254377566955 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1287030,1287030,1048576,256,0,0,8,8,16,64,0x0,0x7eff5ca9cec0,1410254377567676,1410254377653250,1410254377672290,1410254377673756 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1287030,1287030,1048576,256,0,0,8,8,16,64,0x0,0x7eff5ca9cec0,1410254377685168,1410254377693730,1410254377712610,1410254377713752 diff --git a/tests/workloads/ipblocks_SPI/MI200/log.txt b/tests/workloads/ipblocks_SPI/MI200/log.txt new file mode 100644 index 0000000000..0960090ce1 --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/log.txt @@ -0,0 +1,304 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SPI/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['spi'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_165304' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165304_4182032' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165304_4182032/input0_results_240321_165304' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165304_4182032/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, GRBM_COUNT, GRBM_GUI_ACTIVE, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165304_4182032/input0_results_240321_165304 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_165305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165305_4182220' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165305_4182220/input0_results_240321_165305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165305_4182220/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] GRBM_SPI_BUSY, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165305_4182220/input0_results_240321_165305 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_165305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165305_4182419' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165305_4182419/input0_results_240321_165305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165305_4182419/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165305_4182419/input0_results_240321_165305 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_165306' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165306_4182619' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165306_4182619/input0_results_240321_165306' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165306_4182619/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165306_4182619/input0_results_240321_165306 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_165306' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165306_4182808' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165306_4182808/input0_results_240321_165306' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165306_4182808/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165306_4182808/input0_results_240321_165306 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_165307' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165307_4183009' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165307_4183009/input0_results_240321_165307' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165307_4183009/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165307_4183009/input0_results_240321_165307 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_165307' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165307_4183210' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165307_4183210/input0_results_240321_165307' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165307_4183210/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165307_4183210/input0_results_240321_165307 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_165308' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165308_4183396' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165308_4183396/input0_results_240321_165308' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165308_4183396/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165308_4183396/input0_results_240321_165308 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_165308' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165308_4183597' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165308_4183597/input0_results_240321_165308' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165308_4183597/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165308_4183597/input0_results_240321_165308 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SPI/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_165309' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SPI/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165309_4183784' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165309_4183784/input0_results_240321_165309' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165309_4183784/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165309_4183784/input0_results_240321_165309 + |-> [rocprof] File 'tests/workloads/ipblocks_SPI/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_SPI/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_0.txt new file mode 100644 index 0000000000..cef0ece5fa --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_0.txt @@ -0,0 +1,5 @@ +pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES GRBM_COUNT GRBM_GUI_ACTIVE SPI_CSN_WINDOW_VALID SPI_CSN_BUSY + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_1.txt new file mode 100644 index 0000000000..7bc758b39a --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_1.txt @@ -0,0 +1,5 @@ +pmc: GRBM_SPI_BUSY SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_2.txt new file mode 100644 index 0000000000..731670f3c3 --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_2.txt @@ -0,0 +1,5 @@ +pmc: SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_3.txt new file mode 100644 index 0000000000..1619932f59 --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_3.txt @@ -0,0 +1,5 @@ +pmc: SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_4.txt new file mode 100644 index 0000000000..6c6eb69559 --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_4.txt @@ -0,0 +1,5 @@ +pmc: SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_5.txt new file mode 100644 index 0000000000..d3a4bf5d24 --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_5.txt @@ -0,0 +1,5 @@ +pmc: SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_6.txt new file mode 100644 index 0000000000..e08c6c9abd --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_6.txt @@ -0,0 +1,5 @@ +pmc: SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_7.txt new file mode 100644 index 0000000000..3c0c370859 --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_7.txt @@ -0,0 +1,5 @@ +pmc: SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR + +gpu: +range: +kernel: diff --git a/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_8.txt new file mode 100644 index 0000000000..948b95e01b --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/perfmon/pmc_perf_8.txt @@ -0,0 +1,5 @@ +pmc: SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN + +gpu: +range: +kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/timestamps.txt b/tests/workloads/ipblocks_SPI/MI200/perfmon/timestamps.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI100/perfmon/timestamps.txt rename to tests/workloads/ipblocks_SPI/MI200/perfmon/timestamps.txt diff --git a/tests/workloads/ipblocks_SPI/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SPI/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SPI/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SPI/MI200/pmc_perf.csv new file mode 100644 index 0000000000..b41d0738fb --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_1,obj_1,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_2,obj_2,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_3,obj_3,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_4,obj_4,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_5,obj_5,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_6,obj_6,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_7,obj_7,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f64b64c4ec0,16384,0,64,0x7fd295a3cec0,8833,0,64,0x7f02ff968ec0,0,0,64,0x7f63a74bcec0,0,32768,64,0x7f68460dcec0,521403,0,64,0x7fc87df54ec0,0,0,64,0x7f2e9f4a0ec0,18564,4096,16384,64,0x7f244e978ec0,13024,18699,64,0x7f0309ba8ec0,223152,129791,16384,27893,27893,221441,137902,1413721490530695,1413721490550855 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f64b64c4ec0,16384,0,64,0x7fd295a3cec0,18718,0,64,0x7f02ff968ec0,0,0,64,0x7f63a74bcec0,0,32768,64,0x7f68460dcec0,988977,0,64,0x7fc87df54ec0,0,0,64,0x7f2e9f4a0ec0,30212,4096,16384,64,0x7f244e978ec0,34362,28809,64,0x7f0309ba8ec0,341552,242222,16384,42693,42693,341544,252065,1413721490569895,1413721490585735 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f64b64c4ec0,16384,0,64,0x7fd295a3cec0,18588,0,64,0x7f02ff968ec0,0,0,64,0x7f63a74bcec0,0,32768,64,0x7f68460dcec0,962725,0,64,0x7fc87df54ec0,0,0,64,0x7f2e9f4a0ec0,29535,4096,16384,64,0x7f244e978ec0,33194,27105,64,0x7f0309ba8ec0,325352,226687,16384,40668,40668,325344,236519,1413721490643815,1413721490660455 diff --git a/tests/workloads/ipblocks_SPI/MI200/roofline.csv b/tests/workloads/ipblocks_SPI/MI200/roofline.csv new file mode 100644 index 0000000000..cebc0e48de --- /dev/null +++ b/tests/workloads/ipblocks_SPI/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.9447,1388.3563,1389.5331,5017.9067,5014.7549,5021.0586,9227.6787,9227.0117,9228.3457,17716.801,17713.486,17720.115,20946.129,20885.578,21006.68,20273.949,20273.318,20274.58,170504.7,170501.38,170508.03,164926.7,164922.14,164931.27,41437.906,41437.375,41438.438,41496.199,41495.562,41496.836,166417.2,165925.25,166909.16 +1,1389.106,1388.5654,1389.6465,5028.894,5026.9673,5030.8208,9236.0664,9235.2822,9236.8506,18238.027,18235.617,18240.438,20982.055,20915.113,21048.996,20296.98,20296.457,20297.504,170867.27,170863.06,170871.47,165112.08,165108.19,165115.97,41485.316,41484.523,41486.109,41543.543,41542.469,41544.617,166873.45,166870.44,166876.47 +2,1388.9207,1388.3898,1389.4515,5036.0679,5033.9575,5038.1782,9262.002,9261.3369,9262.667,18218.199,18217.369,18219.029,21051.002,21050.521,21051.482,20350.826,20350.402,20351.25,171129.62,171125.81,171133.44,165524.77,165521.06,165528.47,41583.191,41582.312,41584.07,41644.961,41643.938,41645.984,166958.92,166363.44,167554.41 +3,1388.0017,1387.4788,1388.5247,5033.8398,5032.4165,5035.2632,9239.2031,9238.4922,9239.9141,18329.768,18329.01,18330.525,21033.695,21033.434,21033.957,20309.061,20308.24,20309.881,171044.95,171040.03,171049.88,165183.91,165179.16,165188.66,41430.203,41276.809,41583.598,41579.672,41578.383,41580.961,166989.88,166985.22,166994.53 diff --git a/tests/workloads/dispatch_invalid/MI100/sysinfo.csv b/tests/workloads/ipblocks_SPI/MI200/sysinfo.csv similarity index 52% rename from tests/workloads/dispatch_invalid/MI100/sysinfo.csv rename to tests/workloads/ipblocks_SPI/MI200/sysinfo.csv index 5011fc14b5..3aa3e9ed13 100644 --- a/tests/workloads/dispatch_invalid/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SPI/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -dispatch_invalid,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:16:56 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,spi|roofline,Thu 21 Mar 2024 04:53:04 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_summaries/MI100/timestamps.csv b/tests/workloads/ipblocks_SPI/MI200/timestamps.csv similarity index 50% rename from tests/workloads/kernel_summaries/MI100/timestamps.csv rename to tests/workloads/ipblocks_SPI/MI200/timestamps.csv index 5f7181ff0c..f996fc7f0f 100644 --- a/tests/workloads/kernel_summaries/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SPI/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,220054,220054,1048576,256,0,0,8,8,16,64,0x0,0x7f57d82c2e80,194428972558481,194428972583416,194428972607736,194428972621691 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,220054,220054,1048576,256,0,0,8,8,16,64,0x0,0x7f57d82c2e80,194428972621020,194428972707576,194428972726776,194428972727672 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,220054,220054,1048576,256,0,0,8,8,16,64,0x0,0x7f57d82c2e80,194428972739344,194428972748536,194428972767576,194428972768459 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4183944,4183944,1048576,256,0,0,8,0,16,64,0x0,0x7fad10af8ec0,1413721490504848,1413721490530695,1413721490550855,1413721490564120 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4183944,4183944,1048576,256,0,0,8,0,16,64,0x0,0x7fad10af8ec0,1413721490562116,1413721490569895,1413721490585735,1413721490640865 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4183944,4183944,1048576,256,0,0,8,0,16,64,0x0,0x7fad10af8ec0,1413721490596180,1413721490643815,1413721490660455,1413721490661394 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv index fb7bb937c9..527f73bd4f 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,176352,176352,1048576,256,0,0,8,8,16,64,0x0,0x7ff2f710ce80,48234,48234,16384,65536,13448,1730548,194287866542271,194294746542348,194294746566668,194287875222636 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,176352,176352,1048576,256,0,0,8,8,16,64,0x0,0x7ff2f710ce80,39353,39353,16384,65536,8354,1048644,194287874860921,194294746587308,194294746606348,194287876419964 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,176352,176352,1048576,256,0,0,8,8,16,64,0x0,0x7ff2f710ce80,38863,38863,16384,65536,8197,1048648,194287875000886,194294746690668,194294746709548,194287875226604 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1271978,1271978,1048576,256,0,0,8,8,16,64,0x0,0x7fb8fbaf4ec0,48994,48994,16384,65536,14572,1859668,1410207576240960,1410214261055107,1410214261079427,1410207583940121 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1271978,1271978,1048576,256,0,0,8,8,16,64,0x0,0x7fb8fbaf4ec0,42770,42770,16384,65536,8094,1048604,1410207583964968,1410214261164067,1410214261182947,1410207584273149 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1271978,1271978,1048576,256,0,0,8,8,16,64,0x0,0x7fb8fbaf4ec0,43684,43684,16384,65536,8224,1048592,1410207584305260,1410214261204227,1410214261222947,1410207584479618 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv index 784d9079d6..52f342d648 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,176537,176537,1048576,256,0,0,8,8,16,64,0x0,0x7f3eb9a06e80,0,0,0,194288360563039,194294746542348,194294746566668,194288368404226 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,176537,176537,1048576,256,0,0,8,8,16,64,0x0,0x7f3eb9a06e80,0,0,0,194288368424535,194294746587308,194294746606348,194288368724302 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,176537,176537,1048576,256,0,0,8,8,16,64,0x0,0x7f3eb9a06e80,0,0,0,194288368752355,194294746690668,194294746709548,194288368924201 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1272162,1272162,1048576,256,0,0,8,8,16,64,0x0,0x7fb1b3804ec0,0,0,0,1410208053428241,1410214261055107,1410214261079427,1410208061241256 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1272162,1272162,1048576,256,0,0,8,8,16,64,0x0,0x7fb1b3804ec0,0,0,0,1410208061260061,1410214261164067,1410214261182947,1410208061573733 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1272162,1272162,1048576,256,0,0,8,8,16,64,0x0,0x7fb1b3804ec0,0,0,0,1410208061602307,1410214261204227,1410214261222947,1410208061786574 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv index 599b11b04e..7f843cdd4b 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,176723,176723,1048576,256,0,0,8,8,16,64,0x0,0x7f36dba02e80,65536,215186,27423112,194288851113227,194294746542348,194294746566668,194288858883329 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,176723,176723,1048576,256,0,0,8,8,16,64,0x0,0x7f36dba02e80,65536,208000,26558816,194288858902876,194294746587308,194294746606348,194288859206020 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,176723,176723,1048576,256,0,0,8,8,16,64,0x0,0x7f36dba02e80,65536,189368,24301824,194288859234474,194294746690668,194294746709548,194288859410838 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1272349,1272349,1048576,256,0,0,8,8,16,64,0x0,0x7f1543d90ec0,65536,190294,24406952,1410208534073653,1410214261055107,1410214261079427,1410208541676392 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1272349,1272349,1048576,256,0,0,8,8,16,64,0x0,0x7f1543d90ec0,65536,181188,23163584,1410208541695829,1410214261164067,1410214261182947,1410208542000814 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1272349,1272349,1048576,256,0,0,8,8,16,64,0x0,0x7f1543d90ec0,65536,180898,23098168,1410208542028957,1410214261204227,1410214261222947,1410208542197104 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv index a5b42e05d5..21a18b2528 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,176906,176906,1048576,256,0,0,8,8,16,64,0x0,0x7f7026c14e80,32768,641207,82083564,194289338933616,194294746542348,194294746566668,194289346782968 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,176906,176906,1048576,256,0,0,8,8,16,64,0x0,0x7f7026c14e80,32768,659200,84360976,194289346801022,194294746587308,194294746606348,194289347142408 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,176906,176906,1048576,256,0,0,8,8,16,64,0x0,0x7f7026c14e80,32768,634018,81134416,194289347171143,194294746690668,194294746709548,194289347345263 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1272532,1272532,1048576,256,0,0,8,8,16,64,0x0,0x7fcc45e60ec0,32768,637551,81595980,1410209014511845,1410214261055107,1410214261079427,1410209022190677 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1272532,1272532,1048576,256,0,0,8,8,16,64,0x0,0x7fcc45e60ec0,32768,666727,85339076,1410209022210915,1410214261164067,1410214261182947,1410209022519467 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1272532,1272532,1048576,256,0,0,8,8,16,64,0x0,0x7fcc45e60ec0,32768,639083,81807428,1410209022547971,1410214261204227,1410214261222947,1410209022736126 diff --git a/tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv index 46e5cf0be9..10d9f307c8 100644 --- a/tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,177092,177092,1048576,256,0,0,8,8,16,64,0x0,0x7fc837804e80,49473,49473,18573,395792,16384,25193691,240627,0,101250320,194289831974198,194294746542348,194294746566668,194289839769899 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,177092,177092,1048576,256,0,0,8,8,16,64,0x0,0x7fc837804e80,43137,43137,12928,345104,16384,25261600,238599,0,101529368,194289839802441,194294746587308,194294746606348,194289840061511 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,177092,177092,1048576,256,0,0,8,8,16,64,0x0,0x7fc837804e80,42681,42681,12493,341456,16384,24886720,234534,0,100039300,194289840101277,194294746690668,194294746709548,194289840270677 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1272715,1272715,1048576,256,0,0,8,8,16,64,0x0,0x7fb1dbbd8ec0,48718,48718,18283,389752,16384,25235056,238765,0,101467848,1410209493858388,1410214261055107,1410214261079427,1410209501557679 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1272715,1272715,1048576,256,0,0,8,8,16,64,0x0,0x7fb1dbbd8ec0,43605,43605,14556,348848,16384,24701386,235875,0,99336004,1410209501587735,1410214261164067,1410214261182947,1410209501905805 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1272715,1272715,1048576,256,0,0,8,8,16,64,0x0,0x7fb1dbbd8ec0,43381,43381,14586,347056,16384,25043205,236240,0,100701676,1410209501943847,1410214261204227,1410214261222947,1410209502128635 diff --git a/tests/workloads/ipblocks_SQ/MI100/log.txt b/tests/workloads/ipblocks_SQ/MI100/log.txt new file mode 100644 index 0000000000..8089b70bb1 --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI100/log.txt @@ -0,0 +1,447 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155433' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155433_1271818' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155433_1271818/input0_results_240321_155433' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155433_1271818/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155433_1271818/input0_results_240321_155433 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155434' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155434_1272002' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155434_1272002/input0_results_240321_155434' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155434_1272002/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155434_1272002/input0_results_240321_155434 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155434' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155434_1272189' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155434_1272189/input0_results_240321_155434' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155434_1272189/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155434_1272189/input0_results_240321_155434 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155435' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155435_1272372' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155435_1272372/input0_results_240321_155435' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155435_1272372/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155435_1272372/input0_results_240321_155435 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155435' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155435_1272555' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155435_1272555/input0_results_240321_155435' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155435_1272555/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155435_1272555/input0_results_240321_155435 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155435' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155435_1272740' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155435_1272740/input0_results_240321_155435' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155435_1272740/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, GRBM_COUNT, GRBM_GUI_ACTIVE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155435_1272740/input0_results_240321_155435 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155436' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155436_1272924' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155436_1272924/input0_results_240321_155436' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155436_1272924/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155436_1272924/input0_results_240321_155436 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155436' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155436_1273109' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155436_1273109/input0_results_240321_155436' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155436_1273109/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155436_1273109/input0_results_240321_155436 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155437' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155437_1273292' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155437_1273292/input0_results_240321_155437' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155437_1273292/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155437_1273292/input0_results_240321_155437 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155437' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155437_1273475' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155437_1273475/input0_results_240321_155437' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155437_1273475/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES, SQ_WAVES_EQ_64, SQ_WAVES_LT_64 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155437_1273475/input0_results_240321_155437 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155438' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155438_1273659' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155438_1273659/input0_results_240321_155438' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155438_1273659/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155438_1273659/input0_results_240321_155438 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155438' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155438_1273842' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155438_1273842/input0_results_240321_155438' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155438_1273842/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155438_1273842/input0_results_240321_155438 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155439' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155439_1274025' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155439_1274025/input0_results_240321_155439' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155439_1274025/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155439_1274025/input0_results_240321_155439 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155439' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155439_1274210' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155439_1274210/input0_results_240321_155439' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155439_1274210/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155439_1274210/input0_results_240321_155439 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155440' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155440_1274394' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155440_1274394/input0_results_240321_155440' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155440_1274394/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155440_1274394/input0_results_240321_155440 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_SQ/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_SQ/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_SQ/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv index 2c63a23501..054f0c7078 100644 --- a/tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,wave_size_1,obj_1,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_2,obj_2,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,wave_size_4,obj_4,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,wave_size_5,obj_5,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,wave_size_6,obj_6,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,wave_size_7,obj_7,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,wave_size_8,obj_8,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,GRBM_COUNT,GRBM_GUI_ACTIVE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2d32c78e80,360448,383040,230767,3394741,163840,0,0,180224,64,0x7f9f987fce80,65536,64048,48,1440,32768,32768,0,64,0x7ff727660e80,0,0,16384,16384,393216,24251404,21796835,2094121,64,0x7fa2e0434e80,0,65536,64548,48,1462,192379,0,0,64,0x7f6230282e80,11534336,65536,0,0,0,16384,16384,0,64,0x7f1a99face80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f221d6eae80,0,0,0,1048576,0,0,0,0,64,0x7fccf1014e80,0,131072,144,48,0,0,0,192,64,0x7f2865f04e80,16384,16384,32768,49152,0,65536,32768,0,48122,48122,194294746542348,194294746566668 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2d32c78e80,360448,339472,228619,3354299,163840,0,0,180224,64,0x7f9f987fce80,65536,64048,48,1440,32768,32768,0,64,0x7ff727660e80,0,0,16384,16384,393216,24739969,23168673,1210848,64,0x7fa2e0434e80,0,65536,65536,0,0,204715,0,0,64,0x7f6230282e80,11534336,65536,0,0,0,16384,16384,0,64,0x7f1a99face80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f221d6eae80,0,0,0,1048576,0,0,0,0,64,0x7fccf1014e80,0,131072,0,48,0,0,0,48,64,0x7f2865f04e80,16384,16384,32768,49152,0,65536,32768,0,43105,43105,194294746587308,194294746606348 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2d32c78e80,360448,345616,234177,3390078,163840,0,0,180224,64,0x7f9f987fce80,65536,64048,48,1440,32768,32768,0,64,0x7ff727660e80,0,0,16384,16384,393216,23757309,22259143,1137718,64,0x7fa2e0434e80,0,65536,65536,0,0,124150,0,0,64,0x7f6230282e80,11534336,65536,0,0,0,16384,16384,0,64,0x7f1a99face80,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f221d6eae80,0,0,0,1048576,0,0,0,0,64,0x7fccf1014e80,0,131072,0,48,0,0,0,48,64,0x7f2865f04e80,16384,16384,32768,49152,0,65536,32768,0,43540,43540,194294746690668,194294746709548 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,wave_size_1,obj_1,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_2,obj_2,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,wave_size_3,obj_3,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,wave_size_4,obj_4,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,wave_size_5,obj_5,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,wave_size_6,obj_6,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,wave_size_7,obj_7,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_8,obj_8,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7871d34ec0,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f87f24e4ec0,16384,16384,32768,49152,0,65536,32768,0,48610,48610,64,0x7f19c008cec0,0,0,0,1048576,0,0,0,0,64,0x7f227ef30ec0,11534336,65536,0,0,0,16384,16384,0,64,0x7f6b8732cec0,0,0,16384,16384,393216,24939041,22877248,1701345,64,0x7f9768af8ec0,360448,389176,235922,3459582,163840,0,0,180224,64,0x7fc8ebc94ec0,0,131072,144,48,0,0,0,192,64,0x7f33aab20ec0,65536,64048,48,1440,32768,32768,0,64,0x7fe6a6ce8ec0,0,65536,64483,48,1344,192830,0,0,1410214261055107,1410214261079427 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7871d34ec0,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f87f24e4ec0,16384,16384,32768,49152,0,65536,32768,0,42783,42783,64,0x7f19c008cec0,0,0,0,1048576,0,0,0,0,64,0x7f227ef30ec0,11534336,65536,0,0,0,16384,16384,0,64,0x7f6b8732cec0,0,0,16384,16384,393216,24432198,22892790,1178960,64,0x7f9768af8ec0,360448,347960,234507,3423369,163840,0,0,180224,64,0x7fc8ebc94ec0,0,131072,0,48,0,0,0,48,64,0x7f33aab20ec0,65536,64048,48,1440,32768,32768,0,64,0x7fe6a6ce8ec0,0,65536,65536,0,0,197916,0,0,1410214261164067,1410214261182947 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7871d34ec0,114688,0,32768,32768,16384,16384,65536,49152,64,0x7f87f24e4ec0,16384,16384,32768,49152,0,65536,32768,0,43010,43010,64,0x7f19c008cec0,0,0,0,1048576,0,0,0,0,64,0x7f227ef30ec0,11534336,65536,0,0,0,16384,16384,0,64,0x7f6b8732cec0,0,0,16384,16384,393216,24377166,22871471,1145247,64,0x7f9768af8ec0,360448,346936,232915,3404998,163840,0,0,180224,64,0x7fc8ebc94ec0,0,131072,0,48,0,0,0,48,64,0x7f33aab20ec0,65536,64048,48,1440,32768,32768,0,64,0x7fe6a6ce8ec0,0,65536,65536,0,0,194362,0,0,1410214261204227,1410214261222947 diff --git a/tests/workloads/ipblocks_SQ/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ/MI100/sysinfo.csv index c13650d778..e7f9eb171c 100644 --- a/tests/workloads/ipblocks_SQ/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ,./tests/vcopy -n 1048576 -b 256 -i 3,sq,Thu 07 Mar 2024 01:09:12 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ,./tests/vcopy -n 1048576 -b 256 -i 3,sq,Thu 21 Mar 2024 03:54:33 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ/MI100/timestamps.csv index 54300edca9..b9a3788c8b 100644 --- a/tests/workloads/ipblocks_SQ/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,178946,178946,1048576,256,0,0,8,8,16,64,0x0,0x7f140cd24e80,194294746517963,194294746542348,194294746566668,194294746592004 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,178946,178946,1048576,256,0,0,8,8,16,64,0x0,0x7f140cd24e80,194294746579850,194294746587308,194294746606348,194294746688917 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,178946,178946,1048576,256,0,0,8,8,16,64,0x0,0x7f140cd24e80,194294746618003,194294746690668,194294746709548,194294746710728 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1274554,1274554,1048576,256,0,0,8,8,16,64,0x0,0x7f4202420ec0,1410214261030186,1410214261055107,1410214261079427,1410214261091191 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1274554,1274554,1048576,256,0,0,8,8,16,64,0x0,0x7f4202420ec0,1410214261092113,1410214261164067,1410214261182947,1410214261184377 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1274554,1274554,1048576,256,0,0,8,8,16,64,0x0,0x7f4202420ec0,1410214261194997,1410214261204227,1410214261222947,1410214261224272 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv index 6df566d2e8..69fb559158 100644 --- a/tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,336275,336275,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18340ec0,27606,27606,16384,65536,13698,1553080,199243257890335,199251858177827,199251858197828,199243273617477 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,336275,336275,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18340ec0,40557,40557,16384,65536,9412,1048644,199243273638647,199251858218948,199251858234148,199243273939656 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,336275,336275,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18340ec0,40036,40036,16384,65536,9730,1048692,199243273969292,199251858254148,199251858269668,199243274140837 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4160782,4160782,1048576,256,0,0,8,0,16,64,0x0,0x7f43581d8ec0,28254,28254,16384,65536,12974,1483840,1412823910746438,1412832625908622,1412832625929262,1412823926614106 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4160782,4160782,1048576,256,0,0,8,0,16,64,0x0,0x7f43581d8ec0,42342,42342,16384,65536,9196,1048668,1412823926633263,1412832625948622,1412832625964462,1412823926978505 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4160782,4160782,1048576,256,0,0,8,0,16,64,0x0,0x7f43581d8ec0,41700,41700,16384,65536,9134,1048608,1412823927007380,1412832626019342,1412832626036142,1412823927180678 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv index c6bc2d6b86..aa5249900c 100644 --- a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,336459,336459,1048576,256,0,0,8,0,16,64,0x0,0x7f8d3eb34ec0,0,0,0,199243740198768,199251858177827,199251858197828,199243755900662 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,336459,336459,1048576,256,0,0,8,0,16,64,0x0,0x7f8d3eb34ec0,0,0,0,199243755918826,199251858218948,199251858234148,199243756228833 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,336459,336459,1048576,256,0,0,8,0,16,64,0x0,0x7f8d3eb34ec0,0,0,0,199243756254982,199251858254148,199251858269668,199243756413292 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4160965,4160965,1048576,256,0,0,8,0,16,64,0x0,0x7fbfe8fd8ec0,0,0,0,1412824396726833,1412832625908622,1412832625929262,1412824412492488 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4160965,4160965,1048576,256,0,0,8,0,16,64,0x0,0x7fbfe8fd8ec0,0,0,0,1412824412510703,1412832625948622,1412832625964462,1412824412811351 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4160965,4160965,1048576,256,0,0,8,0,16,64,0x0,0x7fbfe8fd8ec0,0,0,0,1412824412837771,1412832626019342,1412832626036142,1412824412991782 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv index f2ba009db1..33763574c8 100644 --- a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,336644,336644,1048576,256,0,0,8,0,16,64,0x0,0x7f601be04ec0,65536,172532,19226608,199244217858407,199251858177827,199251858197828,199244233653417 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,336644,336644,1048576,256,0,0,8,0,16,64,0x0,0x7f601be04ec0,65536,221966,24789584,199244233670409,199251858218948,199251858234148,199244233973923 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,336644,336644,1048576,256,0,0,8,0,16,64,0x0,0x7f601be04ec0,65536,223208,24976792,199244234000182,199251858254148,199251858269668,199244234155717 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4161149,4161149,1048576,256,0,0,8,0,16,64,0x0,0x7ff524694ec0,65536,173682,19543264,1412824881339070,1412832625908622,1412832625929262,1412824897688509 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4161149,4161149,1048576,256,0,0,8,0,16,64,0x0,0x7ff524694ec0,65536,226778,25378776,1412824897706163,1412832625948622,1412832625964462,1412824898004367 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4161149,4161149,1048576,256,0,0,8,0,16,64,0x0,0x7ff524694ec0,65536,227844,25516896,1412824898030055,1412832626019342,1412832626036142,1412824898196380 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv index 6e72edc0ad..3754bc7c71 100644 --- a/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,336828,336828,1048576,256,0,0,8,0,16,64,0x0,0x7f57fc768ec0,32768,291116,32616104,199244692689033,199251858177827,199251858197828,199244708573473 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,336828,336828,1048576,256,0,0,8,0,16,64,0x0,0x7f57fc768ec0,32768,586097,65651116,199244708592498,199251858218948,199251858234148,199244708875995 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,336828,336828,1048576,256,0,0,8,0,16,64,0x0,0x7f57fc768ec0,32768,589928,66080600,199244708902164,199251858254148,199251858269668,199244709053841 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4161350,4161350,1048576,256,0,0,8,0,16,64,0x0,0x7f7087474ec0,32768,299607,33556532,1412825361112807,1412832625908622,1412832625929262,1412825377436888 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4161350,4161350,1048576,256,0,0,8,0,16,64,0x0,0x7f7087474ec0,32768,574763,64371732,1412825377453730,1412832625948622,1412832625964462,1412825377740362 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4161350,4161350,1048576,256,0,0,8,0,16,64,0x0,0x7f7087474ec0,32768,596025,66743572,1412825377766412,1412832626019342,1412832626036142,1412825377924851 diff --git a/tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv index 71f20939fa..16f9111812 100644 --- a/tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,337011,337011,1048576,256,0,0,8,0,16,64,0x0,0x7f6e468a0ec0,28447,28447,11419,227584,16384,11171625,132835,0,45191448,199245172812934,199251858177827,199251858197828,199245188521290 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,337011,337011,1048576,256,0,0,8,0,16,64,0x0,0x7f6e468a0ec0,42213,42213,13481,337712,16384,19736747,227586,0,79416648,199245188549874,199251858218948,199251858234148,199245188790269 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,337011,337011,1048576,256,0,0,8,0,16,64,0x0,0x7f6e468a0ec0,43110,43110,14163,344888,16384,20211071,231384,0,81328932,199245188825485,199251858254148,199251858269668,199245188974427 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4161535,4161535,1048576,256,0,0,8,0,16,64,0x0,0x7fa939c80ec0,27371,27371,11384,218976,16384,10204241,122705,0,41318760,1412825850697198,1412832625908622,1412832625929262,1412825866881875 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4161535,4161535,1048576,256,0,0,8,0,16,64,0x0,0x7fa939c80ec0,39847,39847,13400,318784,16384,18104608,210773,0,72895592,1412825866909998,1412832625948622,1412832625964462,1412825867225725 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4161535,4161535,1048576,256,0,0,8,0,16,64,0x0,0x7fa939c80ec0,39689,39689,12768,317520,16384,19007582,217920,0,76505944,1412825867260772,1412832626019342,1412832626036142,1412825867435111 diff --git a/tests/workloads/ipblocks_SQ/MI200/log.txt b/tests/workloads/ipblocks_SQ/MI200/log.txt new file mode 100644 index 0000000000..4e8bf5b34a --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/log.txt @@ -0,0 +1,565 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_163811' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163811_4160622' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163811_4160622/input0_results_240321_163811' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163811_4160622/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163811_4160622/input0_results_240321_163811 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_163812' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163812_4160805' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163812_4160805/input0_results_240321_163812' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163812_4160805/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163812_4160805/input0_results_240321_163812 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_163812' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163812_4160989' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163812_4160989/input0_results_240321_163812' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163812_4160989/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163812_4160989/input0_results_240321_163812 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_163813' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163813_4161190' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163813_4161190/input0_results_240321_163813' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163813_4161190/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163813_4161190/input0_results_240321_163813 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_163813' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163813_4161375' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163813_4161375/input0_results_240321_163813' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163813_4161375/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163813_4161375/input0_results_240321_163813 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_163814' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163814_4161579' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163814_4161579/input0_results_240321_163814' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163814_4161579/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, GRBM_COUNT, GRBM_GUI_ACTIVE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163814_4161579/input0_results_240321_163814 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_163814' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163814_4161764' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163814_4161764/input0_results_240321_163814' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163814_4161764/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163814_4161764/input0_results_240321_163814 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_163815' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163815_4161948' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163815_4161948/input0_results_240321_163815' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163815_4161948/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163815_4161948/input0_results_240321_163815 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_163815' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163815_4162132' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163815_4162132/input0_results_240321_163815' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163815_4162132/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163815_4162132/input0_results_240321_163815 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_163816' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163816_4162333' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163816_4162333/input0_results_240321_163816' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163816_4162333/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163816_4162333/input0_results_240321_163816 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_163816' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163816_4162520' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163816_4162520/input0_results_240321_163816' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163816_4162520/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163816_4162520/input0_results_240321_163816 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_163817' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163817_4162704' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163817_4162704/input0_results_240321_163817' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163817_4162704/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163817_4162704/input0_results_240321_163817 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_163817' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163817_4162889' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163817_4162889/input0_results_240321_163817' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163817_4162889/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163817_4162889/input0_results_240321_163817 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_163817' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163817_4163075' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163817_4163075/input0_results_240321_163817' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163817_4163075/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163817_4163075/input0_results_240321_163817 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_163818' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163818_4163264' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163818_4163264/input0_results_240321_163818' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163818_4163264/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163818_4163264/input0_results_240321_163818 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_163818' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163818_4163453' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163818_4163453/input0_results_240321_163818' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163818_4163453/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163818_4163453/input0_results_240321_163818 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_163819' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163819_4163642' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163819_4163642/input0_results_240321_163819' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163819_4163642/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163819_4163642/input0_results_240321_163819 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_163819' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163819_4163826' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163819_4163826/input0_results_240321_163819' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163819_4163826/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163819_4163826/input0_results_240321_163819 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_163820' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163820_4164028' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163820_4164028/input0_results_240321_163820' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163820_4164028/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163820_4164028/input0_results_240321_163820 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_SQ/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_SQ/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_SQ/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv index 2bb202d22c..3d4a38e248 100644 --- a/tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,wave_size_1,obj_1,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,wave_size_3,obj_3,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,wave_size_4,obj_4,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,wave_size_8,obj_8,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_9,obj_9,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_10,obj_10,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,wave_size_11,obj_11,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_12,obj_12,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc9c3768ec0,0,0,1048576,0,0,0,0,0,64,0x7feb9ac18ec0,131072,0,0,0,0,0,0,0,64,0x7f12b2c28ec0,0,0,0,0,0,0,0,0,64,0x7f6c79108ec0,0,0,0,0,114688,0,65536,32768,64,0x7fa00f670ec0,0,0,0,16384,16384,10934965,9763176,827725,64,0x7fee3825cec0,0,0,0,0,0,0,168,56,64,0x7f59b1f38ec0,32768,32768,0,64,0x7f5674918ec0,344064,222976,127987,1615005,0,0,163840,114688,64,0x7f0011640ec0,0,0,0,224,0,65536,64162,56,64,0x7fe75edd8ec0,1319,113132,0,0,65536,63800,56,1680,64,0x7fae1f40cec0,65536,0,0,0,16384,16384,0,0,64,0x7f3d30f78ec0,0,16384,16384,32768,49152,0,393216,163840,28295,28295,64,0x7f89cd87cec0,0,32768,32768,16384,16384,65536,49152,10485760,199251858177827,199251858197828 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc9c3768ec0,0,0,1048576,0,0,0,0,0,64,0x7feb9ac18ec0,131072,0,0,0,0,0,0,0,64,0x7f12b2c28ec0,0,0,0,0,0,0,0,0,64,0x7f6c79108ec0,0,0,0,0,114688,0,65536,32768,64,0x7fa00f670ec0,0,0,0,16384,16384,19187139,18007559,835516,64,0x7fee3825cec0,0,0,0,0,0,0,0,56,64,0x7f59b1f38ec0,32768,32768,0,64,0x7f5674918ec0,344064,333920,223951,2824441,0,0,163840,114688,64,0x7f0011640ec0,0,0,0,56,0,65536,65536,0,64,0x7fe75edd8ec0,0,229693,0,0,65536,63800,56,1680,64,0x7fae1f40cec0,65536,0,0,0,16384,16384,0,0,64,0x7f3d30f78ec0,0,16384,16384,32768,49152,0,393216,163840,42135,42135,64,0x7f89cd87cec0,0,32768,32768,16384,16384,65536,49152,10485760,199251858218948,199251858234148 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc9c3768ec0,0,0,1048576,0,0,0,0,0,64,0x7feb9ac18ec0,131072,0,0,0,0,0,0,0,64,0x7f12b2c28ec0,0,0,0,0,0,0,0,0,64,0x7f6c79108ec0,0,0,0,0,114688,0,65536,32768,64,0x7fa00f670ec0,0,0,0,16384,16384,19443161,18081365,1017732,64,0x7fee3825cec0,0,0,0,0,0,0,0,56,64,0x7f59b1f38ec0,32768,32768,0,64,0x7f5674918ec0,344064,335296,224911,2814564,0,0,163840,114688,64,0x7f0011640ec0,0,0,0,56,0,65536,65536,0,64,0x7fe75edd8ec0,0,185998,0,0,65536,63800,56,1680,64,0x7fae1f40cec0,65536,0,0,0,16384,16384,0,0,64,0x7f3d30f78ec0,0,16384,16384,32768,49152,0,393216,163840,41526,41526,64,0x7f89cd87cec0,0,32768,32768,16384,16384,65536,49152,10485760,199251858254148,199251858269668 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,wave_size_1,obj_1,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_2,obj_2,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,wave_size_3,obj_3,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,wave_size_4,obj_4,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,wave_size_5,obj_5,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,wave_size_6,obj_6,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,wave_size_7,obj_7,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_8,obj_8,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_9,obj_9,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,wave_size_10,obj_10,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_11,obj_11,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_12,obj_12,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fd72551cec0,344064,219576,128624,1626198,0,0,163840,114688,64,0x7f6bfc378ec0,32768,32768,0,64,0x7f3ab34fcec0,131072,0,0,0,0,0,0,0,64,0x7f220e298ec0,0,32768,32768,16384,16384,65536,49152,10485760,64,0x7f8184484ec0,0,0,0,0,114688,0,65536,32768,64,0x7ff602f68ec0,0,0,0,0,0,0,0,0,64,0x7f68ddb04ec0,0,0,0,16384,16384,10715405,9621596,749745,64,0x7f059b82cec0,0,16384,16384,32768,49152,0,393216,163840,28350,28350,64,0x7f2ebb610ec0,0,0,0,224,0,65536,64273,56,64,0x7f4194f10ec0,65536,0,0,0,16384,16384,0,0,64,0x7f18dcb60ec0,0,0,0,0,0,0,168,56,64,0x7f7fe7498ec0,1304,121211,0,0,65536,63800,56,1680,64,0x7fdb6d3f8ec0,0,0,1048576,0,0,0,0,0,1412832625908622,1412832625929262 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fd72551cec0,344064,326784,216282,2712015,0,0,163840,114688,64,0x7f6bfc378ec0,32768,32768,0,64,0x7f3ab34fcec0,131072,0,0,0,0,0,0,0,64,0x7f220e298ec0,0,32768,32768,16384,16384,65536,49152,10485760,64,0x7f8184484ec0,0,0,0,0,114688,0,65536,32768,64,0x7ff602f68ec0,0,0,0,0,0,0,0,0,64,0x7f68ddb04ec0,0,0,0,16384,16384,19850019,18464249,1041706,64,0x7f059b82cec0,0,16384,16384,32768,49152,0,393216,163840,41271,41271,64,0x7f2ebb610ec0,0,0,0,56,0,65536,65536,0,64,0x7f4194f10ec0,65536,0,0,0,16384,16384,0,0,64,0x7f18dcb60ec0,0,0,0,0,0,0,0,56,64,0x7f7fe7498ec0,0,186578,0,0,65536,63800,56,1680,64,0x7fdb6d3f8ec0,0,0,1048576,0,0,0,0,0,1412832625948622,1412832625964462 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fd72551cec0,344064,326072,213971,2695051,0,0,163840,114688,64,0x7f6bfc378ec0,32768,32768,0,64,0x7f3ab34fcec0,131072,0,0,0,0,0,0,0,64,0x7f220e298ec0,0,32768,32768,16384,16384,65536,49152,10485760,64,0x7f8184484ec0,0,0,0,0,114688,0,65536,32768,64,0x7ff602f68ec0,0,0,0,0,0,0,0,0,64,0x7f68ddb04ec0,0,0,0,16384,16384,18931454,17773175,814215,64,0x7f059b82cec0,0,16384,16384,32768,49152,0,393216,163840,41332,41332,64,0x7f2ebb610ec0,0,0,0,56,0,65536,65536,0,64,0x7f4194f10ec0,65536,0,0,0,16384,16384,0,0,64,0x7f18dcb60ec0,0,0,0,0,0,0,0,56,64,0x7f7fe7498ec0,0,187127,0,0,65536,63800,56,1680,64,0x7fdb6d3f8ec0,0,0,1048576,0,0,0,0,0,1412832626019342,1412832626036142 diff --git a/tests/workloads/ipblocks_SQ/MI200/roofline.csv b/tests/workloads/ipblocks_SQ/MI200/roofline.csv index eb12972e07..96fa11c8dc 100644 --- a/tests/workloads/ipblocks_SQ/MI200/roofline.csv +++ b/tests/workloads/ipblocks_SQ/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.606,1388.014,1389.1979,5013.4312,5010.3784,5016.4839,9222.1006,9221.4424,9222.7588,18048.148,18047.154,18049.143,20925.711,20865.328,20986.094,20259.674,20258.982,20260.365,170342.34,170338.62,170346.06,164805.45,164801.22,164809.69,41405.574,41404.898,41406.25,41467.379,41466.711,41468.047,166282.69,165791.16,166774.22 -1,1389.085,1388.5358,1389.6342,5028.3569,5026.0806,5030.6333,9233.1758,9232.5146,9233.8369,18085.131,18083.555,18086.707,20972.803,20905.426,21040.18,20294.641,20294.074,20295.207,170848.98,170844.91,170853.06,165103.45,165099.84,165107.06,41483.621,41482.855,41484.387,41543.184,41542.176,41544.191,166873.55,166870.08,166877.02 -2,1388.2489,1387.6832,1388.8146,5035.9229,5033.5801,5038.2656,9262.1865,9261.2529,9263.1201,18106.953,18106.029,18107.877,21051.465,21051.16,21051.77,20354.99,20354.521,20355.459,171135,171132.19,171137.81,165515.41,165511.5,165519.31,41590.117,41589.039,41591.195,41653.234,41652.277,41654.191,166991.17,166397.83,167584.52 -3,1388.8011,1388.223,1389.3793,5033.9556,5032.5698,5035.3413,9242.6387,9242.1729,9243.1045,18028.344,18024.803,18031.885,21039.02,21038.312,21039.727,20316.457,20315.727,20317.188,171056.38,171052.06,171060.69,165249.28,165243.64,165254.92,41447.359,41294.148,41600.57,41587.234,41586.715,41587.754,167034.94,167032.98,167036.89 +0,1389.149,1388.5695,1389.7286,5017.498,5014.5425,5020.4536,9227.4746,9226.7764,9228.1729,17716.939,17713.738,17720.141,20946.105,20885.916,21006.295,20275.338,20274.693,20275.982,170520.08,170516.92,170523.23,164928.39,164923.2,164933.58,41434.664,41434.211,41435.117,41490.637,41489.773,41491.5,166394.97,165904.02,166885.92 +1,1389.3711,1388.8942,1389.848,5028.7451,5026.8232,5030.667,9233.2695,9232.7363,9233.8027,18230.164,18227.889,18232.439,20973.34,20906.623,21040.057,20291.283,20290.693,20291.873,170807.34,170803.84,170810.84,165083.88,165079.75,165088,41478.855,41478.191,41479.52,41539.512,41538.711,41540.312,166863.23,166860.86,166865.61 +2,1388.6953,1388.1658,1389.2249,5037.3721,5034.9126,5039.8315,9263.8574,9263.1104,9264.6045,18221.762,18220.834,18222.689,21054.215,21053.811,21054.619,20355.158,20354.6,20355.717,171145.84,171142.03,171149.66,165536.2,165532.69,165539.72,41589.191,41588.344,41590.039,41648.039,41647.105,41648.973,166983.75,166390.45,167577.05 +3,1389.7206,1389.1255,1390.3157,5035.0845,5033.5171,5036.6519,9239.2891,9238.5176,9240.0605,18328.168,18327.238,18329.098,21036.189,21035.861,21036.518,20309.928,20309.445,20310.41,171048.16,171043.16,171053.16,165147.84,165142.84,165152.84,41423.414,41268.914,41577.914,41569.262,41567.777,41570.746,166964.8,166960.86,166968.73 diff --git a/tests/workloads/ipblocks_SQ/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ/MI200/sysinfo.csv index f770ed362f..bfb16a2601 100644 --- a/tests/workloads/ipblocks_SQ/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ,./sample/vcopy -n 1048576 -b 256 -i 3,sq|roofline,Thu 07 Mar 2024 02:31:50 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_SQ,./tests/vcopy -n 1048576 -b 256 -i 3,sq|roofline,Thu 21 Mar 2024 04:38:11 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ/MI200/timestamps.csv index c1b26c690f..a4b06c7e18 100644 --- a/tests/workloads/ipblocks_SQ/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_SQ/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,339689,339689,1048576,256,0,0,8,0,16,64,0x0,0x7f29ed89cec0,199251858149201,199251858177827,199251858197828,199251858425263 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,339689,339689,1048576,256,0,0,8,0,16,64,0x0,0x7f29ed89cec0,199251858210547,199251858218948,199251858234148,199251858515855 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,339689,339689,1048576,256,0,0,8,0,16,64,0x0,0x7f29ed89cec0,199251858244962,199251858254148,199251858269668,199251858506176 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4164188,4164188,1048576,256,0,0,8,0,16,64,0x0,0x7f0dc6c30ec0,1412832625884553,1412832625908622,1412832625929262,1412832625944176 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4164188,4164188,1048576,256,0,0,8,0,16,64,0x0,0x7f0dc6c30ec0,1412832625940229,1412832625948622,1412832625964462,1412832626016132 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4164188,4164188,1048576,256,0,0,8,0,16,64,0x0,0x7f0dc6c30ec0,1412832625974824,1412832626019342,1412832626036142,1412832626037493 diff --git a/tests/workloads/ipblocks_SQC/MI100/log.txt b/tests/workloads/ipblocks_SQC/MI100/log.txt new file mode 100644 index 0000000000..cd84b7ac7f --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI100/log.txt @@ -0,0 +1,157 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQC/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sqc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155342' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155342_1255117' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155342_1255117/input0_results_240321_155342' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155342_1255117/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155342_1255117/input0_results_240321_155342 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155342' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155342_1255303' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155342_1255303/input0_results_240321_155342' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155342_1255303/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155342_1255303/input0_results_240321_155342 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155343' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155343_1255491' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155343_1255491/input0_results_240321_155343' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155343_1255491/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155343_1255491/input0_results_240321_155343 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155343' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155343_1255679' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155343_1255679/input0_results_240321_155343' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155343_1255679/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155343_1255679/input0_results_240321_155343 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155344' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155344_1255862' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155344_1255862/input0_results_240321_155344' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155344_1255862/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155344_1255862/input0_results_240321_155344 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_SQC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQC/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_SQC/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_SQC/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv index 622ae8c42f..0a83574ba5 100644 --- a/tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_2,obj_2,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8502124e80,186901,0,0,65536,64048,48,1440,32768,64,0x7f9356168e80,382680,232518,3401999,16384,25014980,144,48,0,47834,47834,64,0x7f36d050ee80,32768,0,64,0x7fbac8766e80,0,0,192,0,65536,64491,48,1460,194236443950538,194236443974218 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8502124e80,135615,0,0,65536,64048,48,1440,32768,64,0x7f9356168e80,342496,231822,3379461,16384,24720277,0,48,0,42811,42811,64,0x7f36d050ee80,32768,0,64,0x7fbac8766e80,0,0,48,0,65536,65536,0,0,194236444061258,194236444080778 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8502124e80,186340,0,0,65536,64048,48,1440,32768,64,0x7f9356168e80,338336,226328,3294963,16384,23775059,0,48,0,42291,42291,64,0x7f36d050ee80,32768,0,64,0x7fbac8766e80,0,0,48,0,65536,65536,0,0,194236444104138,194236444123338 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_2,obj_2,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f00d1958ec0,0,0,192,0,65536,64464,48,1508,64,0x7f691212cec0,393264,239949,3509115,16384,25972681,144,48,0,49157,49157,64,0x7fda1782cec0,185382,0,0,65536,64048,48,1440,32768,64,0x7f92af7d8ec0,32768,0,1410158223562739,1410158223586579 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f00d1958ec0,0,0,48,0,65536,65536,0,0,64,0x7f691212cec0,345768,232880,3415438,16384,25009377,0,48,0,43220,43220,64,0x7fda1782cec0,185605,0,0,65536,64048,48,1440,32768,64,0x7f92af7d8ec0,32768,0,1410158223606259,1410158223624819 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f00d1958ec0,0,0,48,0,65536,65536,0,0,64,0x7f691212cec0,347624,233653,3396665,16384,24934552,0,48,0,43452,43452,64,0x7fda1782cec0,193072,0,0,65536,64048,48,1440,32768,64,0x7f92af7d8ec0,32768,0,1410158223669779,1410158223688979 diff --git a/tests/workloads/ipblocks_SQC/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQC/MI100/sysinfo.csv index 7146d184e7..bd54e30e7e 100644 --- a/tests/workloads/ipblocks_SQC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQC,./tests/vcopy -n 1048576 -b 256 -i 3,sqc,Thu 07 Mar 2024 01:08:19 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQC,./tests/vcopy -n 1048576 -b 256 -i 3,sqc,Thu 21 Mar 2024 03:53:41 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQC/MI100/timestamps.csv b/tests/workloads/ipblocks_SQC/MI100/timestamps.csv index 8f9ff4ebd7..fd6ce89afc 100644 --- a/tests/workloads/ipblocks_SQC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,160402,160402,1048576,256,0,0,8,8,16,64,0x0,0x7f851f682e80,194236443922433,194236443950538,194236443974218,194236443985733 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,160402,160402,1048576,256,0,0,8,8,16,64,0x0,0x7f851f682e80,194236443988097,194236444061258,194236444080778,194236444082426 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,160402,160402,1048576,256,0,0,8,8,16,64,0x0,0x7f851f682e80,194236444093878,194236444104138,194236444123338,194236444124756 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1256022,1256022,1048576,256,0,0,8,8,16,64,0x0,0x7f14788f8ec0,1410158223536971,1410158223562739,1410158223586579,1410158223611923 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1256022,1256022,1048576,256,0,0,8,8,16,64,0x0,0x7f14788f8ec0,1410158223599148,1410158223606259,1410158223624819,1410158223664151 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1256022,1256022,1048576,256,0,0,8,8,16,64,0x0,0x7f14788f8ec0,1410158223636629,1410158223669779,1410158223688979,1410158223690340 diff --git a/tests/workloads/ipblocks_SQC/MI200/log.txt b/tests/workloads/ipblocks_SQC/MI200/log.txt new file mode 100644 index 0000000000..c6a639cf50 --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/log.txt @@ -0,0 +1,159 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQC/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sqc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_162910' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162910_4140637' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162910_4140637/input0_results_240321_162910' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162910_4140637/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162910_4140637/input0_results_240321_162910 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_162911' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162911_4140838' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162911_4140838/input0_results_240321_162911' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162911_4140838/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162911_4140838/input0_results_240321_162911 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_162911' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162911_4141039' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162911_4141039/input0_results_240321_162911' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162911_4141039/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162911_4141039/input0_results_240321_162911 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_162912' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162912_4141240' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162912_4141240/input0_results_240321_162912' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162912_4141240/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162912_4141240/input0_results_240321_162912 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQC/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_162912' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQC/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162912_4141441' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162912_4141441/input0_results_240321_162912' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162912_4141441/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162912_4141441/input0_results_240321_162912 + |-> [rocprof] File 'tests/workloads/ipblocks_SQC/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_SQC/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_SQC/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQC/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_SQC/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv index ff6a97d7d8..34f0b81369 100644 --- a/tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQC/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_1,obj_1,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,wave_size_2,obj_2,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce0fe80ec0,219376,127421,1603313,16384,10739783,168,56,0,27421,27421,64,0x7effd4f98ec0,115211,0,0,65536,63800,56,1680,32768,64,0x7f31cc13cec0,0,0,224,0,65536,64213,56,1267,64,0x7efecfec0ec0,32768,0,198704749963343,198704749983343 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce0fe80ec0,333120,218312,2747759,16384,19026276,0,56,0,41639,41639,64,0x7effd4f98ec0,219412,0,0,65536,63800,56,1680,32768,64,0x7f31cc13cec0,0,0,56,0,65536,65536,0,0,64,0x7efecfec0ec0,32768,0,198704750002383,198704750018383 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce0fe80ec0,325832,218495,2717504,16384,18986325,0,56,0,40728,40728,64,0x7effd4f98ec0,217554,0,0,65536,63800,56,1680,32768,64,0x7f31cc13cec0,0,0,56,0,65536,65536,0,0,64,0x7efecfec0ec0,32768,0,198704750078383,198704750095343 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,wave_size_2,obj_2,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3da5918ec0,32768,0,64,0x7fd4ebad4ec0,224424,130327,1642802,16384,10937071,168,56,0,28052,28052,64,0x7f263dd08ec0,0,0,224,0,65536,64231,56,1249,64,0x7fc519164ec0,116468,0,0,65536,63800,56,1680,32768,1412285098692208,1412285098712208 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3da5918ec0,32768,0,64,0x7fd4ebad4ec0,328192,218543,2720338,16384,19196225,0,56,0,41023,41023,64,0x7f263dd08ec0,0,0,56,0,65536,65536,0,0,64,0x7fc519164ec0,185773,0,0,65536,63800,56,1680,32768,1412285098799888,1412285098816368 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3da5918ec0,32768,0,64,0x7fd4ebad4ec0,331184,223084,2752641,16384,19199761,0,56,0,41397,41397,64,0x7f263dd08ec0,0,0,56,0,65536,65536,0,0,64,0x7fc519164ec0,185133,0,0,65536,63800,56,1680,32768,1412285098836688,1412285098852208 diff --git a/tests/workloads/ipblocks_SQC/MI200/roofline.csv b/tests/workloads/ipblocks_SQC/MI200/roofline.csv index 60fcbd8066..f3fea95db5 100644 --- a/tests/workloads/ipblocks_SQC/MI200/roofline.csv +++ b/tests/workloads/ipblocks_SQC/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.7397,1388.1733,1389.3062,5015.8813,5012.8813,5018.8813,9222.6709,9222.0166,9223.3252,18048.17,18047.064,18049.275,20930.85,20870.938,20990.762,20262.855,20262.229,20263.482,170394.98,170390.84,170399.12,164837.41,164832.53,164842.28,41414.047,41413.523,41414.57,41474.961,41474.348,41475.574,166325.28,165839.44,166811.12 -1,1389.2844,1388.7231,1389.8457,5028.6113,5026.665,5030.5576,9234.4121,9233.7969,9235.0273,18091.221,18088.502,18093.939,20975.447,20909.34,21041.555,20293.709,20293.186,20294.232,170842.59,170837.84,170847.34,165111.66,165108.61,165114.7,41485.648,41484.945,41486.352,41545.789,41544.871,41546.707,166902.91,166900.58,166905.23 -2,1388.4371,1387.9282,1388.946,5036.417,5034.2773,5038.5566,9257.5527,9256.7119,9258.3936,18101.041,18100.248,18101.834,21043.045,21042.604,21043.486,20343.709,20343.178,20344.24,171059.3,171054.94,171063.66,165454.78,165450.5,165459.06,41572.215,41571.301,41573.129,41629.695,41628.672,41630.719,166910.55,166325.86,167495.23 -3,1388.9329,1388.3834,1389.4823,5030.9453,5029.4277,5032.4629,9239.9854,9239.418,9240.5527,18024.152,18020.881,18027.424,21028.113,21027.771,21028.455,20310.254,20309.654,20310.854,170997,170993.67,171000.33,165191.84,165187.67,165196.02,41437.301,41285.773,41588.828,41577.523,41576.809,41578.238,166997.12,166994.06,167000.19 +0,1389.2308,1388.731,1389.7307,5018.0518,5015.0923,5021.0112,9229.8623,9229.1553,9230.5693,17723.016,17719.75,17726.281,20950.797,20890.359,21011.234,20275.492,20274.729,20276.256,170537.08,170532.8,170541.36,164953.19,164948.42,164957.95,41441.797,41441.211,41442.383,41498.809,41497.996,41499.621,166436.94,165946.03,166927.84 +1,1388.7181,1388.1539,1389.2823,5030.2666,5028.165,5032.3682,9236.1465,9235.458,9236.835,18237.061,18235.59,18238.531,20982.117,20915.217,21049.018,20296.52,20295.83,20297.209,170887.78,170883.06,170892.5,165117.86,165112.56,165123.16,41485.531,41484.715,41486.348,41546.898,41546.012,41547.785,166889.16,166885.5,166892.81 +2,1389.2806,1388.7114,1389.8499,5036.3887,5034.085,5038.6924,9261.5449,9260.7705,9262.3193,18219.48,18218.531,18220.43,21052.527,21052.045,21053.01,20351.457,20350.943,20351.971,171157.84,171153.81,171161.88,165536.23,165533.52,165538.95,41588.363,41587.68,41589.047,41646.973,41646.281,41647.664,166969.34,166377.14,167561.55 +3,1388.5833,1388.0214,1389.1451,5032.7153,5031.0347,5034.396,9236.8291,9236.0498,9237.6084,18325.926,18324.896,18326.955,21032.488,21032.219,21032.758,20310.074,20309.287,20310.861,170998.66,170995.03,171002.28,165127.77,165122.53,165133,41412.305,41258.867,41565.742,41550.141,41549.219,41551.062,166887.81,166885.11,166890.52 diff --git a/tests/workloads/ipblocks_SQC/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQC/MI200/sysinfo.csv index 5c32b483cd..094bc74263 100644 --- a/tests/workloads/ipblocks_SQC/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_SQC/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQC,./sample/vcopy -n 1048576 -b 256 -i 3,sqc|roofline,Thu 07 Mar 2024 02:22:49 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_SQC,./tests/vcopy -n 1048576 -b 256 -i 3,sqc|roofline,Thu 21 Mar 2024 04:29:10 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQC/MI200/timestamps.csv b/tests/workloads/ipblocks_SQC/MI200/timestamps.csv index 5a3983e799..ca090a2fe3 100644 --- a/tests/workloads/ipblocks_SQC/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_SQC/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,317082,317082,1048576,256,0,0,8,0,16,64,0x0,0x7f2883b64ec0,198704749934740,198704749963343,198704749983343,198704749996978 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,317082,317082,1048576,256,0,0,8,0,16,64,0x0,0x7f2883b64ec0,198704749994884,198704750002383,198704750018383,198704750077080 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,317082,317082,1048576,256,0,0,8,0,16,64,0x0,0x7f2883b64ec0,198704750029149,198704750078383,198704750095343,198704750096626 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4141601,4141601,1048576,256,0,0,8,0,16,64,0x0,0x7f066f284ec0,1412285098666513,1412285098692208,1412285098712208,1412285098724513 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4141601,4141601,1048576,256,0,0,8,0,16,64,0x0,0x7f066f284ec0,1412285098723190,1412285098799888,1412285098816368,1412285098817689 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4141601,4141601,1048576,256,0,0,8,0,16,64,0x0,0x7f066f284ec0,1412285098827377,1412285098836688,1412285098852208,1412285098853357 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv index e8982b8f0f..f3504a930b 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179219,179219,1048576,256,0,0,8,8,16,64,0x0,0x7f4fa8cdae80,48237,48237,16384,65536,12726,1616628,194296245157507,194303154953219,194303154977539,194296253306787 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179219,179219,1048576,256,0,0,8,8,16,64,0x0,0x7f4fa8cdae80,43612,43612,16384,65536,8203,1048584,194296253328137,194303155101219,194303155120099,194296253677840 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179219,179219,1048576,256,0,0,8,8,16,64,0x0,0x7f4fa8cdae80,42636,42636,16384,65536,8398,1048580,194296253711113,194303155144579,194303155163459,194296253904108 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1274827,1274827,1048576,256,0,0,8,8,16,64,0x0,0x7f4b6c978ec0,48656,48656,16384,65536,14444,1820980,1410215672123464,1410222375777291,1410222375801611,1410215679828185 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1274827,1274827,1048576,256,0,0,8,8,16,64,0x0,0x7f4b6c978ec0,43497,43497,16384,65536,8153,1048588,1410215679851769,1410222375882091,1410222375900811,1410215680166613 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1274827,1274827,1048576,256,0,0,8,8,16,64,0x0,0x7f4b6c978ec0,42257,42257,16384,65536,8106,1048580,1410215680197922,1410222375921131,1410222375939851,1410215680377952 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv index 4896b0c14e..0d528ac4c9 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179403,179403,1048576,256,0,0,8,8,16,64,0x0,0x7ffb2d164e80,0,0,0,194296741272601,194303154953219,194303154977539,194296748949056 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179403,179403,1048576,256,0,0,8,8,16,64,0x0,0x7ffb2d164e80,0,0,0,194296748969966,194303155101219,194303155120099,194296749218075 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179403,179403,1048576,256,0,0,8,8,16,64,0x0,0x7ffb2d164e80,0,0,0,194296749247321,194303155144579,194303155163459,194296749392927 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1275019,1275019,1048576,256,0,0,8,8,16,64,0x0,0x7f2338e14ec0,0,0,0,1410216152237364,1410222375777291,1410222375801611,1410216160003862 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1275019,1275019,1048576,256,0,0,8,8,16,64,0x0,0x7f2338e14ec0,0,0,0,1410216160024911,1410222375882091,1410222375900811,1410216160438401 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1275019,1275019,1048576,256,0,0,8,8,16,64,0x0,0x7f2338e14ec0,0,0,0,1410216160466724,1410222375921131,1410222375939851,1410216160612429 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv index ccc2429eed..8a293cb62d 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179603,179603,1048576,256,0,0,8,8,16,64,0x0,0x7fed1067ee80,65536,191914,24554992,194297231769678,194303154953219,194303154977539,194297239406849 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179603,179603,1048576,256,0,0,8,8,16,64,0x0,0x7fed1067ee80,65536,176036,22521432,194297239426245,194303155101219,194303155120099,194297239733517 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179603,179603,1048576,256,0,0,8,8,16,64,0x0,0x7fed1067ee80,65536,180074,23061640,194297239762101,194303155144579,194303155163459,194297239932263 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1275202,1275202,1048576,256,0,0,8,8,16,64,0x0,0x7fe25b654ec0,65536,194068,24872160,1410216632331396,1410222375777291,1410222375801611,1410216639797738 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1275202,1275202,1048576,256,0,0,8,8,16,64,0x0,0x7fe25b654ec0,65536,174548,22290936,1410216639818056,1410222375882091,1410222375900811,1410216640122441 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1275202,1275202,1048576,256,0,0,8,8,16,64,0x0,0x7fe25b654ec0,65536,197734,25315080,1410216640150874,1410222375921131,1410222375939851,1410216640318921 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv index 31d386d446..616363c7f7 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179787,179787,1048576,256,0,0,8,8,16,64,0x0,0x7f7116630e80,32768,662899,84848352,194297721610422,194303154953219,194303154977539,194297729775242 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179787,179787,1048576,256,0,0,8,8,16,64,0x0,0x7f7116630e80,32768,678115,86800424,194297729793015,194303155101219,194303155120099,194297730132308 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179787,179787,1048576,256,0,0,8,8,16,64,0x0,0x7f7116630e80,32768,670499,85820956,194297730160451,194303155144579,194303155163459,194297730337426 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1275385,1275385,1048576,256,0,0,8,8,16,64,0x0,0x7f3140e9cec0,32768,650161,83216288,1410217111031590,1410222375777291,1410222375801611,1410217118777409 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1275385,1275385,1048576,256,0,0,8,8,16,64,0x0,0x7f3140e9cec0,32768,652355,83502592,1410217118797567,1410222375882091,1410222375900811,1410217119097242 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1275385,1275385,1048576,256,0,0,8,8,16,64,0x0,0x7f3140e9cec0,32768,659013,84358620,1410217119125435,1410222375921131,1410222375939851,1410217119292791 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv index b534b5f98f..61c024ddc1 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,179971,179971,1048576,256,0,0,8,8,16,64,0x0,0x7f93969ece80,47115,47115,16580,376928,16384,24402873,228411,0,98111176,194298215596255,194303154953219,194303154977539,194298223228756 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,179971,179971,1048576,256,0,0,8,8,16,64,0x0,0x7f93969ece80,42027,42027,14108,336224,16384,23800432,225815,0,95691556,194298223258402,194303155101219,194303155120099,194298223587736 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,179971,179971,1048576,256,0,0,8,8,16,64,0x0,0x7f93969ece80,41914,41914,13672,335320,16384,23933998,225355,0,96226252,194298223626329,194303155144579,194303155163459,194298223811700 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1275571,1275571,1048576,256,0,0,8,8,16,64,0x0,0x7f7ec46b0ec0,48374,48374,15786,387000,16384,25145543,235038,0,101113104,1410217592118796,1410222375777291,1410222375801611,1410217599665048 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1275571,1275571,1048576,256,0,0,8,8,16,64,0x0,0x7f7ec46b0ec0,43557,43557,14022,348464,16384,24571833,238270,0,98814560,1410217599696027,1410222375882091,1410222375900811,1410217599999108 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1275571,1275571,1048576,256,0,0,8,8,16,64,0x0,0x7f7ec46b0ec0,43386,43386,13410,347096,16384,24673922,236486,0,99218352,1410217600037350,1410222375921131,1410222375939851,1410217600204135 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/log.txt b/tests/workloads/ipblocks_SQ_CPC/MI100/log.txt new file mode 100644 index 0000000000..fbe8eaba84 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/log.txt @@ -0,0 +1,447 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_CPC/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'cpc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155441' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155441_1274667' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155441_1274667/input0_results_240321_155441' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155441_1274667/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155441_1274667/input0_results_240321_155441 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155442' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155442_1274859' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155442_1274859/input0_results_240321_155442' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155442_1274859/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155442_1274859/input0_results_240321_155442 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155442' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155442_1275042' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155442_1275042/input0_results_240321_155442' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155442_1275042/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155442_1275042/input0_results_240321_155442 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155443' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155443_1275225' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155443_1275225/input0_results_240321_155443' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155443_1275225/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155443_1275225/input0_results_240321_155443 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155443' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155443_1275411' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155443_1275411/input0_results_240321_155443' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155443_1275411/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155443_1275411/input0_results_240321_155443 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155444' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155444_1275595' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155444_1275595/input0_results_240321_155444' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155444_1275595/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155444_1275595/input0_results_240321_155444 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155444' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155444_1275781' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155444_1275781/input0_results_240321_155444' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155444_1275781/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155444_1275781/input0_results_240321_155444 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155445' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155445_1275964' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155445_1275964/input0_results_240321_155445' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155445_1275964/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155445_1275964/input0_results_240321_155445 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155445' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155445_1276147' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155445_1276147/input0_results_240321_155445' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155445_1276147/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155445_1276147/input0_results_240321_155445 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155445' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155445_1276332' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155445_1276332/input0_results_240321_155445' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155445_1276332/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155445_1276332/input0_results_240321_155445 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155446' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155446_1276516' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155446_1276516/input0_results_240321_155446' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155446_1276516/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, CPC_ME1_DC0_SPI_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155446_1276516/input0_results_240321_155446 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155446' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155446_1276699' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155446_1276699/input0_results_240321_155446' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155446_1276699/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155446_1276699/input0_results_240321_155446 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155447' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155447_1276884' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155447_1276884/input0_results_240321_155447' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155447_1276884/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155447_1276884/input0_results_240321_155447 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155447' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155447_1277067' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155447_1277067/input0_results_240321_155447' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155447_1277067/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155447_1277067/input0_results_240321_155447 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155448' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155448_1277254' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155448_1277254/input0_results_240321_155448' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155448_1277254/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155448_1277254/input0_results_240321_155448 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf.csv index 6afb61f1a9..31901d227b 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,wave_size_1,obj_1,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,wave_size_2,obj_2,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_3,obj_3,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_5,obj_5,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_6,obj_6,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_7,obj_7,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,CPC_ME1_DC0_SPI_BUSY,wave_size_8,obj_8,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7de483ee80,0,65536,64420,48,1512,184781,0,0,64,0x7fc02916ae80,0,131072,144,48,0,0,0,192,64,0x7fd39d668e80,25190401,22862816,1967137,360448,3464068,163840,0,0,9922,550,64,0x7f2836094e80,65536,64048,48,1440,32768,32768,0,64,0x7fcaf0230e80,386640,236679,16384,16384,16384,32768,49152,0,48329,48329,48329,0,64,0x7f7cff96ae80,65536,32768,0,0,0,16384,16384,393216,538,48520,64,0x7f5cc86cee80,49152,11534336,65536,0,0,0,16384,0,0,17178,64,0x7faf9f4f8e80,0,0,0,1048576,0,0,0,0,26608,64,0x7f39e9cf0e80,180224,114688,0,32768,32768,16384,16384,65536,913,46716,194303154953219,194303154977539 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7de483ee80,0,65536,65536,0,0,189056,0,0,64,0x7fc02916ae80,0,131072,0,48,0,0,0,48,64,0x7fd39d668e80,24542210,23002282,1179480,360448,3326223,163840,0,0,8528,2446,64,0x7f2836094e80,65536,64048,48,1440,32768,32768,0,64,0x7fcaf0230e80,339080,229752,16384,16384,16384,32768,49152,0,42384,42384,42384,0,64,0x7f7cff96ae80,65536,32768,0,0,0,16384,16384,393216,458,42952,64,0x7f5cc86cee80,49152,11534336,65536,0,0,0,16384,0,0,13929,64,0x7faf9f4f8e80,0,0,0,1048576,0,0,0,0,26163,64,0x7f39e9cf0e80,180224,114688,0,32768,32768,16384,16384,65536,3403,39353,194303155101219,194303155120099 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7de483ee80,0,65536,65536,0,0,188847,0,0,64,0x7fc02916ae80,0,131072,0,48,0,0,0,48,64,0x7fd39d668e80,24773562,22908769,1504345,360448,3353456,163840,0,0,8561,2448,64,0x7f2836094e80,65536,64048,48,1440,32768,32768,0,64,0x7fcaf0230e80,340424,229204,16384,16384,16384,32768,49152,0,42552,42552,42552,0,64,0x7f7cff96ae80,65536,32768,0,0,0,16384,16384,393216,458,42745,64,0x7f5cc86cee80,49152,11534336,65536,0,0,0,16384,0,0,13916,64,0x7faf9f4f8e80,0,0,0,1048576,0,0,0,0,26695,64,0x7f39e9cf0e80,180224,114688,0,32768,32768,16384,16384,65536,3197,39311,194303155144579,194303155163459 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_1,obj_1,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,wave_size_2,obj_2,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,CPC_ME1_DC0_SPI_BUSY,wave_size_3,obj_3,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_4,obj_4,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_6,obj_6,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,wave_size_8,obj_8,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7367e2cec0,65536,32768,0,0,0,16384,16384,393216,539,48237,64,0x7f17ab8acec0,0,131072,144,48,0,0,0,192,64,0x7fd2d09bcec0,0,0,0,1048576,0,0,0,0,25884,64,0x7f5bfe3d8ec0,180224,114688,0,32768,32768,16384,16384,65536,913,47394,64,0x7fab8f51cec0,65536,64048,48,1440,32768,32768,0,64,0x7f5b4fdd8ec0,390728,241704,16384,16384,16384,32768,49152,0,48840,48840,48840,0,64,0x7f8fd57d8ec0,49152,11534336,65536,0,0,0,16384,0,0,17751,64,0x7fbe215c0ec0,0,65536,64376,48,1476,200225,0,0,64,0x7fba5caa0ec0,25008982,22219277,2429257,360448,3418842,163840,0,0,10135,588,1410222375777291,1410222375801611 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7367e2cec0,65536,32768,0,0,0,16384,16384,393216,457,42609,64,0x7f17ab8acec0,0,131072,0,48,0,0,0,48,64,0x7fd2d09bcec0,0,0,0,1048576,0,0,0,0,25092,64,0x7f5bfe3d8ec0,180224,114688,0,32768,32768,16384,16384,65536,2693,40196,64,0x7fab8f51cec0,65536,64048,48,1440,32768,32768,0,64,0x7f5b4fdd8ec0,353032,239682,16384,16384,16384,32768,49152,0,44128,44128,44128,0,64,0x7f8fd57d8ec0,49152,11534336,65536,0,0,0,16384,0,0,14036,64,0x7fbe215c0ec0,0,65536,65536,0,0,194802,0,0,64,0x7fba5caa0ec0,25039340,22542316,2136576,360448,3409344,163840,0,0,8517,2436,1410222375882091,1410222375900811 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7367e2cec0,65536,32768,0,0,0,16384,16384,393216,457,42137,64,0x7f17ab8acec0,0,131072,0,48,0,0,0,48,64,0x7fd2d09bcec0,0,0,0,1048576,0,0,0,0,25337,64,0x7f5bfe3d8ec0,180224,114688,0,32768,32768,16384,16384,65536,2718,39766,64,0x7fab8f51cec0,65536,64048,48,1440,32768,32768,0,64,0x7f5b4fdd8ec0,347760,238950,16384,16384,16384,32768,49152,0,43469,43469,43469,0,64,0x7f8fd57d8ec0,49152,11534336,65536,0,0,0,16384,0,0,14252,64,0x7fbe215c0ec0,0,65536,65536,0,0,193806,0,0,64,0x7fba5caa0ec0,25016939,22467331,2189160,360448,3405503,163840,0,0,8573,2436,1410222375921131,1410222375939851 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv index d15e30ddd0..e4b0aff7f9 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|cpc,Thu 07 Mar 2024 01:09:21 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|cpc,Thu 21 Mar 2024 03:54:41 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv index a74ac54706..f1984fc3c4 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,181828,181828,1048576,256,0,0,8,8,16,64,0x0,0x7faed23dce80,194303154921411,194303154953219,194303154977539,194303154991624 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,181828,181828,1048576,256,0,0,8,8,16,64,0x0,0x7faed23dce80,194303154992265,194303155101219,194303155120099,194303155121700 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,181828,181828,1048576,256,0,0,8,8,16,64,0x0,0x7faed23dce80,194303155133332,194303155144579,194303155163459,194303155164551 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1277414,1277414,1048576,256,0,0,8,8,16,64,0x0,0x7f6caa578ec0,1410222375751540,1410222375777291,1410222375801611,1410222375812585 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1277414,1277414,1048576,256,0,0,8,8,16,64,0x0,0x7f6caa578ec0,1410222375814328,1410222375882091,1410222375900811,1410222375902114 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1277414,1277414,1048576,256,0,0,8,8,16,64,0x0,0x7f6caa578ec0,1410222375912904,1410222375921131,1410222375939851,1410222375941127 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv index ae6276d011..789bc05d73 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340095,340095,1048576,256,0,0,8,0,16,64,0x0,0x7fbfbed34ec0,27545,27545,16384,65536,13794,1537480,199346183656323,199354805603573,199354805623573,199346199519652 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340095,340095,1048576,256,0,0,8,0,16,64,0x0,0x7fbfbed34ec0,39996,39996,16384,65536,9115,1048660,199346199542595,199354805693333,199354805709493,199346199799782 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340095,340095,1048576,256,0,0,8,0,16,64,0x0,0x7fbfbed34ec0,40217,40217,16384,65536,9662,1048624,199346199830089,199354805729173,199354805744853,199346199968210 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4164530,4164530,1048576,256,0,0,8,0,16,64,0x0,0x7f176e708ec0,27485,27485,16384,65536,13576,1494700,1412925824031427,1412934514038602,1412934514058922,1412925840286978 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4164530,4164530,1048576,256,0,0,8,0,16,64,0x0,0x7f176e708ec0,42138,42138,16384,65536,9318,1048704,1412925840308168,1412934514077322,1412934514092842,1412925840620288 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4164530,4164530,1048576,256,0,0,8,0,16,64,0x0,0x7f176e708ec0,41528,41528,16384,65536,9188,1048716,1412925840649934,1412934514205322,1412934514221802,1412925840807041 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv index c49f56e0fb..3d37695465 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340296,340296,1048576,256,0,0,8,0,16,64,0x0,0x7f2cae3d8ec0,0,0,0,199346665525434,199354805603573,199354805623573,199346681607207 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340296,340296,1048576,256,0,0,8,0,16,64,0x0,0x7f2cae3d8ec0,0,0,0,199346681627014,199354805693333,199354805709493,199346681918365 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340296,340296,1048576,256,0,0,8,0,16,64,0x0,0x7f2cae3d8ec0,0,0,0,199346681944725,199354805729173,199354805744853,199346682095040 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4164716,4164716,1048576,256,0,0,8,0,16,64,0x0,0x7f6c12644ec0,0,0,0,1412926306920996,1412934514038602,1412934514058922,1412926322924491 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4164716,4164716,1048576,256,0,0,8,0,16,64,0x0,0x7f6c12644ec0,0,0,0,1412926322944408,1412934514077322,1412934514092842,1412926323219258 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4164716,4164716,1048576,256,0,0,8,0,16,64,0x0,0x7f6c12644ec0,0,0,0,1412926323245568,1412934514205322,1412934514221802,1412926323404970 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv index 809ba6c7f6..e03a3b4e18 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340481,340481,1048576,256,0,0,8,0,16,64,0x0,0x7f1759bd4ec0,65536,178848,20060256,199347149054236,199354805603573,199354805623573,199347165898721 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340481,340481,1048576,256,0,0,8,0,16,64,0x0,0x7f1759bd4ec0,65536,240092,26751520,199347165915412,199354805693333,199354805709493,199347166219187 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340481,340481,1048576,256,0,0,8,0,16,64,0x0,0x7f1759bd4ec0,65536,273970,30599728,199347166245417,199354805729173,199354805744853,199347166403686 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4164917,4164917,1048576,256,0,0,8,0,16,64,0x0,0x7ff7803bcec0,65536,173906,19469000,1412926787927194,1412934514038602,1412934514058922,1412926803915500 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4164917,4164917,1048576,256,0,0,8,0,16,64,0x0,0x7ff7803bcec0,65536,228750,25585360,1412926803933764,1412934514077322,1412934514092842,1412926804365791 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4164917,4164917,1048576,256,0,0,8,0,16,64,0x0,0x7ff7803bcec0,65536,227612,25430520,1412926804391921,1412934514205322,1412934514221802,1412926804552384 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv index 7118877eb0..c5934d77a1 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340665,340665,1048576,256,0,0,8,0,16,64,0x0,0x7ff7d7298ec0,32768,294077,32921148,199347626702343,199354805603573,199354805623573,199347642382786 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340665,340665,1048576,256,0,0,8,0,16,64,0x0,0x7ff7d7298ec0,32768,588434,65913900,199347642400749,199354805693333,199354805709493,199347642690558 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340665,340665,1048576,256,0,0,8,0,16,64,0x0,0x7ff7d7298ec0,32768,581140,65092960,199347642716938,199354805729173,199354805744853,199347642866701 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4165103,4165103,1048576,256,0,0,8,0,16,64,0x0,0x7f17f55d8ec0,32768,287054,32154080,1412927278551320,1412934514038602,1412934514058922,1412927294391536 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4165103,4165103,1048576,256,0,0,8,0,16,64,0x0,0x7f17f55d8ec0,32768,585910,65632292,1412927294411464,1412934514077322,1412934514092842,1412927294680994 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4165103,4165103,1048576,256,0,0,8,0,16,64,0x0,0x7f17f55d8ec0,32768,562922,63053152,1412927294706903,1412934514205322,1412934514221802,1412927294860092 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv index 1dc2e3cc83..2f26f8273d 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,340850,340850,1048576,256,0,0,8,0,16,64,0x0,0x7fb581614ec0,27751,27751,10948,222016,16384,11022828,130256,0,44587476,199348107548679,199354805603573,199354805623573,199348123449429 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,340850,340850,1048576,256,0,0,8,0,16,64,0x0,0x7fb581614ec0,41274,41274,14375,330200,16384,18889989,221826,0,76041052,199348123477242,199354805693333,199354805709493,199348123798940 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,340850,340850,1048576,256,0,0,8,0,16,64,0x0,0x7fb581614ec0,41644,41644,14220,333160,16384,19526078,223830,0,78584000,199348123833596,199354805729173,199354805744853,199348123999540 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4165304,4165304,1048576,256,0,0,8,0,16,64,0x0,0x7fedf5e48ec0,27360,27360,11139,218888,16384,10377348,124660,0,42010824,1412927766646114,1412934514038602,1412934514058922,1412927783485309 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4165304,4165304,1048576,256,0,0,8,0,16,64,0x0,0x7fedf5e48ec0,39187,39187,12796,313504,16384,18642592,213434,0,75058884,1412927783511228,1412934514077322,1412934514092842,1412927783829650 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4165304,4165304,1048576,256,0,0,8,0,16,64,0x0,0x7fedf5e48ec0,39774,39774,12782,318200,16384,19044010,217621,0,76641068,1412927783865087,1412934514205322,1412934514221802,1412927784032904 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/log.txt b/tests/workloads/ipblocks_SQ_CPC/MI200/log.txt new file mode 100644 index 0000000000..87a7b49804 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/log.txt @@ -0,0 +1,565 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_CPC/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'cpc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_163953' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163953_4164370' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163953_4164370/input0_results_240321_163953' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163953_4164370/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163953_4164370/input0_results_240321_163953 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_163954' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163954_4164556' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163954_4164556/input0_results_240321_163954' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163954_4164556/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163954_4164556/input0_results_240321_163954 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_163954' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163954_4164757' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163954_4164757/input0_results_240321_163954' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163954_4164757/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163954_4164757/input0_results_240321_163954 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_163955' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163955_4164943' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163955_4164943/input0_results_240321_163955' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163955_4164943/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163955_4164943/input0_results_240321_163955 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_163955' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163955_4165144' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163955_4165144/input0_results_240321_163955' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163955_4165144/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163955_4165144/input0_results_240321_163955 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_163956' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163956_4165332' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163956_4165332/input0_results_240321_163956' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163956_4165332/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163956_4165332/input0_results_240321_163956 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_163956' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163956_4165519' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163956_4165519/input0_results_240321_163956' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163956_4165519/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163956_4165519/input0_results_240321_163956 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_163957' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163957_4165702' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163957_4165702/input0_results_240321_163957' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163957_4165702/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163957_4165702/input0_results_240321_163957 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_163957' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163957_4165889' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163957_4165889/input0_results_240321_163957' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163957_4165889/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163957_4165889/input0_results_240321_163957 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_163957' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163957_4166076' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163957_4166076/input0_results_240321_163957' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163957_4166076/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163957_4166076/input0_results_240321_163957 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_163958' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163958_4166262' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163958_4166262/input0_results_240321_163958' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163958_4166262/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163958_4166262/input0_results_240321_163958 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_163958' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163958_4166449' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163958_4166449/input0_results_240321_163958' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163958_4166449/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163958_4166449/input0_results_240321_163958 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_163959' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163959_4166650' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163959_4166650/input0_results_240321_163959' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163959_4166650/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163959_4166650/input0_results_240321_163959 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_163959' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163959_4166835' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163959_4166835/input0_results_240321_163959' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163959_4166835/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, CPC_ME1_DC0_SPI_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163959_4166835/input0_results_240321_163959 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_164000' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164000_4167020' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164000_4167020/input0_results_240321_164000' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164000_4167020/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164000_4167020/input0_results_240321_164000 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_164000' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164000_4167205' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164000_4167205/input0_results_240321_164000' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164000_4167205/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164000_4167205/input0_results_240321_164000 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_164001' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164001_4167389' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164001_4167389/input0_results_240321_164001' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164001_4167389/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164001_4167389/input0_results_240321_164001 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_164001' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164001_4167590' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164001_4167590/input0_results_240321_164001' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164001_4167590/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164001_4167590/input0_results_240321_164001 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_164002' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_CPC/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164002_4167775' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164002_4167775/input0_results_240321_164002' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164002_4167775/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164002_4167775/input0_results_240321_164002 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_SQ_CPC/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf.csv index e3d61d14b5..4535ac8875 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,wave_size_1,obj_1,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_2,obj_2,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_6,obj_6,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_7,obj_7,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_8,obj_8,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_9,obj_9,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_10,obj_10,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,CPC_ME1_DC0_SPI_BUSY,wave_size_11,obj_11,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,wave_size_12,obj_12,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5c00d38ec0,0,0,1048576,0,0,0,0,0,64,0x7f969f5b8ec0,32768,32768,0,64,0x7f4f8e064ec0,65536,0,0,0,16384,16384,0,0,64,0x7f8b5522cec0,1309,118813,0,0,65536,63800,56,1680,64,0x7f01b1a78ec0,0,0,0,0,0,0,0,0,352,26713,64,0x7fd799508ec0,0,0,0,0,0,0,168,56,64,0x7f2fd4028ec0,0,0,0,0,114688,0,65536,32768,6975,545,64,0x7f92067f8ec0,0,0,0,224,0,65536,64281,56,64,0x7f07c3da4ec0,0,0,0,16384,16384,10962787,9750506,868217,819,27095,64,0x7f1dfa30cec0,344064,222320,129677,1638076,0,0,163840,114688,0,10897,64,0x7f2afe650ec0,0,32768,32768,16384,16384,65536,49152,10485760,14976,64,0x7fe928480ec0,131072,0,0,0,0,0,0,0,64,0x7f2dd787cec0,0,16384,16384,32768,49152,0,393216,163840,28084,28084,28084,0,199354805603573,199354805623573 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5c00d38ec0,0,0,1048576,0,0,0,0,0,64,0x7f969f5b8ec0,32768,32768,0,64,0x7f4f8e064ec0,65536,0,0,0,16384,16384,0,0,64,0x7f8b5522cec0,0,184208,0,0,65536,63800,56,1680,64,0x7f01b1a78ec0,0,0,0,0,0,0,0,0,302,40076,64,0x7fd799508ec0,0,0,0,0,0,0,0,56,64,0x7f2fd4028ec0,0,0,0,0,114688,0,65536,32768,9493,3123,64,0x7f92067f8ec0,0,0,0,56,0,65536,65536,0,64,0x7f07c3da4ec0,0,0,0,16384,16384,20187209,18709486,1133659,3400,39163,64,0x7f1dfa30cec0,344064,335088,226311,2849726,0,0,163840,114688,0,13257,64,0x7f2afe650ec0,0,32768,32768,16384,16384,65536,49152,10485760,25389,64,0x7fe928480ec0,131072,0,0,0,0,0,0,0,64,0x7f2dd787cec0,0,16384,16384,32768,49152,0,393216,163840,43103,43103,43103,0,199354805693333,199354805709493 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5c00d38ec0,0,0,1048576,0,0,0,0,0,64,0x7f969f5b8ec0,32768,32768,0,64,0x7f4f8e064ec0,65536,0,0,0,16384,16384,0,0,64,0x7f8b5522cec0,0,186988,0,0,65536,63800,56,1680,64,0x7f01b1a78ec0,0,0,0,0,0,0,0,0,302,40301,64,0x7fd799508ec0,0,0,0,0,0,0,0,56,64,0x7f2fd4028ec0,0,0,0,0,114688,0,65536,32768,9501,3093,64,0x7f92067f8ec0,0,0,0,56,0,65536,65536,0,64,0x7f07c3da4ec0,0,0,0,16384,16384,19566197,18340038,882095,3396,38395,64,0x7f1dfa30cec0,344064,329504,221551,2765990,0,0,163840,114688,0,13935,64,0x7f2afe650ec0,0,32768,32768,16384,16384,65536,49152,10485760,25246,64,0x7fe928480ec0,131072,0,0,0,0,0,0,0,64,0x7f2dd787cec0,0,16384,16384,32768,49152,0,393216,163840,43655,43655,43655,0,199354805729173,199354805744853 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_1,obj_1,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_3,obj_3,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_4,obj_4,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_6,obj_6,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_7,obj_7,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,wave_size_8,obj_8,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,CPC_ME1_DC0_SPI_BUSY,wave_size_9,obj_9,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,wave_size_10,obj_10,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_11,obj_11,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_12,obj_12,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fc63d6ccec0,0,0,0,224,0,65536,64243,56,64,0x7fdefb224ec0,0,0,1048576,0,0,0,0,0,64,0x7f00a4644ec0,0,0,0,0,114688,0,65536,32768,7173,551,64,0x7f01be7c0ec0,344064,226496,133268,1682303,0,0,163840,114688,0,10913,64,0x7f7f54c60ec0,1230,128065,0,0,65536,63800,56,1680,64,0x7f0565320ec0,32768,32768,0,64,0x7fac20860ec0,0,0,0,0,0,0,168,56,64,0x7f6020100ec0,131072,0,0,0,0,0,0,0,64,0x7f6cb90b0ec0,0,32768,32768,16384,16384,65536,49152,10485760,15199,64,0x7f92e4060ec0,65536,0,0,0,16384,16384,0,0,64,0x7fb6d2d04ec0,0,0,0,0,0,0,0,0,352,27556,64,0x7f2b27304ec0,0,0,0,16384,16384,10615939,9570523,701352,819,26584,64,0x7fea9309cec0,0,16384,16384,32768,49152,0,393216,163840,28173,28173,28173,0,1412934514038602,1412934514058922 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fc63d6ccec0,0,0,0,56,0,65536,65536,0,64,0x7fdefb224ec0,0,0,1048576,0,0,0,0,0,64,0x7f00a4644ec0,0,0,0,0,114688,0,65536,32768,9640,2443,64,0x7f01be7c0ec0,344064,341728,230340,2879275,0,0,163840,114688,0,14311,64,0x7f7f54c60ec0,0,206510,0,0,65536,63800,56,1680,64,0x7f0565320ec0,32768,32768,0,64,0x7fac20860ec0,0,0,0,0,0,0,0,56,64,0x7f6020100ec0,131072,0,0,0,0,0,0,0,64,0x7f6cb90b0ec0,0,32768,32768,16384,16384,65536,49152,10485760,26262,64,0x7f92e4060ec0,65536,0,0,0,16384,16384,0,0,64,0x7fb6d2d04ec0,0,0,0,0,0,0,0,0,302,41740,64,0x7f2b27304ec0,0,0,0,16384,16384,19104084,17957546,802474,2715,38562,64,0x7fea9309cec0,0,16384,16384,32768,49152,0,393216,163840,41943,41943,41943,0,1412934514077322,1412934514092842 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fc63d6ccec0,0,0,0,56,0,65536,65536,0,64,0x7fdefb224ec0,0,0,1048576,0,0,0,0,0,64,0x7f00a4644ec0,0,0,0,0,114688,0,65536,32768,9799,2430,64,0x7f01be7c0ec0,344064,334496,224751,2797956,0,0,163840,114688,0,14267,64,0x7f7f54c60ec0,0,203870,0,0,65536,63800,56,1680,64,0x7f0565320ec0,32768,32768,0,64,0x7fac20860ec0,0,0,0,0,0,0,0,56,64,0x7f6020100ec0,131072,0,0,0,0,0,0,0,64,0x7f6cb90b0ec0,0,32768,32768,16384,16384,65536,49152,10485760,25200,64,0x7f92e4060ec0,65536,0,0,0,16384,16384,0,0,64,0x7fb6d2d04ec0,0,0,0,0,0,0,0,0,302,40806,64,0x7f2b27304ec0,0,0,0,16384,16384,18864554,17754994,765496,2839,38317,64,0x7fea9309cec0,0,16384,16384,32768,49152,0,393216,163840,41878,41878,41878,0,1412934514205322,1412934514221802 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/roofline.csv index 6eee7a1e9c..fcf4d895ff 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/roofline.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.4314,1387.9395,1388.9233,5015.6025,5012.6465,5018.5586,9222.3379,9221.7363,9222.9395,18050.59,18049.518,18051.662,20929.807,20867.709,20991.904,20262.221,20261.627,20262.814,170387.2,170383.38,170391.03,164851.75,164847.52,164855.98,41416.543,41415.984,41417.102,41473.898,41473.359,41474.438,166320.42,165829.55,166811.3 -1,1389.0236,1388.483,1389.5641,5027.7773,5025.6187,5029.936,9233.9785,9233.334,9234.623,18091.418,18088.111,18094.725,20974.865,20908.154,21041.576,20295.217,20294.699,20295.734,170844.5,170840.8,170848.2,165102.59,165099.59,165105.59,41483.016,41482.293,41483.738,41542.473,41541.531,41543.414,166885.02,166882.05,166887.98 -2,1389.0247,1388.4352,1389.6141,5037.124,5034.7544,5039.4937,9263.2285,9262.3828,9264.0742,18109.248,18108.34,18110.156,21052.637,21052.268,21053.006,20357.676,20357.145,20358.207,171147.55,171144.06,171151.03,165545,165541.28,165548.72,41594.102,41593.266,41594.938,41649.09,41648.023,41650.156,167005.12,166409.08,167601.17 -3,1389.4426,1388.9342,1389.951,5033.2988,5031.9365,5034.6611,9242.4365,9241.75,9243.123,18030.496,18027.463,18033.529,21037.92,21037.492,21038.348,20317.32,20316.609,20318.031,171048.77,171045.73,171051.8,165249.95,165246.5,165253.41,41449.465,41294.613,41604.316,41588.441,41587.867,41589.016,167047.19,167045.06,167049.31 +0,1388.6853,1388.1606,1389.21,5018.7529,5015.8857,5021.6201,9228.6338,9227.9307,9229.3369,17719.479,17716.539,17722.418,20947.072,20886.713,21007.432,20275.988,20275.467,20276.51,170528.58,170524.58,170532.58,164927.94,164922.3,164933.58,41437.145,41436.664,41437.625,41494.141,41493.547,41494.734,166420.23,165930.94,166909.53 +1,1388.7947,1388.2532,1389.3362,5027.4634,5025.5957,5029.3311,9231.8896,9231.3428,9232.4365,18227.756,18226.002,18229.51,20970.895,20904.359,21037.43,20289.17,20288.576,20289.764,170791.45,170787.66,170795.25,165071.22,165067.25,165075.19,41476.594,41475.988,41477.199,41535.078,41534.426,41535.73,166851.22,166849.16,166853.28 +2,1388.7842,1388.2498,1389.3186,5036.0425,5033.752,5038.333,9260.5479,9259.9697,9261.126,18218.117,18217.098,18219.137,21048.176,21047.707,21048.645,20349.758,20349.158,20350.357,171118.98,171115.27,171122.7,165512.05,165508.78,165515.31,41582.883,41582.281,41583.484,41639.078,41638.305,41639.852,166943.39,166346.77,167540.02 +3,1388.8778,1388.3442,1389.4114,5033.0928,5031.3877,5034.7979,9238.9961,9238.2793,9239.7129,18329.318,18328.463,18330.174,21033.25,21032.904,21033.596,20308.471,20307.846,20309.096,171031.56,171026.42,171036.7,165162.27,165158.47,165166.06,41427.566,41273.59,41581.543,41576.848,41575.664,41578.031,166964.67,166960.58,166968.77 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv index af00d1fd25..c82264ede6 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_CPC,./sample/vcopy -n 1048576 -b 256 -i 3,sq|cpc|roofline,Thu 07 Mar 2024 02:33:33 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_SQ_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|cpc|roofline,Thu 21 Mar 2024 04:39:52 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv index 6164bfea33..49e83c5617 100644 --- a/tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_CPC/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,343486,343486,1048576,256,0,0,8,0,16,64,0x0,0x7f55a444cec0,199354805579822,199354805603573,199354805623573,199354805635117 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,343486,343486,1048576,256,0,0,8,0,16,64,0x0,0x7f55a444cec0,199354805634415,199354805693333,199354805709493,199354805710539 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,343486,343486,1048576,256,0,0,8,0,16,64,0x0,0x7f55a444cec0,199354805720829,199354805729173,199354805744853,199354805745776 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4167935,4167935,1048576,256,0,0,8,0,16,64,0x0,0x7f024c07cec0,1412934514014149,1412934514038602,1412934514058922,1412934514091646 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4167935,4167935,1048576,256,0,0,8,0,16,64,0x0,0x7f024c07cec0,1412934514070275,1412934514077322,1412934514092842,1412934514199640 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4167935,4167935,1048576,256,0,0,8,0,16,64,0x0,0x7f024c07cec0,1412934514103288,1412934514205322,1412934514221802,1412934514222824 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv index fefe68ca0a..d753c2b1c4 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,134626,134626,1048576,256,0,0,8,8,16,64,0x0,0x7f7f2ff9ae80,48131,48131,16384,65536,12910,1645524,194154641852352,194161603172864,194161603197984,194154649704009 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,134626,134626,1048576,256,0,0,8,8,16,64,0x0,0x7f7f2ff9ae80,42906,42906,16384,65536,8228,1048580,194154649726401,194161603299102,194161603318622,194154650043171 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,134626,134626,1048576,256,0,0,8,8,16,64,0x0,0x7f7f2ff9ae80,42538,42538,16384,65536,8309,1048580,194154650085221,194161603339422,194161603358782,194154650269850 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1230377,1230377,1048576,256,0,0,8,8,16,64,0x0,0x7fe864458ec0,49877,49877,16384,65536,14566,1866920,1410080046068187,1410086759522522,1410086759546522,1410080053693468 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1230377,1230377,1048576,256,0,0,8,8,16,64,0x0,0x7fe864458ec0,43218,43218,16384,65536,7991,1048580,1410080053717122,1410086759649082,1410086759668282,1410080054054599 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1230377,1230377,1048576,256,0,0,8,8,16,64,0x0,0x7fe864458ec0,43505,43505,16384,65536,8237,1048576,1410080054086609,1410086759687162,1410086759706362,1410080054268843 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv index 1d04feffad..11fb30e8f6 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,134813,134813,1048576,256,0,0,8,8,16,64,0x0,0x7f05c5dcce80,0,0,0,194155149233598,194161603172864,194161603197984,194155156840731 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,134813,134813,1048576,256,0,0,8,8,16,64,0x0,0x7f05c5dcce80,0,0,0,194155156859918,194161603299102,194161603318622,194155157181146 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,134813,134813,1048576,256,0,0,8,8,16,64,0x0,0x7f05c5dcce80,0,0,0,194155157209219,194161603339422,194161603358782,194155157389641 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1230560,1230560,1048576,256,0,0,8,8,16,64,0x0,0x7f9f88644ec0,0,0,0,1410080529026549,1410086759522522,1410086759546522,1410080536619810 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1230560,1230560,1048576,256,0,0,8,8,16,64,0x0,0x7f9f88644ec0,0,0,0,1410080536630380,1410086759649082,1410086759668282,1410080536929144 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1230560,1230560,1048576,256,0,0,8,8,16,64,0x0,0x7f9f88644ec0,0,0,0,1410080536956816,1410086759687162,1410086759706362,1410080537126686 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv index f32d70fb64..1da676fedd 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,135010,135010,1048576,256,0,0,8,8,16,64,0x0,0x7f8d722cee80,65536,186144,23831152,194155648390291,194161603172864,194161603197984,194155656189689 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,135010,135010,1048576,256,0,0,8,8,16,64,0x0,0x7f8d722cee80,65536,162520,20755640,194155656209657,194161603299102,194161603318622,194155656532107 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,135010,135010,1048576,256,0,0,8,8,16,64,0x0,0x7f8d722cee80,65536,165198,21102216,194155656561563,194161603339422,194161603358782,194155656745271 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1230761,1230761,1048576,256,0,0,8,8,16,64,0x0,0x7f926f718ec0,65536,197734,25202896,1410081003501062,1410086759522522,1410086759546522,1410081011001047 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1230761,1230761,1048576,256,0,0,8,8,16,64,0x0,0x7f926f718ec0,65536,168908,21640080,1410081011019902,1410086759649082,1410086759668282,1410081011329797 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1230761,1230761,1048576,256,0,0,8,8,16,64,0x0,0x7f926f718ec0,65536,173848,22293512,1410081011358150,1410086759687162,1410086759706362,1410081011523853 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv index 156c7a6aa7..9875e28346 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,135197,135197,1048576,256,0,0,8,8,16,64,0x0,0x7f29c5cd8e80,32768,668934,85616252,194156148107576,194161603172864,194161603197984,194156155682769 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,135197,135197,1048576,256,0,0,8,8,16,64,0x0,0x7f29c5cd8e80,32768,674790,86381088,194156155699641,194161603299102,194161603318622,194156156015058 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,135197,135197,1048576,256,0,0,8,8,16,64,0x0,0x7f29c5cd8e80,32768,665462,85191512,194156156043151,194161603339422,194161603358782,194156156215438 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1230944,1230944,1048576,256,0,0,8,8,16,64,0x0,0x7ffbc1f4cec0,32768,645816,82677572,1410081477739489,1410086759522522,1410086759546522,1410081485518320 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1230944,1230944,1048576,256,0,0,8,8,16,64,0x0,0x7ffbc1f4cec0,32768,680377,87084488,1410081485537947,1410086759649082,1410086759668282,1410081485867789 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1230944,1230944,1048576,256,0,0,8,8,16,64,0x0,0x7ffbc1f4cec0,32768,673922,86271688,1410081485896303,1410086759687162,1410086759706362,1410081486072595 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv index aaaf6b9cf1..6eec6cbaab 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,135386,135386,1048576,256,0,0,8,8,16,64,0x0,0x7f6c8e1bae80,48123,48123,17292,384992,16384,25142758,233752,0,101056832,194156649274716,194161603172864,194161603197984,194156657125771 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,135386,135386,1048576,256,0,0,8,8,16,64,0x0,0x7f6c8e1bae80,42746,42746,13457,341976,16384,25281138,232746,0,101615784,194156657156529,194161603299102,194161603318622,194156657462328 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,135386,135386,1048576,256,0,0,8,8,16,64,0x0,0x7f6c8e1bae80,42114,42114,13671,336920,16384,23618044,225682,0,94966952,194156657500110,194161603339422,194161603358782,194156657688617 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1231127,1231127,1048576,256,0,0,8,8,16,64,0x0,0x7ffa5eb30ec0,49550,49550,17610,396408,16384,25459492,243358,0,102363764,1410081956413632,1410086759522522,1410086759546522,1410081964082705 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1231127,1231127,1048576,256,0,0,8,8,16,64,0x0,0x7ffa5eb30ec0,42482,42482,13337,339864,16384,24596688,235713,0,98916828,1410081964113574,1410086759649082,1410086759668282,1410081964417066 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1231127,1231127,1048576,256,0,0,8,8,16,64,0x0,0x7ffa5eb30ec0,43354,43354,13430,346840,16384,26102943,241411,0,104929252,1410081964455288,1410086759687162,1410086759706362,1410081964649104 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/log.txt b/tests/workloads/ipblocks_SQ_SPI/MI100/log.txt new file mode 100644 index 0000000000..d14c99a76a --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/log.txt @@ -0,0 +1,447 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_SPI/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'spi'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155226' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155226_1230217' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155226_1230217/input0_results_240321_155226' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155226_1230217/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155226_1230217/input0_results_240321_155226 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155226' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155226_1230400' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155226_1230400/input0_results_240321_155226' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155226_1230400/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155226_1230400/input0_results_240321_155226 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155227' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155227_1230601' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155227_1230601/input0_results_240321_155227' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155227_1230601/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155227_1230601/input0_results_240321_155227 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155227' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155227_1230784' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155227_1230784/input0_results_240321_155227' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155227_1230784/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155227_1230784/input0_results_240321_155227 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155227' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155227_1230967' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155227_1230967/input0_results_240321_155227' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155227_1230967/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155227_1230967/input0_results_240321_155227 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155228' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155228_1231151' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155228_1231151/input0_results_240321_155228' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155228_1231151/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, GRBM_COUNT, GRBM_GUI_ACTIVE, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155228_1231151/input0_results_240321_155228 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155228' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155228_1231340' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155228_1231340/input0_results_240321_155228' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155228_1231340/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 11 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, GRBM_SPI_BUSY, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155228_1231340/input0_results_240321_155228 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155229' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155229_1231529' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155229_1231529/input0_results_240321_155229' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155229_1231529/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155229_1231529/input0_results_240321_155229 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155229' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155229_1231713' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155229_1231713/input0_results_240321_155229' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155229_1231713/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155229_1231713/input0_results_240321_155229 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155230' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155230_1231907' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155230_1231907/input0_results_240321_155230' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155230_1231907/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155230_1231907/input0_results_240321_155230 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155230' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155230_1232095' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155230_1232095/input0_results_240321_155230' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155230_1232095/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155230_1232095/input0_results_240321_155230 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155231' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155231_1232279' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155231_1232279/input0_results_240321_155231' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155231_1232279/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155231_1232279/input0_results_240321_155231 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155231' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155231_1232463' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155231_1232463/input0_results_240321_155231' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155231_1232463/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155231_1232463/input0_results_240321_155231 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155232' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155232_1232647' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155232_1232647/input0_results_240321_155232' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155232_1232647/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155232_1232647/input0_results_240321_155232 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155232' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155232_1232835' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155232_1232835/input0_results_240321_155232' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155232_1232835/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155232_1232835/input0_results_240321_155232 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf.csv index f3eaae786e..0fc693e412 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_1,obj_1,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_3,obj_3,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_4,obj_4,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_5,obj_5,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_7,obj_7,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_8,obj_8,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5923544e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7fa935b38e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f7859e02e80,395368,236097,16384,16384,16384,32768,49152,0,49420,49420,393655,246030,64,0x7feaa9ba2e80,65536,32768,0,0,0,16384,16384,393216,31452,4096,16384,64,0x7fb995e02e80,0,131072,144,48,0,0,0,192,0,0,64,0x7f4f2c506e80,24520468,22424805,1735215,360448,3334469,163840,0,0,13494,29878,64,0x7fec1cb22e80,0,65536,64442,48,1376,187995,0,0,0,81920,64,0x7f8560958e80,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7fe5b7f64e80,180224,114688,0,32768,32768,16384,16384,65536,0,0,194161603172864,194161603197984 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5923544e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7fa935b38e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f7859e02e80,353216,233714,16384,16384,16384,32768,49152,0,44151,44151,353208,243493,64,0x7feaa9ba2e80,65536,32768,0,0,0,16384,16384,393216,31284,4096,16384,64,0x7fb995e02e80,0,131072,0,48,0,0,0,48,0,0,64,0x7f4f2c506e80,24356495,22744903,1251144,360448,3325659,163840,0,0,14177,30561,64,0x7fec1cb22e80,0,65536,65536,0,0,185875,0,0,0,81920,64,0x7f8560958e80,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7fe5b7f64e80,180224,114688,0,32768,32768,16384,16384,65536,0,0,194161603299102,194161603318622 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5923544e80,0,0,0,1048576,0,0,0,0,0,0,64,0x7fa935b38e80,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f7859e02e80,349696,229854,16384,16384,16384,32768,49152,0,43711,43711,349688,239631,64,0x7feaa9ba2e80,65536,32768,0,0,0,16384,16384,393216,30778,4096,16384,64,0x7fb995e02e80,0,131072,0,48,0,0,0,48,0,0,64,0x7f4f2c506e80,24572646,23048526,1163672,360448,3374138,163840,0,0,14639,31023,64,0x7fec1cb22e80,0,65536,65536,0,0,190076,0,0,0,81920,64,0x7f8560958e80,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7fe5b7f64e80,180224,114688,0,32768,32768,16384,16384,65536,0,0,194161603339422,194161603358782 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_1,obj_1,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_3,obj_3,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_4,obj_4,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_5,obj_5,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_6,obj_6,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_7,obj_7,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_8,obj_8,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff0c6e6cec0,0,131072,144,48,0,0,0,192,0,0,64,0x7f27479d0ec0,65536,32768,0,0,0,16384,16384,393216,31956,4096,16384,64,0x7f0496b68ec0,389544,236775,16384,16384,16384,32768,49152,0,48692,48692,387831,246710,64,0x7f245a784ec0,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f3b2a660ec0,25086624,22771809,1954367,360448,3448287,163840,0,0,14260,30644,64,0x7efcd2d2cec0,0,0,0,1048576,0,0,0,0,0,0,64,0x7f8092100ec0,180224,114688,0,32768,32768,16384,16384,65536,0,0,64,0x7f04f6d1cec0,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7ff14359cec0,0,65536,64453,48,1472,184351,0,0,0,81920,1410086759522522,1410086759546522 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff0c6e6cec0,0,131072,0,48,0,0,0,48,0,0,64,0x7f27479d0ec0,65536,32768,0,0,0,16384,16384,393216,30906,4096,16384,64,0x7f0496b68ec0,348232,234401,16384,16384,16384,32768,49152,0,43528,43528,348224,244193,64,0x7f245a784ec0,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f3b2a660ec0,24647470,23057115,1229907,360448,3368535,163840,0,0,14207,30591,64,0x7efcd2d2cec0,0,0,0,1048576,0,0,0,0,0,0,64,0x7f8092100ec0,180224,114688,0,32768,32768,16384,16384,65536,0,0,64,0x7f04f6d1cec0,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7ff14359cec0,0,65536,65536,0,0,191929,0,0,0,81920,1410086759649082,1410086759668282 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff0c6e6cec0,0,131072,0,48,0,0,0,48,0,0,64,0x7f27479d0ec0,65536,32768,0,0,0,16384,16384,393216,30772,4096,16384,64,0x7f0496b68ec0,345416,234002,16384,16384,16384,32768,49152,0,43176,43176,345408,243779,64,0x7f245a784ec0,49152,11534336,65536,0,0,0,16384,0,0,0,64,0x7f3b2a660ec0,24085016,22504433,1220135,360448,3343834,163840,0,0,12532,28916,64,0x7efcd2d2cec0,0,0,0,1048576,0,0,0,0,0,0,64,0x7f8092100ec0,180224,114688,0,32768,32768,16384,16384,65536,0,0,64,0x7f04f6d1cec0,65536,64048,48,1440,32768,32768,0,16384,0,64,0x7ff14359cec0,0,65536,65536,0,0,186799,0,0,0,81920,1410086759687162,1410086759706362 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv index 0a350019fc..098c81b6e3 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi,Thu 07 Mar 2024 01:06:59 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi,Thu 21 Mar 2024 03:52:25 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv index 3c296667c3..b5c270d014 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,137249,137249,1048576,256,0,0,8,8,16,64,0x0,0x7ff2ac8b6e80,194161603144802,194161603172864,194161603197984,194161603211438 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,137249,137249,1048576,256,0,0,8,8,16,64,0x0,0x7ff2ac8b6e80,194161603210616,194161603299102,194161603318622,194161603319783 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,137249,137249,1048576,256,0,0,8,8,16,64,0x0,0x7ff2ac8b6e80,194161603330663,194161603339422,194161603358782,194161603359678 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1232995,1232995,1048576,256,0,0,8,8,16,64,0x0,0x7f4b9bb00ec0,1410086759497441,1410086759522522,1410086759546522,1410086759558877 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1232995,1232995,1048576,256,0,0,8,8,16,64,0x0,0x7f4b9bb00ec0,1410086759559307,1410086759649082,1410086759668282,1410086759669966 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1232995,1232995,1048576,256,0,0,8,8,16,64,0x0,0x7f4b9bb00ec0,1410086759680456,1410086759687162,1410086759706362,1410086759707798 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv index f9e3462d8c..15436369c7 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,287510,287510,1048576,256,0,0,8,0,16,64,0x0,0x7f0f3f26cec0,27747,27747,16384,65536,13573,1533656,198159671186521,198168314115755,198168314136235,198159687476718 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,287510,287510,1048576,256,0,0,8,0,16,64,0x0,0x7f0f3f26cec0,40947,40947,16384,65536,9537,1048636,198159687497668,198168314155755,198168314170955,198159687804268 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,287510,287510,1048576,256,0,0,8,0,16,64,0x0,0x7f0f3f26cec0,40747,40747,16384,65536,9442,1048632,198159687833403,198168314242315,198168314259115,198159687995650 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4110988,4110988,1048576,256,0,0,8,0,16,64,0x0,0x7f4b0048cec0,28102,28102,16384,65536,13425,1494024,1411645038497275,1411654780403076,1411654780422756,1411645055381345 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4110988,4110988,1048576,256,0,0,8,0,16,64,0x0,0x7f4b0048cec0,41579,41579,16384,65536,9314,1048620,1411645055401553,1411654780594116,1411654780610756,1411645055709546 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4110988,4110988,1048576,256,0,0,8,0,16,64,0x0,0x7f4b0048cec0,40637,40637,16384,65536,9277,1048672,1411645055739543,1411654780632356,1411654780648036,1411645055901028 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv index 3ccec59a01..6de0f9c613 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,287694,287694,1048576,256,0,0,8,0,16,64,0x0,0x7ff9fd7e8ec0,0,0,0,198160151120061,198168314115755,198168314136235,198160166914551 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,287694,287694,1048576,256,0,0,8,0,16,64,0x0,0x7ff9fd7e8ec0,0,0,0,198160166933878,198168314155755,198168314170955,198160167213346 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,287694,287694,1048576,256,0,0,8,0,16,64,0x0,0x7ff9fd7e8ec0,0,0,0,198160167239686,198168314242315,198168314259115,198160167399539 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4111172,4111172,1048576,256,0,0,8,0,16,64,0x0,0x7f094ddf8ec0,0,0,0,1411645523829809,1411654780403076,1411654780422756,1411645539633054 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4111172,4111172,1048576,256,0,0,8,0,16,64,0x0,0x7f094ddf8ec0,0,0,0,1411645539650127,1411654780594116,1411654780610756,1411645539953480 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4111172,4111172,1048576,256,0,0,8,0,16,64,0x0,0x7f094ddf8ec0,0,0,0,1411645539979921,1411654780632356,1411654780648036,1411645540142849 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv index 4f90c02c78..1f8b5cc290 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,287895,287895,1048576,256,0,0,8,0,16,64,0x0,0x7f0ebd7a4ec0,65536,171962,19168800,198160631067549,198168314115755,198168314136235,198160647001192 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,287895,287895,1048576,256,0,0,8,0,16,64,0x0,0x7f0ebd7a4ec0,65536,228224,25515656,198160647021250,198168314155755,198168314170955,198160647358648 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,287895,287895,1048576,256,0,0,8,0,16,64,0x0,0x7f0ebd7a4ec0,65536,226978,25364048,198160647386110,198168314242315,198168314259115,198160647554188 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4111357,4111357,1048576,256,0,0,8,0,16,64,0x0,0x7f56cb9d8ec0,65536,167508,18842696,1411646016730344,1411654780403076,1411654780422756,1411646032536035 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4111357,4111357,1048576,256,0,0,8,0,16,64,0x0,0x7f56cb9d8ec0,65536,225402,25247672,1411646032553117,1411654780594116,1411654780610756,1411646032929629 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4111357,4111357,1048576,256,0,0,8,0,16,64,0x0,0x7f56cb9d8ec0,65536,223538,25046984,1411646032955548,1411654780632356,1411654780648036,1411646033112585 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv index 0dde5094a2..cab9ce6921 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,288099,288099,1048576,256,0,0,8,0,16,64,0x0,0x7f9821224ec0,32768,287176,32152116,198161107879535,198168314115755,198168314136235,198161123985894 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,288099,288099,1048576,256,0,0,8,0,16,64,0x0,0x7f9821224ec0,32768,578942,64844504,198161124004279,198168314155755,198168314170955,198161124322030 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,288099,288099,1048576,256,0,0,8,0,16,64,0x0,0x7f9821224ec0,32768,580926,65072092,198161124347368,198168314242315,198168314259115,198161124505938 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4111543,4111543,1048576,256,0,0,8,0,16,64,0x0,0x7fc09b160ec0,32768,315198,35295148,1411646502756830,1411654780403076,1411654780422756,1411646518921349 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4111543,4111543,1048576,256,0,0,8,0,16,64,0x0,0x7fc09b160ec0,32768,580502,65026460,1411646518939664,1411654780594116,1411654780610756,1411646519347395 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4111543,4111543,1048576,256,0,0,8,0,16,64,0x0,0x7fc09b160ec0,32768,580395,65006788,1411646519373625,1411654780632356,1411654780648036,1411646519523398 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv index 51ea5d84ee..8dac400768 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,288284,288284,1048576,256,0,0,8,0,16,64,0x0,0x7f65cd2a4ec0,27442,27442,10817,219544,16384,10743312,127984,0,43470904,198161591136943,198168314115755,198168314136235,198161606839219 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,288284,288284,1048576,256,0,0,8,0,16,64,0x0,0x7f65cd2a4ec0,41459,41459,13582,331680,16384,19631876,222003,0,79003076,198161606865017,198168314155755,198168314170955,198161607196715 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,288284,288284,1048576,256,0,0,8,0,16,64,0x0,0x7f65cd2a4ec0,41888,41888,13699,335112,16384,19466021,225878,0,78363356,198161607231401,198168314242315,198168314259115,198161607403847 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4111730,4111730,1048576,256,0,0,8,0,16,64,0x0,0x7ff25d84cec0,27942,27942,11409,223544,16384,10901007,128205,0,44109684,1411646992618800,1411654780403076,1411654780422756,1411647009149862 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4111730,4111730,1048576,256,0,0,8,0,16,64,0x0,0x7ff25d84cec0,42670,42670,13049,341368,16384,19915819,234249,0,80149644,1411647009166053,1411654780594116,1411654780610756,1411647009490456 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4111730,4111730,1048576,256,0,0,8,0,16,64,0x0,0x7ff25d84cec0,41493,41493,13575,331952,16384,19233309,223013,0,77422620,1411647009525622,1411654780632356,1411654780648036,1411647009692318 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/log.txt b/tests/workloads/ipblocks_SQ_SPI/MI200/log.txt new file mode 100644 index 0000000000..d3e4f1a96e --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/log.txt @@ -0,0 +1,565 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_SPI/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'spi'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_161832' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161832_4110828' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161832_4110828/input0_results_240321_161832' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161832_4110828/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161832_4110828/input0_results_240321_161832 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_161833' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161833_4111012' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161833_4111012/input0_results_240321_161833' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161833_4111012/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161833_4111012/input0_results_240321_161833 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_161833' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161833_4111195' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161833_4111195/input0_results_240321_161833' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161833_4111195/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161833_4111195/input0_results_240321_161833 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_161834' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161834_4111383' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161834_4111383/input0_results_240321_161834' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161834_4111383/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161834_4111383/input0_results_240321_161834 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_161834' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161834_4111570' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161834_4111570/input0_results_240321_161834' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161834_4111570/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161834_4111570/input0_results_240321_161834 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_161835' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161835_4111756' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161835_4111756/input0_results_240321_161835' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161835_4111756/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, GRBM_COUNT, GRBM_GUI_ACTIVE, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161835_4111756/input0_results_240321_161835 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_161836' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161836_4111944' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161836_4111944/input0_results_240321_161836' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161836_4111944/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 11 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, GRBM_SPI_BUSY, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161836_4111944/input0_results_240321_161836 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_161837' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161837_4112130' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161837_4112130/input0_results_240321_161837' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161837_4112130/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161837_4112130/input0_results_240321_161837 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_161837' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161837_4112316' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161837_4112316/input0_results_240321_161837' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161837_4112316/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161837_4112316/input0_results_240321_161837 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_161838' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161838_4112502' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161838_4112502/input0_results_240321_161838' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161838_4112502/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161838_4112502/input0_results_240321_161838 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_161838' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161838_4112689' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161838_4112689/input0_results_240321_161838' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161838_4112689/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161838_4112689/input0_results_240321_161838 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_161839' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161839_4112876' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161839_4112876/input0_results_240321_161839' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161839_4112876/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161839_4112876/input0_results_240321_161839 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_161839' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161839_4113059' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161839_4113059/input0_results_240321_161839' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161839_4113059/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161839_4113059/input0_results_240321_161839 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_161840' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161840_4113260' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161840_4113260/input0_results_240321_161840' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161840_4113260/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161840_4113260/input0_results_240321_161840 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_161840' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161840_4113462' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161840_4113462/input0_results_240321_161840' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161840_4113462/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161840_4113462/input0_results_240321_161840 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_161841' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161841_4113648' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161841_4113648/input0_results_240321_161841' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161841_4113648/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161841_4113648/input0_results_240321_161841 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_161841' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161841_4113831' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161841_4113831/input0_results_240321_161841' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161841_4113831/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161841_4113831/input0_results_240321_161841 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_161842' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161842_4114018' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161842_4114018/input0_results_240321_161842' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161842_4114018/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161842_4114018/input0_results_240321_161842 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_161842' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161842_4114201' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161842_4114201/input0_results_240321_161842' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161842_4114201/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161842_4114201/input0_results_240321_161842 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_SQ_SPI/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf.csv index df5b2b20c7..97b46159c4 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_1,obj_1,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_5,obj_5,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_9,obj_9,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_10,obj_10,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_11,obj_11,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_12,obj_12,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f91da168ec0,344064,224752,132874,1676287,0,0,163840,114688,540944,0,64,0x7f3fab4e8ec0,0,0,0,16384,16384,10977714,9695634,938016,10605,0,64,0x7f42d5018ec0,0,0,0,0,114688,0,65536,32768,12144,18590,64,0x7ff0e2e18ec0,1907,119011,0,0,65536,63800,56,1680,64,0x7f13f57d8ec0,0,0,0,0,0,0,0,0,17743,4096,16384,64,0x7f2613534ec0,0,16384,16384,32768,49152,0,393216,163840,27557,27557,218753,135290,64,0x7effe6794ec0,32768,32768,0,64,0x7f74fae7cec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7fc7e3068ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f974543cec0,0,0,0,224,0,65536,63530,56,64,0x7f935d93cec0,0,0,0,0,0,0,168,56,64,0x7f8e9dbc4ec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f5fc9a24ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,198168314115755,198168314136235 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f91da168ec0,344064,336800,228544,2865927,0,0,163840,114688,1086607,0,64,0x7f3fab4e8ec0,0,0,0,16384,16384,20446740,18834238,1268438,22328,0,64,0x7f42d5018ec0,0,0,0,0,114688,0,65536,32768,30760,27082,64,0x7ff0e2e18ec0,0,186318,0,0,65536,63800,56,1680,64,0x7f13f57d8ec0,0,0,0,0,0,0,0,0,29393,4096,16384,64,0x7f2613534ec0,0,16384,16384,32768,49152,0,393216,163840,41015,41015,328120,229183,64,0x7effe6794ec0,32768,32768,0,64,0x7f74fae7cec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7fc7e3068ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f974543cec0,0,0,0,56,0,65536,65536,0,64,0x7f935d93cec0,0,0,0,0,0,0,0,56,64,0x7f8e9dbc4ec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f5fc9a24ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,198168314155755,198168314170955 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f91da168ec0,344064,339920,229468,2874232,0,0,163840,114688,1058378,0,64,0x7f3fab4e8ec0,0,0,0,16384,16384,19365443,18057527,963852,20373,0,64,0x7f42d5018ec0,0,0,0,0,114688,0,65536,32768,31008,27817,64,0x7ff0e2e18ec0,0,185450,0,0,65536,63800,56,1680,64,0x7f13f57d8ec0,0,0,0,0,0,0,0,0,31289,4096,16384,64,0x7f2613534ec0,0,16384,16384,32768,49152,0,393216,163840,41675,41675,333400,232571,64,0x7effe6794ec0,32768,32768,0,64,0x7f74fae7cec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7fc7e3068ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f974543cec0,0,0,0,56,0,65536,65536,0,64,0x7f935d93cec0,0,0,0,0,0,0,0,56,64,0x7f8e9dbc4ec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f5fc9a24ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,198168314242315,198168314259115 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,GRBM_SPI_BUSY,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,wave_size_1,obj_1,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,wave_size_2,obj_2,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,wave_size_4,obj_4,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_6,obj_6,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,wave_size_7,obj_7,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_8,obj_8,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,wave_size_9,obj_9,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_10,obj_10,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,wave_size_11,obj_11,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,wave_size_12,obj_12,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f60b2444ec0,0,0,0,0,0,0,0,0,17624,4096,16384,64,0x7fd9612e8ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f21ea858ec0,1199,119879,0,0,65536,63800,56,1680,64,0x7f9ac19c8ec0,0,16384,16384,32768,49152,0,393216,163840,27512,27512,218393,134670,64,0x7ff9f9104ec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7f6a15b9cec0,32768,32768,0,64,0x7f11cbd5cec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f03bc60cec0,0,0,0,224,0,65536,64280,56,64,0x7fce08ef4ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,64,0x7f6157014ec0,0,0,0,0,0,0,168,56,64,0x7f0330014ec0,344064,219936,127406,1615032,0,0,163840,114688,488525,0,64,0x7f162504cec0,0,0,0,16384,16384,10847134,9773211,729859,10336,0,64,0x7f2513d74ec0,0,0,0,0,114688,0,65536,32768,13652,18752,1411654780403076,1411654780422756 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f60b2444ec0,0,0,0,0,0,0,0,0,29838,4096,16384,64,0x7fd9612e8ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f21ea858ec0,0,186099,0,0,65536,63800,56,1680,64,0x7f9ac19c8ec0,0,16384,16384,32768,49152,0,393216,163840,41431,41431,331448,231545,64,0x7ff9f9104ec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7f6a15b9cec0,32768,32768,0,64,0x7f11cbd5cec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f03bc60cec0,0,0,0,56,0,65536,65536,0,64,0x7fce08ef4ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,64,0x7f6157014ec0,0,0,0,0,0,0,0,56,64,0x7f0330014ec0,344064,331416,222248,2781574,0,0,163840,114688,986828,0,64,0x7f162504cec0,0,0,0,16384,16384,19326373,18172977,809332,20575,0,64,0x7f2513d74ec0,0,0,0,0,114688,0,65536,32768,33945,27855,1411654780594116,1411654780610756 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f60b2444ec0,0,0,0,0,0,0,0,0,29277,4096,16384,64,0x7fd9612e8ec0,131072,0,0,0,0,0,0,0,16384,0,64,0x7f21ea858ec0,0,189505,0,0,65536,63800,56,1680,64,0x7f9ac19c8ec0,0,16384,16384,32768,49152,0,393216,163840,40657,40657,325256,228731,64,0x7ff9f9104ec0,65536,0,0,0,16384,16384,0,0,0,0,64,0x7f6a15b9cec0,32768,32768,0,64,0x7f11cbd5cec0,0,0,1048576,0,0,0,0,0,0,32768,64,0x7f03bc60cec0,0,0,0,56,0,65536,65536,0,64,0x7fce08ef4ec0,0,32768,32768,16384,16384,65536,49152,10485760,0,0,64,0x7f6157014ec0,0,0,0,0,0,0,0,56,64,0x7f0330014ec0,344064,340400,230274,2899401,0,0,163840,114688,1078763,0,64,0x7f162504cec0,0,0,0,16384,16384,19821355,18639520,837771,21844,0,64,0x7f2513d74ec0,0,0,0,0,114688,0,65536,32768,34504,27978,1411654780632356,1411654780648036 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/roofline.csv index 603442600d..c7e532a3e8 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/roofline.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.2981,1388.6581,1389.9381,5016.5327,5013.4414,5019.624,9223.5947,9222.998,9224.1914,18050.371,18049.385,18051.357,20933.727,20873.285,20994.168,20264.689,20264.02,20265.359,170412.19,170406.34,170418.03,164847.23,164841.38,164853.09,41415.691,41415.066,41416.316,41473.828,41473.082,41474.574,166301.5,165803.25,166799.75 -1,1389.3405,1388.8101,1389.8708,5027.9414,5025.811,5030.0718,9235.7158,9235.0078,9236.4238,18095.494,18091.707,18099.281,20976.84,20909.99,21043.689,20299.086,20298.502,20299.67,170871.09,170867.22,170874.97,165139.88,165133.42,165146.33,41490.809,41489.973,41491.645,41554.738,41553.953,41555.523,166900.34,166896.47,166904.22 -2,1388.2317,1387.6322,1388.8312,5036.1846,5033.8223,5038.5469,9262.5654,9261.708,9263.4229,18105.012,18104.068,18105.955,21048.953,21048.598,21049.309,20354.756,20354.223,20355.289,171126.64,171123.47,171129.81,165513.05,165509.33,165516.77,41587.539,41586.488,41588.59,41648.672,41647.238,41650.105,166971.38,166380.41,167562.34 -3,1388.9213,1388.332,1389.5105,5032.4907,5031.2202,5033.7612,9241.041,9240.5186,9241.5635,18023.152,18019.688,18026.617,21033.707,21033.018,21034.396,20314.184,20313.395,20314.973,171044.81,171041.44,171048.19,165239.59,165235.86,165243.33,41442.719,41288.254,41597.184,41582.965,41582.488,41583.441,167032.02,167030.33,167033.7 +0,1389.0472,1388.5072,1389.5873,5017.9268,5014.8643,5020.9893,9228.5059,9227.7432,9229.2686,17717.703,17714.436,17720.971,20948.148,20887.664,21008.633,20273.328,20272.471,20274.186,170491.81,170487.64,170495.98,164935.19,164930.47,164939.91,41434.359,41433.496,41435.223,41494.328,41493.695,41494.961,166414.17,165923.95,166904.39 +1,1388.8302,1388.2301,1389.4303,5030.5298,5028.374,5032.6855,9238.4971,9237.9072,9239.0869,18246.24,18243.674,18248.807,20985.586,20918.393,21052.779,20302.154,20301.637,20302.672,170924.02,170919.86,170928.17,165160.5,165156.66,165164.34,41501.66,41500.738,41502.582,41557.648,41556.715,41558.582,166935.69,166932.58,166938.8 +2,1388.6953,1388.1727,1389.2179,5035.8525,5033.6807,5038.0244,9258.9141,9258.2236,9259.6045,18215.807,18214.838,18216.775,21048.705,21048.254,21049.156,20352.855,20352.293,20353.418,171130.2,171126.72,171133.69,165517.11,165513.31,165520.91,41590.109,41589.395,41590.824,41644.664,41643.832,41645.496,166967.2,166369.62,167564.78 +3,1389.0238,1388.4399,1389.6077,5033.834,5032.2744,5035.3936,9238.1201,9237.3779,9238.8623,18327.48,18326.615,18328.346,21034.287,21033.939,21034.635,20306.002,20305.527,20306.477,171011.8,171007.33,171016.27,165132.52,165126.94,165138.09,41422.961,41268.508,41577.414,41561.359,41560.449,41562.27,166955.34,166951.92,166958.77 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv index 4b91da03b4..f472fa54e2 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SPI,./sample/vcopy -n 1048576 -b 256 -i 3,sq|spi|roofline,Thu 07 Mar 2024 02:13:46 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_SQ_SPI,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi|roofline,Thu 21 Mar 2024 04:18:32 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv index 2e8c320f58..bb43a8cf8b 100644 --- a/tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SPI/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,290916,290916,1048576,256,0,0,8,0,16,64,0x0,0x7fca90930ec0,198168314092247,198168314115755,198168314136235,198168314161749 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,290916,290916,1048576,256,0,0,8,0,16,64,0x0,0x7fca90930ec0,198168314147683,198168314155755,198168314170955,198168314239666 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,290916,290916,1048576,256,0,0,8,0,16,64,0x0,0x7fca90930ec0,198168314181466,198168314242315,198168314259115,198168314261067 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4114361,4114361,1048576,256,0,0,8,0,16,64,0x0,0x7f11b05f8ec0,1411654780378271,1411654780403076,1411654780422756,1411654780436441 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4114361,4114361,1048576,256,0,0,8,0,16,64,0x0,0x7f11b05f8ec0,1411654780434097,1411654780594116,1411654780610756,1411654780611993 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4114361,4114361,1048576,256,0,0,8,0,16,64,0x0,0x7f11b05f8ec0,1411654780622022,1411654780632356,1411654780648036,1411654780649083 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv index d2c95ab678..7e42236856 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,114804,114804,1048576,256,0,0,8,8,16,64,0x0,0x7f2225ccee80,47612,47612,16384,65536,14038,1815892,194094975442809,194102861062915,194102861087395,194094983210487 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,114804,114804,1048576,256,0,0,8,8,16,64,0x0,0x7f2225ccee80,41618,41618,16384,65536,8188,1048580,194094983232428,194102861176995,194102861195875,194094983556031 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,114804,114804,1048576,256,0,0,8,8,16,64,0x0,0x7f2225ccee80,42058,42058,16384,65536,8308,1048608,194094983588442,194102861217315,194102861236515,194094983753735 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1210455,1210455,1048576,256,0,0,8,8,16,64,0x0,0x7fcc5a45cec0,48115,48115,16384,65536,14247,1816824,1410023042678608,1410030696942687,1410030696966687,1410023050498416 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1210455,1210455,1048576,256,0,0,8,8,16,64,0x0,0x7fcc5a45cec0,42619,42619,16384,65536,8233,1048588,1410023050523083,1410030697050527,1410030697069887,1410023050842154 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1210455,1210455,1048576,256,0,0,8,8,16,64,0x0,0x7fcc5a45cec0,42647,42647,16384,65536,8106,1048580,1410023050873483,1410030697092767,1410030697111327,1410023051053122 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv index c4aee2e07a..51df972b3a 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,115016,115016,1048576,256,0,0,8,8,16,64,0x0,0x7f2b54f20e80,0,0,0,194095472713822,194102861062915,194102861087395,194095480325935 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,115016,115016,1048576,256,0,0,8,8,16,64,0x0,0x7f2b54f20e80,0,0,0,194095480345362,194102861176995,194102861195875,194095480648586 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,115016,115016,1048576,256,0,0,8,8,16,64,0x0,0x7f2b54f20e80,0,0,0,194095480676559,194102861217315,194102861236515,194095480846561 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1210656,1210656,1048576,256,0,0,8,8,16,64,0x0,0x7feea4f14ec0,0,0,0,1410023527817734,1410030696942687,1410030696966687,1410023535603407 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1210656,1210656,1048576,256,0,0,8,8,16,64,0x0,0x7feea4f14ec0,0,0,0,1410023535624226,1410030697050527,1410030697069887,1410023536014252 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1210656,1210656,1048576,256,0,0,8,8,16,64,0x0,0x7feea4f14ec0,0,0,0,1410023536041954,1410030697092767,1410030697111327,1410023536211113 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv index e001bba91b..5847a9d6e6 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,115205,115205,1048576,256,0,0,8,8,16,64,0x0,0x7ff93663ae80,65536,217060,27703096,194095962342495,194102861062915,194102861087395,194095970358883 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,115205,115205,1048576,256,0,0,8,8,16,64,0x0,0x7ff93663ae80,65536,154114,19694896,194095970377949,194102861176995,194102861195875,194095970678538 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,115205,115205,1048576,256,0,0,8,8,16,64,0x0,0x7ff93663ae80,65536,186826,23911120,194095970706852,194102861217315,194102861236515,194095970877345 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1210845,1210845,1048576,256,0,0,8,8,16,64,0x0,0x7f614e354ec0,65536,217406,27812696,1410024004081049,1410030696942687,1410030696966687,1410024011579983 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1210845,1210845,1048576,256,0,0,8,8,16,64,0x0,0x7f614e354ec0,65536,180092,23007248,1410024011601032,1410030697050527,1410030697069887,1410024012051652 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1210845,1210845,1048576,256,0,0,8,8,16,64,0x0,0x7f614e354ec0,65536,178752,22885544,1410024012080096,1410030697092767,1410030697111327,1410024012252210 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv index 0112fe9dc1..e49fe58e73 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,115396,115396,1048576,256,0,0,8,8,16,64,0x0,0x7fbf9e40ee80,32768,656989,84067744,194096454708641,194102861062915,194102861087395,194096464884598 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,115396,115396,1048576,256,0,0,8,8,16,64,0x0,0x7fbf9e40ee80,32768,672665,86091356,194096464502735,194102861176995,194102861195875,194096466421498 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,115396,115396,1048576,256,0,0,8,8,16,64,0x0,0x7fbf9e40ee80,32768,665343,85156924,194096464629004,194102861217315,194102861236515,194096464887523 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1211028,1211028,1048576,256,0,0,8,8,16,64,0x0,0x7f340bcfcec0,32768,612662,78425108,1410024481916440,1410030696942687,1410030696966687,1410024489620941 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1211028,1211028,1048576,256,0,0,8,8,16,64,0x0,0x7f340bcfcec0,32768,674126,86271720,1410024489628836,1410030697050527,1410030697069887,1410024489943369 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1211028,1211028,1048576,256,0,0,8,8,16,64,0x0,0x7f340bcfcec0,32768,658159,84242228,1410024489971733,1410030697092767,1410030697111327,1410024490144448 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv index 67b62b38e1..5c46026741 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,115585,115585,1048576,256,0,0,8,8,16,64,0x0,0x7f9f8bd2ae80,48998,48998,17076,391992,16384,25118597,240543,0,100974952,194096951203704,194102861062915,194102861087395,194096958897582 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,115585,115585,1048576,256,0,0,8,8,16,64,0x0,0x7f9f8bd2ae80,42877,42877,13400,343024,16384,25037316,231371,0,100640244,194096958926386,194102861176995,194102861195875,194096959282872 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,115585,115585,1048576,256,0,0,8,8,16,64,0x0,0x7f9f8bd2ae80,43653,43653,13953,349232,16384,25264572,235861,0,101535948,194096959321014,194102861217315,194102861236515,194096959513127 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1211226,1211226,1048576,256,0,0,8,8,16,64,0x0,0x7fd6d98e0ec0,47545,47545,17498,380368,16384,24361927,228767,0,97993372,1410024965701753,1410030696942687,1410030696966687,1410024973333015 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1211226,1211226,1048576,256,0,0,8,8,16,64,0x0,0x7fd6d98e0ec0,42801,42801,13881,342416,16384,24793376,230292,0,99709084,1410024973363874,1410030697050527,1410030697069887,1410024973671854 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1211226,1211226,1048576,256,0,0,8,8,16,64,0x0,0x7fd6d98e0ec0,41538,41538,13471,332312,16384,23781135,223289,0,95671016,1410024973710277,1410030697092767,1410030697111327,1410024973905555 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/log.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/log.txt new file mode 100644 index 0000000000..962606b7f5 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/log.txt @@ -0,0 +1,505 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'spi', 'ta', 'tcc', 'cpf'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155129' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155129_1210295' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155129_1210295/input0_results_240321_155129' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155129_1210295/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155129_1210295/input0_results_240321_155129 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155129' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155129_1210496' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155129_1210496/input0_results_240321_155129' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155129_1210496/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155129_1210496/input0_results_240321_155129 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155130' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155130_1210680' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155130_1210680/input0_results_240321_155130' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155130_1210680/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155130_1210680/input0_results_240321_155130 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155130' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155130_1210868' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155130_1210868/input0_results_240321_155130' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155130_1210868/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155130_1210868/input0_results_240321_155130 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155130' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155130_1211066' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155130_1211066/input0_results_240321_155130' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155130_1211066/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155130_1211066/input0_results_240321_155130 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155131' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155131_1211267' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155131_1211267/input0_results_240321_155131' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155131_1211267/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_BUSY_CU_CYCLES, SQ_WAVE_CYCLES, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, GRBM_COUNT, GRBM_GUI_ACTIVE, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155131_1211267/input0_results_240321_155131 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155131' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155131_1211468' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155131_1211468/input0_results_240321_155131' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155131_1211468/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 19 metrics + |-> [rocprof] SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, GRBM_SPI_BUSY, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155131_1211468/input0_results_240321_155131 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155132' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155132_1211669' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155132_1211669/input0_results_240321_155132' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155132_1211669/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155132_1211669/input0_results_240321_155132 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155132' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155132_1211870' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155132_1211870/input0_results_240321_155132' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155132_1211870/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 18 metrics + |-> [rocprof] SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155132_1211870/input0_results_240321_155132 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155133' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155133_1212058' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155133_1212058/input0_results_240321_155133' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155133_1212058/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155133_1212058/input0_results_240321_155133 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155133' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155133_1212258' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155133_1212258/input0_results_240321_155133' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155133_1212258/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155133_1212258/input0_results_240321_155133 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155134' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155134_1212450' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155134_1212450/input0_results_240321_155134' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155134_1212450/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155134_1212450/input0_results_240321_155134 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155134' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155134_1212651' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155134_1212651/input0_results_240321_155134' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155134_1212651/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155134_1212651/input0_results_240321_155134 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155135' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155135_1212836' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155135_1212836/input0_results_240321_155135' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155135_1212836/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155135_1212836/input0_results_240321_155135 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155135' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155135_1213036' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155135_1213036/input0_results_240321_155135' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155135_1213036/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 13 metrics + |-> [rocprof] SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155135_1213036/input0_results_240321_155135 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155136' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155136_1213225' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155136_1213225/input0_results_240321_155136' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155136_1213225/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155136_1213225/input0_results_240321_155136 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155136' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155136_1213427' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155136_1213427/input0_results_240321_155136' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155136_1213427/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155136_1213427/input0_results_240321_155136 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf.csv index 5720ad4f34..f6ed281e6c 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_2,obj_2,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,GRBM_SPI_BUSY,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_BUSY_CU_CYCLES,SQ_WAVE_CYCLES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_4,obj_4,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_6,obj_6,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_9,obj_9,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_10,obj_10,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb2865aae80,16384,393216,22200776,1784152,360448,163840,0,0,0.0,0.0,10568,26952,0,46139,262599.0,0.0,188.0,262411.0,64,0x7f1040c5ee80,0,131072,144,48,0,0,0,192,32768.0,16384.0,0,0,131432.0,0.0,712.0,131431.0,64,0x7f444f876e80,49152,0,65536,32768,0,0,0,16384,32609,0.0,0.0,4096,16384,1734,0,48.0,275.0,0.0,262288.0,64,0x7f65e7486e80,377376,229487,16384,3356073,24168392,16384,16384,32768,47171,47171,2112502.0,0.0,375663,239438,47171,0,1509472.0,968203.0,0.0,0.0,64,0x7f54eaa56e80,49152,11534336,65536,0,0,0,16384,0,989401.0,32768.0,0,0,131072.0,131072.0,0.0,131072.0,64,0x7fa3d4626e80,65536,64048,48,1440,32768,32768,0,16384,0,86490.0,44582.0,131111.0,0.0,64,0x7f6c4e3cae80,0.0,0.0,117210790.0,58805693.0,64,0x7efff43bae80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131527.0,131072.0,0.0,131104.0,64,0x7fed748cce80,0,65536,64448,48,1331,186472,0,0,16384.0,0.0,0,81920,0.0,0.0,52176.0,115093.0,64,0x7f122a504e80,0,0,0,1048576,0,0,0,0,0.0,754560.0,0,0,109899.0,0.0,0.0,109899.0,64,0x7fefe395ae80,0.0,194102861062915,194102861087395 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb2865aae80,16384,393216,22419225,1797965,360448,163840,0,0,0.0,0.0,12398,28782,0,41377,262543.0,0.0,47.0,262496.0,64,0x7f1040c5ee80,0,131072,0,48,0,0,0,48,32768.0,16384.0,0,0,131425.0,0.0,704.0,131424.0,64,0x7f444f876e80,49152,0,65536,32768,0,0,0,16384,30644,0.0,0.0,4096,16384,1752,0,48.0,239.0,0.0,262144.0,64,0x7f65e7486e80,339744,226057,16384,3281399,23894728,16384,16384,32768,42467,42467,2103992.0,0.0,339736,235841,42467,0,1358944.0,808999.0,0.0,0.0,64,0x7f54eaa56e80,49152,11534336,65536,0,0,0,16384,0,1111960.0,32768.0,0,0,86787.0,86787.0,0.0,86787.0,64,0x7fa3d4626e80,65536,64048,48,1440,32768,32768,0,16384,0,86453.0,0.0,131112.0,0.0,64,0x7f6c4e3cae80,0.0,0.0,116595345.0,46381801.0,64,0x7efff43bae80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131435.0,131072.0,0.0,86619.0,64,0x7fed748cce80,0,65536,65536,0,0,184717,0,0,16384.0,0.0,0,81920,0.0,0.0,50787.0,121609.0,64,0x7f122a504e80,0,0,0,1048576,0,0,0,0,0.0,673275.0,0,0,71820.0,0.0,0.0,71820.0,64,0x7fefe395ae80,0.0,194102861176995,194102861195875 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fb2865aae80,16384,393216,22225569,1344615,360448,163840,0,0,0.0,0.0,11428,27812,0,40916,262515.0,0.0,47.0,262468.0,64,0x7f1040c5ee80,0,131072,0,48,0,0,0,48,32768.0,16384.0,0,0,131416.0,0.0,686.0,131415.0,64,0x7f444f876e80,49152,0,65536,32768,0,0,0,16384,30772,0.0,0.0,4096,16384,1746,0,48.0,226.0,0.0,262144.0,64,0x7f65e7486e80,339920,226305,16384,3282794,24119530,16384,16384,32768,42489,42489,2109274.0,0.0,339912,236097,42489,0,1359648.0,804899.0,0.0,0.0,64,0x7f54eaa56e80,49152,11534336,65536,0,0,0,16384,0,910482.0,32768.0,0,0,86377.0,86377.0,0.0,86377.0,64,0x7fa3d4626e80,65536,64048,48,1440,32768,32768,0,16384,0,86405.0,0.0,131112.0,0.0,64,0x7f6c4e3cae80,0.0,0.0,125024782.0,46812143.0,64,0x7efff43bae80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131472.0,131072.0,0.0,86713.0,64,0x7fed748cce80,0,65536,65536,0,0,187107,0,0,16384.0,0.0,0,81920,0.0,0.0,65660.0,137400.0,64,0x7f122a504e80,0,0,0,1048576,0,0,0,0,0.0,698067.0,0,0,114936.0,0.0,0.0,114936.0,64,0x7fefe395ae80,0.0,194102861217315,194102861236515 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_1,obj_1,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_2,obj_2,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_4,obj_4,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_5,obj_5,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,GRBM_SPI_BUSY,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_7,obj_7,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_BUSY_CU_CYCLES,SQ_WAVE_CYCLES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fc5af4ecec0,0.0,0.0,107109174.0,55625273.0,64,0x7fd7024f8ec0,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131608.0,131072.0,0.0,131104.0,64,0x7fe0c6470ec0,0,0,0,1048576,0,0,0,0,0.0,566979.0,0,0,64146.0,0.0,0.0,64146.0,64,0x7fdbb6994ec0,0,65536,64440,48,1350,186872,0,0,16384.0,0.0,0,81920,0.0,0.0,51592.0,117660.0,64,0x7f9835d38ec0,65536,64048,48,1440,32768,32768,0,16384,0,86499.0,44573.0,131111.0,0.0,64,0x7f0a66914ec0,16384,393216,22409135,2524254,360448,163840,0,0,0.0,0.0,12113,28497,0,46505,262678.0,0.0,188.0,262490.0,64,0x7fb94d950ec0,49152,0,65536,32768,0,0,0,16384,31711,0.0,0.0,4096,16384,1972,0,48.0,116.0,0.0,262288.0,64,0x7fbe66a18ec0,0.0,64,0x7f4c8ebd8ec0,49152,11534336,65536,0,0,0,16384,0,840475.0,32768.0,0,0,131072.0,131072.0,0.0,131072.0,64,0x7ff7de790ec0,385968,234394,16384,3425669,25200106,16384,16384,32768,48245,48245,2047191.0,0.0,384255,244344,48245,0,1543840.0,958203.0,0.0,0.0,64,0x7fd7759d8ec0,0,131072,144,48,0,0,0,192,32768.0,16384.0,0,0,131268.0,0.0,384.0,131267.0,1410030696942687,1410030696966687 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fc5af4ecec0,0.0,0.0,130076775.0,46311078.0,64,0x7fd7024f8ec0,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131416.0,131072.0,0.0,86589.0,64,0x7fe0c6470ec0,0,0,0,1048576,0,0,0,0,0.0,608667.0,0,0,75486.0,0.0,0.0,75486.0,64,0x7fdbb6994ec0,0,65536,65536,0,0,186315,0,0,16384.0,0.0,0,81920,0.0,0.0,57698.0,124126.0,64,0x7f9835d38ec0,65536,64048,48,1440,32768,32768,0,16384,0,86628.0,0.0,131112.0,0.0,64,0x7f0a66914ec0,16384,393216,22986798,1619764,360448,163840,0,0,0.0,0.0,12897,29281,0,40972,262533.0,0.0,47.0,262486.0,64,0x7fb94d950ec0,49152,0,65536,32768,0,0,0,16384,29876,0.0,0.0,4096,16384,1817,0,48.0,131.0,0.0,262144.0,64,0x7fbe66a18ec0,0.0,64,0x7f4c8ebd8ec0,49152,11534336,65536,0,0,0,16384,0,952049.0,32768.0,0,0,86537.0,86537.0,0.0,86537.0,64,0x7ff7de790ec0,341712,230436,16384,3363924,24613349,16384,16384,32768,42713,42713,2137657.0,0.0,341704,240217,42713,0,1366816.0,805901.0,0.0,0.0,64,0x7fd7759d8ec0,0,131072,0,48,0,0,0,48,32768.0,16384.0,0,0,131179.0,0.0,212.0,131178.0,1410030697050527,1410030697069887 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fc5af4ecec0,0.0,0.0,116272007.0,46399208.0,64,0x7fd7024f8ec0,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,0,0,0,131447.0,131072.0,0.0,86403.0,64,0x7fe0c6470ec0,0,0,0,1048576,0,0,0,0,0.0,680668.0,0,0,78272.0,0.0,0.0,78272.0,64,0x7fdbb6994ec0,0,65536,65536,0,0,99568,0,0,16384.0,0.0,0,81920,0.0,0.0,64705.0,133673.0,64,0x7f9835d38ec0,65536,64048,48,1440,32768,32768,0,16384,0,86612.0,0.0,131112.0,0.0,64,0x7f0a66914ec0,16384,393216,22676697,1480182,360448,163840,0,0,0.0,0.0,11983,28367,0,41121,262536.0,0.0,47.0,262489.0,64,0x7fb94d950ec0,49152,0,65536,32768,0,0,0,16384,30396,0.0,0.0,4096,16384,1740,0,48.0,120.0,0.0,262144.0,64,0x7fbe66a18ec0,0.0,64,0x7f4c8ebd8ec0,49152,11534336,65536,0,0,0,16384,0,961650.0,32768.0,0,0,86700.0,86700.0,0.0,86700.0,64,0x7ff7de790ec0,343520,230301,16384,3345328,24539699,16384,16384,32768,42939,42939,2090087.0,0.0,343512,240073,42939,0,1374048.0,799691.0,0.0,0.0,64,0x7fd7759d8ec0,0,131072,0,48,0,0,0,48,32768.0,16384.0,0,0,131283.0,0.0,420.0,131282.0,1410030697092767,1410030697111327 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/sysinfo.csv index 70c030dc44..2d58d3bb3a 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SPI_TA_TCC_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi|ta|tcc|cpf,Thu 07 Mar 2024 01:05:59 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_SPI_TA_TCC_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi|ta|tcc|cpf,Thu 21 Mar 2024 03:51:28 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv index af4e05ae68..1bb9151c09 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,117917,117917,1048576,256,0,0,8,8,16,64,0x0,0x7f5421004e80,194102861037891,194102861062915,194102861087395,194102861100219 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,117917,117917,1048576,256,0,0,8,8,16,64,0x0,0x7f5421004e80,194102861100209,194102861176995,194102861195875,194102861196962 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,117917,117917,1048576,256,0,0,8,8,16,64,0x0,0x7f5421004e80,194102861208575,194102861217315,194102861236515,194102861237539 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1213587,1213587,1048576,256,0,0,8,8,16,64,0x0,0x7f8d8caa0ec0,1410030696912527,1410030696942687,1410030696966687,1410030696978511 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1213587,1213587,1048576,256,0,0,8,8,16,64,0x0,0x7f8d8caa0ec0,1410030696978611,1410030697050527,1410030697069887,1410030697070915 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1213587,1213587,1048576,256,0,0,8,8,16,64,0x0,0x7f8d8caa0ec0,1410030697081625,1410030697092767,1410030697111327,1410030697112343 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv index 6d08223946..64a7f058da 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,264901,264901,1048576,256,0,0,8,0,16,64,0x0,0x7f68fb114ec0,27991,27991,16384,65536,13987,1573028,197729653263752,197738340012541,197738340033181,197729668961669 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,264901,264901,1048576,256,0,0,8,0,16,64,0x0,0x7f68fb114ec0,40318,40318,16384,65536,8950,1048712,197729668981958,197738340125821,197738340142461,197729669313745 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,264901,264901,1048576,256,0,0,8,0,16,64,0x0,0x7f68fb114ec0,40963,40963,16384,65536,9263,1048628,197729669343392,197738340160861,197738340176861,197729669511239 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4088355,4088355,1048576,256,0,0,8,0,16,64,0x0,0x7fc6831a8ec0,28093,28093,16384,65536,13646,1488060,1411214962656046,1411223666824269,1411223666843789,1411214978786170 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4088355,4088355,1048576,256,0,0,8,0,16,64,0x0,0x7fc6831a8ec0,41300,41300,16384,65536,9532,1048624,1411214978808252,1411223666904109,1411223666920429,1411214979114230 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4088355,4088355,1048576,256,0,0,8,0,16,64,0x0,0x7fc6831a8ec0,40347,40347,16384,65536,9369,1048660,1411214979144658,1411223666941709,1411223666957229,1411214979290854 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv index 8762467a6e..6a5889d0f3 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,265102,265102,1048576,256,0,0,8,0,16,64,0x0,0x7f8645a54ec0,0,0,0,197730137973074,197738340012541,197738340033181,197730153856552 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,265102,265102,1048576,256,0,0,8,0,16,64,0x0,0x7f8645a54ec0,0,0,0,197730153873514,197738340125821,197738340142461,197730154179894 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,265102,265102,1048576,256,0,0,8,0,16,64,0x0,0x7f8645a54ec0,0,0,0,197730154205703,197738340160861,197738340176861,197730154365595 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4088556,4088556,1048576,256,0,0,8,0,16,64,0x0,0x7f6e02058ec0,0,0,0,1411215454503673,1411223666824269,1411223666843789,1411215470538657 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4088556,4088556,1048576,256,0,0,8,0,16,64,0x0,0x7f6e02058ec0,0,0,0,1411215470555950,1411223666904109,1411223666920429,1411215470848273 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4088556,4088556,1048576,256,0,0,8,0,16,64,0x0,0x7f6e02058ec0,0,0,0,1411215470874683,1411223666941709,1411223666957229,1411215471030047 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv index 3ec0290360..4e80d3977e 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,265303,265303,1048576,256,0,0,8,0,16,64,0x0,0x7f1a876d0ec0,65536,198076,22038840,197730616407645,197738340012541,197738340033181,197730632452178 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,265303,265303,1048576,256,0,0,8,0,16,64,0x0,0x7f1a876d0ec0,65536,254952,28605296,197730632472366,197738340125821,197738340142461,197730632706750 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,265303,265303,1048576,256,0,0,8,0,16,64,0x0,0x7f1a876d0ec0,65536,255292,28543104,197730632733601,197738340160861,197738340176861,197730632865109 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4088759,4088759,1048576,256,0,0,8,0,16,64,0x0,0x7f01252f0ec0,65536,169946,19106952,1411215939111268,1411223666824269,1411223666843789,1411215955317176 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4088759,4088759,1048576,256,0,0,8,0,16,64,0x0,0x7f01252f0ec0,65536,224994,25313304,1411215955336402,1411223666904109,1411223666920429,1411215955604219 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4088759,4088759,1048576,256,0,0,8,0,16,64,0x0,0x7f01252f0ec0,65536,229044,25547480,1411215955630398,1411223666941709,1411223666957229,1411215955782065 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv index 58b602b1b9..501065ecbf 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,265506,265506,1048576,256,0,0,8,0,16,64,0x0,0x7f651c14cec0,32768,299920,33591524,197731094150167,197738340012541,197738340033181,197731109995744 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,265506,265506,1048576,256,0,0,8,0,16,64,0x0,0x7f651c14cec0,32768,580241,64987892,197731110013077,197738340125821,197738340142461,197731110326710 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,265506,265506,1048576,256,0,0,8,0,16,64,0x0,0x7f651c14cec0,32768,569729,63814316,197731110352609,197738340160861,197738340176861,197731110507672 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4088953,4088953,1048576,256,0,0,8,0,16,64,0x0,0x7fc32b6a0ec0,32768,288575,32318988,1411216424877755,1411223666824269,1411223666843789,1411216440997369 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4088953,4088953,1048576,256,0,0,8,0,16,64,0x0,0x7fc32b6a0ec0,32768,576731,64594100,1411216441017027,1411223666904109,1411223666920429,1411216441363151 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4088953,4088953,1048576,256,0,0,8,0,16,64,0x0,0x7fc32b6a0ec0,32768,585287,65575044,1411216441390202,1411223666941709,1411223666957229,1411216441548382 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv index e03729ad67..7e6030e9d5 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,265690,265690,1048576,256,0,0,8,0,16,64,0x0,0x7f00f8b24ec0,27542,27542,10902,220344,16384,10616210,128610,0,42968660,197731581001963,197738340012541,197738340033181,197731596878277 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,265690,265690,1048576,256,0,0,8,0,16,64,0x0,0x7f00f8b24ec0,41116,41116,13786,328936,16384,18935434,220606,0,76241532,197731596909767,197738340125821,197738340142461,197731597137267 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,265690,265690,1048576,256,0,0,8,0,16,64,0x0,0x7f00f8b24ec0,40838,40838,13793,326712,16384,19028590,218114,0,76587924,197731597169007,197738340160861,197738340176861,197731597315545 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4089156,4089156,1048576,256,0,0,8,0,16,64,0x0,0x7f34212a4ec0,27516,27516,10948,220136,16384,10825782,127517,0,43813480,1411216919014351,1411223666824269,1411223666843789,1411216935159043 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4089156,4089156,1048576,256,0,0,8,0,16,64,0x0,0x7f34212a4ec0,39758,39758,12845,318072,16384,19019767,217900,0,76565452,1411216935180143,1411223666904109,1411223666920429,1411216935488556 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4089156,4089156,1048576,256,0,0,8,0,16,64,0x0,0x7f34212a4ec0,40306,40306,12700,322456,16384,19236955,220697,0,77432856,1411216935523833,1411223666941709,1411223666957229,1411216935689847 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/log.txt b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/log.txt new file mode 100644 index 0000000000..decd0e4e44 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/log.txt @@ -0,0 +1,565 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'spi', 'ta', 'tcc', 'cpf'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_161122' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161122_4088195' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161122_4088195/input0_results_240321_161122' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161122_4088195/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161122_4088195/input0_results_240321_161122 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_161123' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161123_4088396' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161123_4088396/input0_results_240321_161123' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161123_4088396/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161123_4088396/input0_results_240321_161123 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_161123' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161123_4088598' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161123_4088598/input0_results_240321_161123' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161123_4088598/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161123_4088598/input0_results_240321_161123 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_161124' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161124_4088793' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161124_4088793/input0_results_240321_161124' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161124_4088793/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161124_4088793/input0_results_240321_161124 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_161124' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161124_4088996' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161124_4088996/input0_results_240321_161124' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161124_4088996/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161124_4088996/input0_results_240321_161124 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_161125' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161125_4089180' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161125_4089180/input0_results_240321_161125' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161125_4089180/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161125_4089180/input0_results_240321_161125 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_161125' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161125_4089372' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161125_4089372/input0_results_240321_161125' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161125_4089372/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 19 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161125_4089372/input0_results_240321_161125 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_161126' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161126_4089556' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161126_4089556/input0_results_240321_161126' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161126_4089556/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161126_4089556/input0_results_240321_161126 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_161126' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161126_4089740' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161126_4089740/input0_results_240321_161126' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161126_4089740/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161126_4089740/input0_results_240321_161126 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_161127' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161127_4089932' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161127_4089932/input0_results_240321_161127' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161127_4089932/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161127_4089932/input0_results_240321_161127 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_161127' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161127_4090115' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161127_4090115/input0_results_240321_161127' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161127_4090115/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 18 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161127_4090115/input0_results_240321_161127 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_161128' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161128_4090305' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161128_4090305/input0_results_240321_161128' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161128_4090305/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161128_4090305/input0_results_240321_161128 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_161128' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161128_4090506' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161128_4090506/input0_results_240321_161128' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161128_4090506/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161128_4090506/input0_results_240321_161128 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_161129' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161129_4090696' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161129_4090696/input0_results_240321_161129' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161129_4090696/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161129_4090696/input0_results_240321_161129 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_161129' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161129_4090887' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161129_4090887/input0_results_240321_161129' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161129_4090887/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161129_4090887/input0_results_240321_161129 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_161130' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161130_4091070' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161130_4091070/input0_results_240321_161130' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161130_4091070/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161130_4091070/input0_results_240321_161130 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_161130' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161130_4091259' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161130_4091259/input0_results_240321_161130' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161130_4091259/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 13 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161130_4091259/input0_results_240321_161130 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_161130' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161130_4091462' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161130_4091462/input0_results_240321_161130' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161130_4091462/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161130_4091462/input0_results_240321_161130 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_161131' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161131_4091651' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161131_4091651/input0_results_240321_161131' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161131_4091651/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161131_4091651/input0_results_240321_161131 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf.csv index f612280d07..5f582716a7 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_1,obj_1,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_6,obj_6,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_7,obj_7,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_9,obj_9,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_11,obj_11,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_12,obj_12,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f1f91fa8ec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131081.0,34724.0,46249.0,19287.0,64,0x7f79ec6c0ec0,131072,0,0,0,0,0,0,0,16384,0,39490065.0,35717872.0,0.0,64,0x7fd989278ec0,0,393216,163840,0,0,0,0,0,18078,0.0,0.0,4096,16384,1344,0,56.0,6.0,0.0,204330.0,64,0x7faf24d0cec0,1742,117297,0,0,65536,63800,56,1680,64,0x7f6a58f3cec0,218520,126960,16384,0,16384,16384,32768,49152,27314,27314,1052955.0,0.0,216809,135082,27314,0,874048.0,493813.0,0.0,0.0,64,0x7fdb88d68ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,234886.0,0,0,298.0,131083.0,0.0,14.0,64,0x7f400d080ec0,10899495,9735651,819780,344064,1621749,0,0,163840,283274.0,32768.0,487861,0,131072.0,131072.0,0.0,131072.0,64,0x7fd0cc9bcec0,0,0,0,0,0,0,0,114688,0.0,0.0,12360,18768,0,26168,204288.0,0.0,73209.0,131079.0,64,0x7f3658754ec0,0,0,0,0,0,0,168,56,64,0x7fbff87d8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,9804,0,0,73114.0,131072.0,0.0,65568.0,64,0x7f66b5768ec0,32768,32768,0,64,0x7f394f3a0ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fb0d7274ec0,0,0,0,224,0,65536,64261,56,197738340012541,197738340033181 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f1f91fa8ec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131072.0,103006.0,45538.0,0.0,64,0x7f79ec6c0ec0,131072,0,0,0,0,0,0,0,16384,0,120457593.0,58766642.0,0.0,64,0x7fd989278ec0,0,393216,163840,0,0,0,0,0,27601,0.0,0.0,4096,16384,2029,0,56.0,0.0,0.0,200309.0,64,0x7faf24d0cec0,0,192825,0,0,65536,63800,56,1680,64,0x7f6a58f3cec0,298056,205865,16384,0,16384,16384,32768,49152,37256,37256,1641830.0,0.0,298048,215699,37256,0,1192192.0,769375.0,2.0,0.0,64,0x7fdb88d68ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,488393.0,0,0,5625.0,131075.0,0.0,4.0,64,0x7f400d080ec0,17880032,17293519,242449,344064,2563790,0,0,163840,610908.0,32768.0,807534,0,91016.0,91016.0,0.0,91016.0,64,0x7fd0cc9bcec0,0,0,0,0,0,0,0,114688,0.0,0.0,27561,27138,0,35627,201041.0,0.0,69966.0,131075.0,64,0x7f3658754ec0,0,0,0,0,0,0,0,56,64,0x7fbff87d8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,16543,0,0,69339.0,131072.0,0.0,45524.0,64,0x7f66b5768ec0,32768,32768,0,64,0x7f394f3a0ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fb0d7274ec0,0,0,0,56,0,65536,65536,0,197738340125821,197738340142461 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f1f91fa8ec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131085.0,84607.0,45537.0,0.0,64,0x7f79ec6c0ec0,131072,0,0,0,0,0,0,0,16384,0,114147217.0,58588700.0,0.0,64,0x7fd989278ec0,0,393216,163840,0,0,0,0,0,30286,0.0,0.0,4096,16384,2098,0,56.0,10.0,0.0,200992.0,64,0x7faf24d0cec0,0,194417,0,0,65536,63800,56,1680,64,0x7f6a58f3cec0,323152,214939,16384,0,16384,16384,32768,49152,40393,40393,1663115.0,0.0,323144,224787,40393,0,1292576.0,772002.0,0.0,0.0,64,0x7fdb88d68ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,572071.0,0,0,2423.0,131083.0,0.0,20.0,64,0x7f400d080ec0,19566165,18231591,990510,344064,2793194,0,0,163840,564966.0,32768.0,1000045,0,91086.0,91086.0,0.0,91086.0,64,0x7fd0cc9bcec0,0,0,0,0,0,0,0,114688,0.0,0.0,29796,26724,0,38585,200339.0,0.0,69257.0,131082.0,64,0x7f3658754ec0,0,0,0,0,0,0,0,56,64,0x7fbff87d8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,20896,0,0,69107.0,131072.0,0.0,45533.0,64,0x7f66b5768ec0,32768,32768,0,64,0x7f394f3a0ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fb0d7274ec0,0,0,0,56,0,65536,65536,0,197738340160861,197738340176861 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_1,obj_1,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_2,obj_2,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_4,obj_4,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_10,obj_10,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_11,obj_11,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_12,obj_12,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fb87e778ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,218697.0,0,0,402.0,131080.0,0.0,8.0,64,0x7efd77570ec0,0,0,0,0,0,0,0,114688,0.0,0.0,13176,18810,0,26862,204658.0,0.0,73576.0,131082.0,64,0x7f549a470ec0,1253,115640,0,0,65536,63800,56,1680,64,0x7ff92de7cec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131081.0,34847.0,46378.0,19158.0,64,0x7f4eda914ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,10453,0,0,73533.0,131072.0,0.0,65568.0,64,0x7f823f414ec0,232848,134505,16384,0,16384,16384,32768,49152,29105,29105,1141667.0,0.0,231137,142628,29105,0,931360.0,497531.0,0.0,0.0,64,0x7fb26c5c0ec0,32768,32768,0,64,0x7f78fbed8ec0,0,0,0,0,0,0,168,56,64,0x7f3485b14ec0,131072,0,0,0,0,0,0,0,16384,0,39473983.0,34618154.0,0.0,64,0x7f1cf3228ec0,0,393216,163840,0,0,0,0,0,18294,0.0,0.0,4096,16384,1341,0,56.0,4.0,0.0,204200.0,64,0x7fc4100d8ec0,10909054,9734653,830337,344064,1646888,0,0,163840,313146.0,32768.0,499709,0,131072.0,131072.0,0.0,131072.0,64,0x7f747d714ec0,0,0,0,224,0,65536,63654,56,64,0x7fced883cec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,1411223666824269,1411223666843789 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fb87e778ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,439536.0,0,0,3470.0,131073.0,0.0,0.0,64,0x7efd77570ec0,0,0,0,0,0,0,0,114688,0.0,0.0,25634,26019,0,35433,200121.0,0.0,69048.0,131073.0,64,0x7f549a470ec0,0,182346,0,0,65536,63800,56,1680,64,0x7ff92de7cec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131072.0,90238.0,45576.0,0.0,64,0x7f4eda914ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,15487,0,0,69578.0,131072.0,0.0,45502.0,64,0x7f823f414ec0,334744,226807,16384,0,16384,16384,32768,49152,41842,41842,1750809.0,0.0,334736,236635,41842,0,1338944.0,783832.0,0.0,0.0,64,0x7fb26c5c0ec0,32768,32768,0,64,0x7f78fbed8ec0,0,0,0,0,0,0,0,56,64,0x7f3485b14ec0,131072,0,0,0,0,0,0,0,16384,0,125316336.0,60693578.0,0.0,64,0x7f1cf3228ec0,0,393216,163840,0,0,0,0,0,27924,0.0,0.0,4096,16384,2092,0,56.0,0.0,0.0,200417.0,64,0x7fc4100d8ec0,17639070,17012945,282061,344064,2518514,0,0,163840,546923.0,32768.0,756985,0,90726.0,90726.0,0.0,90726.0,64,0x7f747d714ec0,0,0,0,56,0,65536,65536,0,64,0x7fced883cec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,1411223666904109,1411223666920429 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fb87e778ec0,114688,0,32768,32768,16384,16384,65536,49152,0.0,563950.0,0,0,2950.0,131081.0,0.0,16.0,64,0x7efd77570ec0,0,0,0,0,0,0,0,114688,0.0,0.0,30621,26556,0,39578,200720.0,0.0,69636.0,131084.0,64,0x7f549a470ec0,0,181206,0,0,65536,63800,56,1680,64,0x7ff92de7cec0,10485760,65536,0,0,0,16384,0,0,32768.0,16384.0,0,0,131081.0,91108.0,45536.0,0.0,64,0x7f4eda914ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,22487,0,0,69592.0,131072.0,0.0,45669.0,64,0x7f823f414ec0,328736,222358,16384,0,16384,16384,32768,49152,41091,41091,1770061.0,0.0,328728,232199,41091,0,1314912.0,778402.0,0.0,0.0,64,0x7fb26c5c0ec0,32768,32768,0,64,0x7f78fbed8ec0,0,0,0,0,0,0,0,56,64,0x7f3485b14ec0,131072,0,0,0,0,0,0,0,16384,0,115701376.0,57435570.0,0.0,64,0x7f1cf3228ec0,0,393216,163840,0,0,0,0,0,29837,0.0,0.0,4096,16384,2126,0,56.0,8.0,0.0,200154.0,64,0x7fc4100d8ec0,19820159,18420687,1055408,344064,2846556,0,0,163840,668199.0,32768.0,1034986,0,91278.0,91278.0,0.0,91278.0,64,0x7f747d714ec0,0,0,0,56,0,65536,65536,0,64,0x7fced883cec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,1411223666941709,1411223666957229 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/roofline.csv index 4dd3f7395d..b223ee3226 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/roofline.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.8623,1388.2758,1389.4489,5015.0771,5012.0532,5018.1011,9223.1035,9222.5381,9223.6689,18054.863,18053.896,18055.83,20934.51,20873.84,20995.18,20265.703,20265.008,20266.398,170438.22,170433.8,170442.64,164871.09,164866.47,164875.72,41417.742,41417.215,41418.27,41475.672,41475.148,41476.195,166335.41,165840.38,166830.44 -1,1389.1528,1388.5985,1389.7072,5026.2896,5024.1938,5028.3853,9233.2656,9232.6162,9233.915,18097.365,18092.242,18102.488,20973.391,20905.871,21040.91,20296.227,20295.758,20296.695,170859.81,170854.62,170865,165145.91,165142.66,165149.16,41491.523,41490.824,41492.223,41550.941,41550.047,41551.836,166909.02,166906.33,166911.7 -2,1388.7634,1388.2198,1389.307,5035.9404,5033.4253,5038.4556,9258.4541,9257.6875,9259.2207,18101.965,18100.9,18103.029,21045.875,21045.451,21046.299,20350.631,20350.086,20351.176,171082.23,171077.95,171086.52,165465.41,165461.77,165469.05,41570.293,41569.453,41571.133,41627.977,41627,41628.953,166901.95,166307.72,167496.19 -3,1388.174,1387.5312,1388.8167,5030.9858,5029.6353,5032.3364,9239.751,9239.1602,9240.3418,18025.277,18021.568,18028.986,21033.902,21033.303,21034.502,20310.432,20309.742,20311.121,171030.23,171026.98,171033.48,165220.55,165216.59,165224.5,41438.586,41283.68,41593.492,41580.109,41579.582,41580.637,167006.55,167004.34,167008.75 +0,1388.7007,1388.1306,1389.2708,5017.5225,5014.4141,5020.6309,9228.7451,9228.0869,9229.4033,17715.516,17712.518,17718.514,20944.932,20884.609,21005.254,20275.439,20274.982,20275.896,170504.62,170500.95,170508.3,164933.23,164928.62,164937.84,41440.047,41439.539,41440.555,41499.656,41499.043,41500.27,166420.75,165926.91,166914.59 +1,1389.1136,1388.5657,1389.6616,5029.9849,5028.0312,5031.9385,9235.3691,9234.626,9236.1123,18234.205,18232.467,18235.943,20981.51,20914.275,21048.744,20296.695,20296.15,20297.24,170893.02,170888.69,170897.34,165141.83,165138.44,165145.22,41489.523,41488.848,41490.199,41549.398,41548.219,41550.578,166891.27,166888.33,166894.2 +2,1388.4856,1387.9526,1389.0186,5036.5444,5034.3003,5038.7886,9260.8037,9260.0566,9261.5508,18219.021,18218.016,18220.027,21051.648,21051.223,21052.074,20353.875,20353.369,20354.381,171143.95,171139.86,171148.05,165539.94,165536.73,165543.14,41591.004,41589.895,41592.113,41653.695,41652.676,41654.715,166987.88,166397.8,167577.95 +3,1388.8566,1388.2448,1389.4684,5032.915,5031.1968,5034.6333,9237.1543,9236.3555,9237.9531,18325.514,18324.742,18326.285,21029.713,21029.316,21030.109,20303.711,20303.039,20304.383,171010.91,171006.73,171015.08,165115.25,165110.08,165120.42,41417.871,41265.07,41570.672,41552.566,41551.793,41553.34,166935.78,166931.64,166939.92 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/sysinfo.csv index adffddd8da..c8b7277582 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SPI_TA_TCC_CPF,./sample/vcopy -n 1048576 -b 256 -i 3,sq|spi|ta|tcc|cpf|roofline,Thu 07 Mar 2024 02:06:36 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_SQ_SPI_TA_TCC_CPF,./tests/vcopy -n 1048576 -b 256 -i 3,sq|spi|ta|tcc|cpf|roofline,Thu 21 Mar 2024 04:11:22 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv index 65ea55bd1f..f07878f3dd 100644 --- a/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SPI_TA_TCC_CPF/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,268356,268356,1048576,256,0,0,8,0,16,64,0x0,0x7f8141afcec0,197738339987385,197738340012541,197738340033181,197738340046206 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,268356,268356,1048576,256,0,0,8,0,16,64,0x0,0x7f8141afcec0,197738340044352,197738340125821,197738340142461,197738340144001 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,268356,268356,1048576,256,0,0,8,0,16,64,0x0,0x7f8141afcec0,197738340153509,197738340160861,197738340176861,197738340178055 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4091811,4091811,1048576,256,0,0,8,0,16,64,0x0,0x7ff849c98ec0,1411223666799862,1411223666824269,1411223666843789,1411223666853163 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4091811,4091811,1048576,256,0,0,8,0,16,64,0x0,0x7ff849c98ec0,1411223666854675,1411223666904109,1411223666920429,1411223666921211 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4091811,4091811,1048576,256,0,0,8,0,16,64,0x0,0x7ff849c98ec0,1411223666931631,1411223666941709,1411223666957229,1411223666958021 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv index 0fa7ec4f6c..24c13a239c 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,122674,122674,1048576,256,0,0,8,8,16,64,0x0,0x7fa61d720e80,48220,48220,16384,65536,14544,1868668,194118309669326,194125699131803,194125699155643,194118317402538 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,122674,122674,1048576,256,0,0,8,8,16,64,0x0,0x7fa61d720e80,43074,43074,16384,65536,8103,1048576,194118317423819,194125699242363,194125699260923,194118317787547 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,122674,122674,1048576,256,0,0,8,8,16,64,0x0,0x7fa61d720e80,42466,42466,16384,65536,8183,1048576,194118317819288,194125699281723,194125699300603,194118318003877 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1218340,1218340,1048576,256,0,0,8,8,16,64,0x0,0x7f0b11b60ec0,48250,48250,16384,65536,14539,1866516,1410045382517693,1410052555664646,1410052555689286,1410045390201204 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1218340,1218340,1048576,256,0,0,8,8,16,64,0x0,0x7f0b11b60ec0,41492,41492,16384,65536,8164,1048584,1410045390224538,1410052555782406,1410052555801126,1410045390545834 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1218340,1218340,1048576,256,0,0,8,8,16,64,0x0,0x7f0b11b60ec0,41026,41026,16384,65536,8014,1048584,1410045390577755,1410052555821446,1410052555840486,1410045390771300 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv index f5f73f6e30..b6589f602c 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,122861,122861,1048576,256,0,0,8,8,16,64,0x0,0x7f92fac8ee80,0,0,0,194118798617961,194125699131803,194125699155643,194118806316107 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,122861,122861,1048576,256,0,0,8,8,16,64,0x0,0x7f92fac8ee80,0,0,0,194118806335313,194125699242363,194125699260923,194118806630883 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,122861,122861,1048576,256,0,0,8,8,16,64,0x0,0x7f92fac8ee80,0,0,0,194118806659387,194125699281723,194125699300603,194118806829449 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1218527,1218527,1048576,256,0,0,8,8,16,64,0x0,0x7f40d770cec0,0,0,0,1410045861048205,1410052555664646,1410052555689286,1410045868686711 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1218527,1218527,1048576,256,0,0,8,8,16,64,0x0,0x7f40d770cec0,0,0,0,1410045868708252,1410052555782406,1410052555801126,1410045868999521 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1218527,1218527,1048576,256,0,0,8,8,16,64,0x0,0x7f40d770cec0,0,0,0,1410045869028005,1410052555821446,1410052555840486,1410045869197425 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv index 0c46932e00..6b19ff6d41 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,123049,123049,1048576,256,0,0,8,8,16,64,0x0,0x7f964be06e80,65536,203206,25982456,194119291932773,194125699131803,194125699155643,194119299617183 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,123049,123049,1048576,256,0,0,8,8,16,64,0x0,0x7f964be06e80,65536,170204,21847384,194119299639586,194125699242363,194125699260923,194119299885892 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,123049,123049,1048576,256,0,0,8,8,16,64,0x0,0x7f964be06e80,65536,169822,21706128,194119299914736,194125699281723,194125699300603,194119300065041 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1218711,1218711,1048576,256,0,0,8,8,16,64,0x0,0x7fe3c9b24ec0,65536,188610,24111576,1410046337692019,1410052555664646,1410052555689286,1410046345340344 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1218711,1218711,1048576,256,0,0,8,8,16,64,0x0,0x7fe3c9b24ec0,65536,152478,19496112,1410046345360010,1410052555782406,1410052555801126,1410046345678561 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1218711,1218711,1048576,256,0,0,8,8,16,64,0x0,0x7fe3c9b24ec0,65536,169440,21694800,1410046345706855,1410052555821446,1410052555840486,1410046345883598 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv index 84229d7996..1e72e2477a 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,123235,123235,1048576,256,0,0,8,8,16,64,0x0,0x7f60e135ae80,32768,667174,85383028,194119777699844,194125699131803,194125699155643,194119785694431 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,123235,123235,1048576,256,0,0,8,8,16,64,0x0,0x7f60e135ae80,32768,673940,86254240,194119785714219,194125699242363,194125699260923,194119786050996 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,123235,123235,1048576,256,0,0,8,8,16,64,0x0,0x7f60e135ae80,32768,668795,85597592,194119786085021,194125699281723,194125699300603,194119786271163 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1218894,1218894,1048576,256,0,0,8,8,16,64,0x0,0x7f56e0084ec0,32768,654480,83779676,1410046812967141,1410052555664646,1410052555689286,1410046820630624 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1218894,1218894,1048576,256,0,0,8,8,16,64,0x0,0x7f56e0084ec0,32768,687881,88070368,1410046820652255,1410052555782406,1410052555801126,1410046820946380 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1218894,1218894,1048576,256,0,0,8,8,16,64,0x0,0x7f56e0084ec0,32768,653216,83625856,1410046820974252,1410052555821446,1410052555840486,1410046821144353 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv index 51607afe1b..203a6e9f33 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,123419,123419,1048576,256,0,0,8,8,16,64,0x0,0x7f7130cf6e80,47994,47994,16739,383960,16384,25209574,233475,0,101327412,194120274842524,194125699131803,194125699155643,194120282542253 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,123419,123419,1048576,256,0,0,8,8,16,64,0x0,0x7f7130cf6e80,41992,41992,12962,335944,16384,25266450,231306,0,101551480,194120282569234,194125699242363,194125699260923,194120282895672 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,123419,123419,1048576,256,0,0,8,8,16,64,0x0,0x7f7130cf6e80,41856,41856,12840,334856,16384,24684109,230369,0,99229788,194120282933744,194125699281723,194125699300603,194120283125557 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1219092,1219092,1048576,256,0,0,8,8,16,64,0x0,0x7fb76d454ec0,48712,48712,17847,389704,16384,25876328,236525,0,104037036,1410047289994969,1410052555664646,1410052555689286,1410047297715009 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1219092,1219092,1048576,256,0,0,8,8,16,64,0x0,0x7fb76d454ec0,42202,42202,12800,337624,16384,25110894,234139,0,100982320,1410047297745075,1410052555782406,1410052555801126,1410047298169226 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1219092,1219092,1048576,256,0,0,8,8,16,64,0x0,0x7fb76d454ec0,42578,42578,13005,340632,16384,25017366,235365,0,100596720,1410047298207618,1410052555821446,1410052555840486,1410047298366167 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/log.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/log.txt new file mode 100644 index 0000000000..4647de7883 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/log.txt @@ -0,0 +1,476 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'sqc', 'tcp', 'cpc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155151' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155151_1218180' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155151_1218180/input0_results_240321_155151' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155151_1218180/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155151_1218180/input0_results_240321_155151 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155151' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155151_1218367' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155151_1218367/input0_results_240321_155151' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155151_1218367/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155151_1218367/input0_results_240321_155151 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155152' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155152_1218551' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155152_1218551/input0_results_240321_155152' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155152_1218551/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155152_1218551/input0_results_240321_155152 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155152' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155152_1218734' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155152_1218734/input0_results_240321_155152' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155152_1218734/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155152_1218734/input0_results_240321_155152 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155153' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155153_1218932' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155153_1218932/input0_results_240321_155153' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155153_1218932/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155153_1218932/input0_results_240321_155153 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155153' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155153_1219133' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155153_1219133/input0_results_240321_155153' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155153_1219133/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_BUSY_CU_CYCLES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155153_1219133/input0_results_240321_155153 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155154' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155154_1219317' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155154_1219317/input0_results_240321_155154' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155154_1219317/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 14 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155154_1219317/input0_results_240321_155154 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155154' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155154_1219503' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155154_1219503/input0_results_240321_155154' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155154_1219503/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 14 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155154_1219503/input0_results_240321_155154 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155155' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155155_1219699' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155155_1219699/input0_results_240321_155155' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155155_1219699/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 14 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155155_1219699/input0_results_240321_155155 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155155' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155155_1219899' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155155_1219899/input0_results_240321_155155' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155155_1219899/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 14 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155155_1219899/input0_results_240321_155155 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155156' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155156_1220083' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155156_1220083/input0_results_240321_155156' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155156_1220083/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 13 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, CPC_ME1_DC0_SPI_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155156_1220083/input0_results_240321_155156 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155156' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155156_1220268' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155156_1220268/input0_results_240321_155156' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155156_1220268/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155156_1220268/input0_results_240321_155156 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155157' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155157_1220468' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155157_1220468/input0_results_240321_155157' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155157_1220468/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155157_1220468/input0_results_240321_155157 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155157' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155157_1220651' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155157_1220651/input0_results_240321_155157' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155157_1220651/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 11 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155157_1220651/input0_results_240321_155157 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155158' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155158_1220852' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155158_1220852/input0_results_240321_155158' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155158_1220852/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155158_1220852/input0_results_240321_155158 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155158' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155158_1221053' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155158_1221053/input0_results_240321_155158' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155158_1221053/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155158_1221053/input0_results_240321_155158 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv index 32a911ff60..a972f4b7c4 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_2,obj_2,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,CPC_ME1_DC0_SPI_BUSY,wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_4,obj_4,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_6,obj_6,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_7,obj_7,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_8,obj_8,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_BUSY_CU_CYCLES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea865a8e80,131072.0,131072.0,0.0,2543874.0,64,0x7fa4c0e92e80,0,0,192,0,65536,64325,48,1550,0.0,0.0,0.0,32768.0,538,47685,64,0x7f7613e96e80,1932381,360448,163840,0,0,180224,114688,0,70516604.0,208780825.0,79499142.0,131072.0,26008,64,0x7f9d1dac2e80,32768,0,0,0,16384,16384,393216,22941776,960.0,514021.0,0.0,524288.0,0,17981,64,0x7fd9def56e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f588375ee80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,2728,47404,64,0x7fd8cc436e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7f36bfe3ce80,193103,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,9922,550,64,0x7f8481244e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f8cb54eae80,385504,236665,16384,3479670,25335685,144,48,0,48187,48187,3897750.0,3077421.0,7001.0,1048151.0,48187,0,194125699131803,194125699155643 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea865a8e80,131072.0,131072.0,0.0,2635437.0,64,0x7fa4c0e92e80,0,0,48,0,65536,65536,0,0,0.0,0.0,0.0,32768.0,588,48185,64,0x7f7613e96e80,1586536,360448,163840,0,0,180224,114688,0,70397592.0,197861031.0,76054912.0,131072.0,25898,64,0x7f9d1dac2e80,32768,0,0,0,16384,16384,393216,25081865,240.0,521663.0,0.0,524288.0,0,21203,64,0x7fd9def56e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f588375ee80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,5932,40018,64,0x7fd8cc436e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7f36bfe3ce80,121776,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,7773,588,64,0x7f8481244e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f8cb54eae80,344704,231920,16384,3397452,25194808,0,48,0,43087,43087,3763350.0,3104622.0,5667.0,1066874.0,43087,0,194125699242363,194125699260923 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea865a8e80,131072.0,131072.0,0.0,2515231.0,64,0x7fa4c0e92e80,0,0,48,0,65536,65536,0,0,0.0,0.0,0.0,32768.0,432,41348,64,0x7f7613e96e80,1400699,360448,163840,0,0,180224,114688,0,72535482.0,188588285.0,74214524.0,131072.0,26085,64,0x7f9d1dac2e80,32768,0,0,0,16384,16384,393216,23096321,960.0,513907.0,0.0,524288.0,0,14780,64,0x7fd9def56e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f588375ee80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,4573,38128,64,0x7fd8cc436e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7f36bfe3ce80,194465,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,8908,2385,64,0x7f8481244e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f8cb54eae80,336352,226728,16384,3304402,24106612,0,48,0,42043,42043,3687584.0,3011362.0,5447.0,1000897.0,42043,0,194125699281723,194125699300603 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,CPC_ME1_DC0_SPI_BUSY,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_BUSY_CU_CYCLES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_2,obj_2,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_3,obj_3,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_4,obj_4,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_6,obj_6,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_7,obj_7,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_8,obj_8,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_9,obj_9,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f84eefd8ec0,2780165,360448,163840,0,0,180224,114688,0,64780144.0,185482776.0,75048055.0,131072.0,26617,64,0x7f5b501f8ec0,393312,242360,16384,3540683,25484318,144,48,0,49163,49163,3982590.0,3087969.0,6576.0,944444.0,49163,0,64,0x7fd986484ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f390b178ec0,32768,0,0,0,16384,16384,393216,21989951,960.0,513881.0,0.0,524288.0,0,17165,64,0x7f4863838ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7fe646b50ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,913,47043,64,0x7f21f7694ec0,0,0,192,0,65536,64487,48,1338,0.0,0.0,0.0,32768.0,538,49165,64,0x7fbcb5074ec0,131072.0,131072.0,0.0,2569278.0,64,0x7fa46c6fcec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7fefea870ec0,183224,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,10294,588,1410052555664646,1410052555689286 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f84eefd8ec0,1974863,360448,163840,0,0,180224,114688,0,67206741.0,193719173.0,76208101.0,131072.0,26143,64,0x7f5b501f8ec0,351328,233390,16384,3401287,24443276,0,48,0,43915,43915,3787563.0,3120102.0,7502.0,1304243.0,43915,0,64,0x7fd986484ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f390b178ec0,32768,0,0,0,16384,16384,393216,21026213,962.0,513811.0,0.0,524288.0,0,22110,64,0x7f4863838ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7fe646b50ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,913,38155,64,0x7f21f7694ec0,0,0,48,0,65536,65536,0,0,0.0,0.0,0.0,32768.0,435,38691,64,0x7fbcb5074ec0,131072.0,131072.0,0.0,2595909.0,64,0x7fa46c6fcec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7fefea870ec0,460364,0,0,65536,62807,96,2633,32768,2097152.0,2097152.0,1048576.0,1048576.0,23594,4691,1410052555782406,1410052555801126 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f84eefd8ec0,2417863,360448,163840,0,0,180224,114688,0,63897395.0,178058888.0,72218890.0,131072.0,27451,64,0x7f5b501f8ec0,341320,226706,16384,3315284,24492848,0,48,0,42664,42664,3684930.0,3034516.0,6556.0,1097763.0,42664,0,64,0x7fd986484ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,64,0x7f390b178ec0,32768,0,0,0,16384,16384,393216,22583597,960.0,513980.0,0.0,524288.0,0,13117,64,0x7f4863838ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,64,0x7fe646b50ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,3210,38637,64,0x7f21f7694ec0,0,0,48,0,65536,65536,0,0,0.0,0.0,0.0,32768.0,432,42204,64,0x7fbcb5074ec0,131072.0,131072.0,0.0,2554134.0,64,0x7fa46c6fcec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7fefea870ec0,219541,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,8654,2406,1410052555821446,1410052555840486 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv index f390c406ae..8c68f6d235 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SQC_TCP_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|sqc|tcp|cpc,Thu 07 Mar 2024 01:06:23 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_SQC_TCP_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|sqc|tcp|cpc,Thu 21 Mar 2024 03:51:50 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv index 3bec46a004..0dedd7ba45 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,125477,125477,1048576,256,0,0,8,8,16,64,0x0,0x7f7838d5ce80,194125699105040,194125699131803,194125699155643,194125699167298 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,125477,125477,1048576,256,0,0,8,8,16,64,0x0,0x7f7838d5ce80,194125699168571,194125699242363,194125699260923,194125699262428 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,125477,125477,1048576,256,0,0,8,8,16,64,0x0,0x7f7838d5ce80,194125699273650,194125699281723,194125699300603,194125699301833 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1221213,1221213,1048576,256,0,0,8,8,16,64,0x0,0x7f09b9768ec0,1410052555638620,1410052555664646,1410052555689286,1410052555702841 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1221213,1221213,1048576,256,0,0,8,8,16,64,0x0,0x7f09b9768ec0,1410052555702029,1410052555782406,1410052555801126,1410052555802609 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1221213,1221213,1048576,256,0,0,8,8,16,64,0x0,0x7f09b9768ec0,1410052555813369,1410052555821446,1410052555840486,1410052555841732 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv index 639f3e8c46..504c401830 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,273833,273833,1048576,256,0,0,8,0,16,64,0x0,0x7fe6733a8ec0,28198,28198,16384,65536,13973,1557568,197937688664559,197946401420195,197946401440355,197937704802067 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,273833,273833,1048576,256,0,0,8,0,16,64,0x0,0x7fe6733a8ec0,41193,41193,16384,65536,9264,1048672,197937704822767,197946401459235,197946401475075,197937705081326 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,273833,273833,1048576,256,0,0,8,0,16,64,0x0,0x7fe6733a8ec0,40627,40627,16384,65536,9571,1048672,197937705111132,197946401540515,197946401557155,197937705267588 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4097272,4097272,1048576,256,0,0,8,0,16,64,0x0,0x7f4b435bcec0,27552,27552,16384,65536,13645,1505860,1411423006242428,1411431718618788,1411431718638948,1411423022293032 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4097272,4097272,1048576,256,0,0,8,0,16,64,0x0,0x7f4b435bcec0,41179,41179,16384,65536,9638,1048680,1411423022313701,1411431718721828,1411431718738308,1411423022629719 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4097272,4097272,1048576,256,0,0,8,0,16,64,0x0,0x7f4b435bcec0,40675,40675,16384,65536,9430,1048908,1411423022659595,1411431718758628,1411431718774148,1411423022796885 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv index 33cecaeab4..1d96e3ad79 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,274019,274019,1048576,256,0,0,8,0,16,64,0x0,0x7fbb53a20ec0,0,0,0,197938174609107,197946401420195,197946401440355,197938190896290 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,274019,274019,1048576,256,0,0,8,0,16,64,0x0,0x7fbb53a20ec0,0,0,0,197938190913041,197946401459235,197946401475075,197938191245039 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,274019,274019,1048576,256,0,0,8,0,16,64,0x0,0x7fbb53a20ec0,0,0,0,197938191271509,197946401540515,197946401557155,197938191429588 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4097456,4097456,1048576,256,0,0,8,0,16,64,0x0,0x7f7bb6220ec0,0,0,0,1411423490480204,1411431718618788,1411431718638948,1411423506462880 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4097456,4097456,1048576,256,0,0,8,0,16,64,0x0,0x7f7bb6220ec0,0,0,0,1411423506482326,1411431718721828,1411431718738308,1411423506787243 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4097456,4097456,1048576,256,0,0,8,0,16,64,0x0,0x7f7bb6220ec0,0,0,0,1411423506813793,1411431718758628,1411431718774148,1411423506966432 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv index bfc920e015..4ba516bed2 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,274220,274220,1048576,256,0,0,8,0,16,64,0x0,0x7f95243d8ec0,65536,168886,18969808,197938655465490,197946401420195,197946401440355,197938671639167 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,274220,274220,1048576,256,0,0,8,0,16,64,0x0,0x7f95243d8ec0,65536,223370,25131648,197938671658394,197946401459235,197946401475075,197938671917674 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,274220,274220,1048576,256,0,0,8,0,16,64,0x0,0x7f95243d8ec0,65536,229236,25772136,197938671944375,197946401540515,197946401557155,197938672077206 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4097647,4097647,1048576,256,0,0,8,0,16,64,0x0,0x7f556d28cec0,65536,180600,20282616,1411423969775644,1411431718618788,1411431718638948,1411423986430250 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4097647,4097647,1048576,256,0,0,8,0,16,64,0x0,0x7f556d28cec0,65536,276894,31011616,1411423986449957,1411431718721828,1411431718738308,1411423986728724 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4097647,4097647,1048576,256,0,0,8,0,16,64,0x0,0x7f556d28cec0,65536,239640,26752600,1411423986754754,1411431718758628,1411431718774148,1411423986910338 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv index e5bc356deb..e76c61412f 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,274419,274419,1048576,256,0,0,8,0,16,64,0x0,0x7fd36ab24ec0,32768,288927,32358464,197939132572009,197946401420195,197946401440355,197939148812653 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,274419,274419,1048576,256,0,0,8,0,16,64,0x0,0x7fd36ab24ec0,32768,575469,64457372,197939148830557,197946401459235,197946401475075,197939149112881 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,274419,274419,1048576,256,0,0,8,0,16,64,0x0,0x7fd36ab24ec0,32768,586224,65666236,197939149143299,197946401540515,197946401557155,197939149316015 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4097848,4097848,1048576,256,0,0,8,0,16,64,0x0,0x7fd324608ec0,32768,292269,32732420,1411424449328169,1411431718618788,1411431718638948,1411424465594130 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4097848,4097848,1048576,256,0,0,8,0,16,64,0x0,0x7fd324608ec0,32768,594572,66591636,1411424465616392,1411431718721828,1411431718738308,1411424465986472 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4097848,4097848,1048576,256,0,0,8,0,16,64,0x0,0x7fd324608ec0,32768,583483,65351404,1411424466013013,1411431718758628,1411431718774148,1411424466168797 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv index 9b73d65f8c..334d0277e2 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,274604,274604,1048576,256,0,0,8,0,16,64,0x0,0x7f8127084ec0,27907,27907,11496,223264,16384,10880182,129014,0,44024896,197939615767006,197946401420195,197946401440355,197939631710448 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,274604,274604,1048576,256,0,0,8,0,16,64,0x0,0x7f8127084ec0,41500,41500,13088,332008,16384,20096204,229373,0,80869096,197939631737509,197946401459235,197946401475075,197939632032528 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,274604,274604,1048576,256,0,0,8,0,16,64,0x0,0x7f8127084ec0,41713,41713,13872,333712,16384,19653160,226241,0,79095984,197939632067884,197946401540515,197946401557155,197939632243687 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4098056,4098056,1048576,256,0,0,8,0,16,64,0x0,0x7fc7ec6b4ec0,27606,27606,11068,220856,16384,10833638,128078,0,43839700,1411424933029912,1411431718618788,1411431718638948,1411424949423033 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4098056,4098056,1048576,256,0,0,8,0,16,64,0x0,0x7fc7ec6b4ec0,41755,41755,14094,334048,16384,19515445,223111,0,78552584,1411424949450655,1411431718721828,1411431718738308,1411424949840302 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4098056,4098056,1048576,256,0,0,8,0,16,64,0x0,0x7fc7ec6b4ec0,41585,41585,13907,332688,16384,19302761,223359,0,77701992,1411424949875158,1411431718758628,1411431718774148,1411424950043166 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/log.txt b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/log.txt new file mode 100644 index 0000000000..a195f9598b --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/log.txt @@ -0,0 +1,565 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'sqc', 'tcp', 'cpc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_161450' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161450_4097112' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161450_4097112/input0_results_240321_161450' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161450_4097112/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161450_4097112/input0_results_240321_161450 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_161451' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161451_4097296' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161451_4097296/input0_results_240321_161451' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161451_4097296/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161451_4097296/input0_results_240321_161451 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_161451' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161451_4097487' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161451_4097487/input0_results_240321_161451' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161451_4097487/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161451_4097487/input0_results_240321_161451 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_161452' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161452_4097688' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161452_4097688/input0_results_240321_161452' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161452_4097688/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161452_4097688/input0_results_240321_161452 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_161452' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161452_4097896' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161452_4097896/input0_results_240321_161452' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161452_4097896/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161452_4097896/input0_results_240321_161452 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_161453' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161453_4098087' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161453_4098087/input0_results_240321_161453' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161453_4098087/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161453_4098087/input0_results_240321_161453 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_161453' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161453_4098287' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161453_4098287/input0_results_240321_161453' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161453_4098287/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 14 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161453_4098287/input0_results_240321_161453 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_161454' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161454_4098478' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161454_4098478/input0_results_240321_161454' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161454_4098478/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161454_4098478/input0_results_240321_161454 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_161454' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161454_4098666' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161454_4098666/input0_results_240321_161454' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161454_4098666/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161454_4098666/input0_results_240321_161454 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_161455' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161455_4098870' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161455_4098870/input0_results_240321_161455' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161455_4098870/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161455_4098870/input0_results_240321_161455 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_161455' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161455_4099071' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161455_4099071/input0_results_240321_161455' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161455_4099071/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 14 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161455_4099071/input0_results_240321_161455 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_161456' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161456_4099254' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161456_4099254/input0_results_240321_161456' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161456_4099254/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 14 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161456_4099254/input0_results_240321_161456 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_161456' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161456_4099461' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161456_4099461/input0_results_240321_161456' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161456_4099461/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 14 metrics + |-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161456_4099461/input0_results_240321_161456 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_161457' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161457_4099651' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161457_4099651/input0_results_240321_161457' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161457_4099651/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 13 metrics + |-> [rocprof] SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, CPC_ME1_DC0_SPI_BUSY + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161457_4099651/input0_results_240321_161457 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_161457' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161457_4099842' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161457_4099842/input0_results_240321_161457' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161457_4099842/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161457_4099842/input0_results_240321_161457 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_161458' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161458_4100025' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161458_4100025/input0_results_240321_161458' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161458_4100025/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161458_4100025/input0_results_240321_161458 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_161458' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161458_4100209' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161458_4100209/input0_results_240321_161458' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161458_4100209/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161458_4100209/input0_results_240321_161458 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_161459' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161459_4100412' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161459_4100412/input0_results_240321_161459' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161459_4100412/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161459_4100412/input0_results_240321_161459 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_161459' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161459_4100602' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161459_4100602/input0_results_240321_161459' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161459_4100602/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161459_4100602/input0_results_240321_161459 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv index b5eb681f09..37176eaa76 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,CPC_ME1_DC0_SPI_BUSY,wave_size_1,obj_1,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_2,obj_2,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_3,obj_3,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_4,obj_4,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_5,obj_5,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_6,obj_6,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_7,obj_7,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_8,obj_8,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_9,obj_9,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_12,obj_12,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5bf43d8ec0,0,32768,32768,16384,16384,65536,49152,10485760,26997165.0,85414825.0,40321453.0,131072.0,15250,64,0x7ff45f9c8ec0,1303,140878,0,0,65536,63800,56,1680,64,0x7f06a65d4ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,986628.0,64,0x7f5d58e98ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f2b31420ec0,0,16384,16384,32768,49152,0,393216,163840,27880,27880,1961510.0,1349883.0,3786.0,165711.0,27880,0,64,0x7f1eadf9cec0,344064,225112,130673,1654406,0,0,163840,114688,832.0,515136.0,0.0,524288.0,0,11233,64,0x7fad2c518ec0,0,0,0,16384,16384,10564914,9520920,699930,0.0,0.0,0.0,524288.0,814,26641,64,0x7f5e6e3ccec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f94213d0ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,7086,546,64,0x7f3060d3cec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7fb4d61a8ec0,0,0,0,224,0,65536,64282,56,64,0x7f7ed5c28ec0,32768,32768,0,64,0x7f7f21050ec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,352,27567,197946401420195,197946401440355 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5bf43d8ec0,0,32768,32768,16384,16384,65536,49152,10485760,56798761.0,192841727.0,50094814.0,131072.0,23371,64,0x7ff45f9c8ec0,0,205433,0,0,65536,63800,56,1680,64,0x7f06a65d4ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2097499.0,64,0x7f5d58e98ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f2b31420ec0,0,16384,16384,32768,49152,0,393216,163840,36462,36462,2899286.0,2330506.0,4810.0,343689.0,36462,0,64,0x7f1eadf9cec0,344064,300568,205692,2552053,0,0,163840,114688,0.0,524288.0,0.0,524288.0,0,12176,64,0x7fad2c518ec0,0,0,0,16384,16384,17958261,17365707,248490,0.0,0.0,0.0,524288.0,819,37111,64,0x7f5e6e3ccec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f94213d0ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,8554,550,64,0x7f3060d3cec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7fb4d61a8ec0,0,0,0,56,0,65536,65536,0,64,0x7f7ed5c28ec0,32768,32768,0,64,0x7f7f21050ec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,302,36886,197946401459235,197946401475075 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5bf43d8ec0,0,32768,32768,16384,16384,65536,49152,10485760,58517425.0,207689965.0,45731510.0,131072.0,26266,64,0x7ff45f9c8ec0,0,184796,0,0,65536,63800,56,1680,64,0x7f06a65d4ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2055072.0,64,0x7f5d58e98ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f2b31420ec0,0,16384,16384,32768,49152,0,393216,163840,42234,42234,3176485.0,2544885.0,4671.0,358348.0,42234,0,64,0x7f1eadf9cec0,344064,343640,229400,2862506,0,0,163840,114688,832.0,515160.0,0.0,524288.0,0,14317,64,0x7fad2c518ec0,0,0,0,16384,16384,19021718,17882543,795111,0.0,0.0,0.0,524288.0,2712,38099,64,0x7f5e6e3ccec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f94213d0ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,9664,2458,64,0x7f3060d3cec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7fb4d61a8ec0,0,0,0,56,0,65536,65536,0,64,0x7f7ed5c28ec0,32768,32768,0,64,0x7f7f21050ec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,302,40518,197946401540515,197946401557155 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_1,obj_1,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,wave_size_3,obj_3,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,wave_size_4,obj_4,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_5,obj_5,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,wave_size_6,obj_6,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_7,obj_7,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,wave_size_8,obj_8,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,wave_size_9,obj_9,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_10,obj_10,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_11,obj_11,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_12,obj_12,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,CPC_ME1_DC0_SPI_BUSY,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa9ed1a8ec0,1221,117861,0,0,65536,63800,56,1680,64,0x7f194bfd0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f7f1b340ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,6988,545,64,0x7fc9aed84ec0,344064,225072,131439,1664858,0,0,163840,114688,832.0,515140.0,0.0,524288.0,0,11077,64,0x7f5bbe60cec0,0,0,0,224,0,65536,63650,56,64,0x7f7d1ef30ec0,0,0,0,16384,16384,11218756,9990296,884396,0.0,0.0,0.0,524288.0,814,27691,64,0x7fbcef8dcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7fb363b9cec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,352,26655,64,0x7f4800eacec0,0,16384,16384,32768,49152,0,393216,163840,27997,27997,1960314.0,1371071.0,3332.0,172425.0,27997,0,64,0x7f2d43378ec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7f9b50144ec0,32768,32768,0,64,0x7f7c63c40ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,977939.0,64,0x7f8ae3208ec0,0,32768,32768,16384,16384,65536,49152,10485760,27895429.0,85768377.0,37840141.0,131072.0,15260,1411431718618788,1411431718638948 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa9ed1a8ec0,0,186596,0,0,65536,63800,56,1680,64,0x7f194bfd0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f7f1b340ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,8568,550,64,0x7fc9aed84ec0,344064,300744,206657,2574833,0,0,163840,114688,0.0,524288.0,0.0,524288.0,0,12183,64,0x7f5bbe60cec0,0,0,0,56,0,65536,65536,0,64,0x7f7d1ef30ec0,0,0,0,16384,16384,18346111,17706498,295549,0.0,0.0,0.0,524288.0,819,37311,64,0x7fbcef8dcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7fb363b9cec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,302,36956,64,0x7f4800eacec0,0,16384,16384,32768,49152,0,393216,163840,37749,37749,2967848.0,2373237.0,4751.0,349419.0,37749,0,64,0x7f2d43378ec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7f9b50144ec0,32768,32768,0,64,0x7f7c63c40ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2049259.0,64,0x7f8ae3208ec0,0,32768,32768,16384,16384,65536,49152,10485760,57717800.0,194169517.0,48303628.0,131072.0,23528,1411431718721828,1411431718738308 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa9ed1a8ec0,0,186931,0,0,65536,63800,56,1680,64,0x7f194bfd0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7f7f1b340ec0,0,0,0,0,114688,0,65536,32768,2097152.0,2097152.0,1048576.0,1048576.0,9451,2364,64,0x7fc9aed84ec0,344064,331040,222414,2782580,0,0,163840,114688,832.0,515140.0,0.0,524288.0,0,13671,64,0x7f5bbe60cec0,0,0,0,56,0,65536,65536,0,64,0x7f7d1ef30ec0,0,0,0,16384,16384,20237816,18744185,1149567,0.0,0.0,0.0,524288.0,3294,38997,64,0x7fbcef8dcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,64,0x7fb363b9cec0,0,0,0,0,0,0,0,0,0.0,0.0,0.0,32768.0,302,41285,64,0x7f4800eacec0,0,16384,16384,32768,49152,0,393216,163840,41248,41248,3132584.0,2442691.0,4684.0,396921.0,41248,0,64,0x7f2d43378ec0,65536,0,0,0,16384,16384,0,0,131072.0,0.0,0.0,0.0,64,0x7f9b50144ec0,32768,32768,0,64,0x7f7c63c40ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2130544.0,64,0x7f8ae3208ec0,0,32768,32768,16384,16384,65536,49152,10485760,58382576.0,200468876.0,51046669.0,131072.0,25616,1411431718758628,1411431718774148 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv index e82a6792c8..33700b287d 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.4381,1388.8553,1390.0209,5015.0967,5011.8203,5018.373,9224.3516,9223.6533,9225.0498,18051.711,18050.818,18052.604,20932.088,20871.99,20992.186,20267.361,20266.695,20268.027,170435.88,170431.92,170439.83,164881.86,164875.77,164887.95,41421.273,41420.738,41421.809,41478.977,41478.379,41479.574,166347.16,165855.5,166838.81 -1,1388.8232,1388.2603,1389.3862,5028.1265,5026.0376,5030.2153,9235.1104,9234.4307,9235.79,18096.645,18092.363,18100.926,20974.473,20907.904,21041.041,20294.145,20293.709,20294.58,170841,170837.2,170844.8,165117.02,165111.83,165122.2,41481.996,41481.355,41482.637,41541.391,41540.145,41542.637,166875.09,166870.98,166879.2 -2,1388.4731,1387.8798,1389.0665,5034.4199,5032.0317,5036.8081,9257.6221,9256.875,9258.3691,18100.244,18099.41,18101.078,21040.211,21039.766,21040.656,20343.441,20342.75,20344.133,171043.92,171037.59,171050.25,165460.86,165456.91,165464.81,41566.301,41565.512,41567.09,41626.738,41625.742,41627.734,166920.09,166325.59,167514.59 -3,1389.2181,1388.5493,1389.887,5031.2817,5029.7422,5032.8213,9239.5068,9238.8262,9240.1875,18021.037,18017.094,18024.98,21033.131,21032.49,21033.771,20310.314,20309.557,20311.072,171045.16,171040.42,171049.89,165223.34,165217.73,165228.95,41439.453,41285.234,41593.672,41581.762,41581.203,41582.32,167012.78,167010.56,167015 +0,1388.9574,1388.4075,1389.5073,5017.7017,5014.7422,5020.6611,9227.0312,9226.417,9227.6455,17712.477,17709.184,17715.77,20941.863,20881.639,21002.088,20273.27,20272.578,20273.961,170470.09,170466.05,170474.14,164925.09,164922.45,164927.73,41437.934,41437.34,41438.527,41493.578,41492.965,41494.191,166399.03,165908.11,166889.95 +1,1389.0171,1388.472,1389.5621,5030.5518,5028.4419,5032.6616,9238.5586,9237.915,9239.2021,18238.789,18236.633,18240.945,20986.074,20919.295,21052.854,20301.805,20301.15,20302.459,170923.31,170918.97,170927.66,165167.56,165164.2,165170.92,41502.539,41501.727,41503.352,41556.898,41555.934,41557.863,166937.08,166933.5,166940.66 +2,1388.1204,1387.5674,1388.6733,5036.2852,5034.2036,5038.3667,9261.4414,9260.8232,9262.0596,18215.566,18214.602,18216.531,21047.678,21047.145,21048.211,20349.168,20348.512,20349.824,171120.66,171116.75,171124.56,165491.92,165488.02,165495.83,41578.477,41577.621,41579.332,41634.645,41633.945,41635.344,166936.64,166343.23,167530.05 +3,1388.9321,1388.3347,1389.5295,5032.751,5031.0283,5034.4736,9237.6006,9236.9043,9238.2969,18325.562,18324.643,18326.482,21030.988,21030.703,21031.273,20304.449,20303.975,20304.924,171017.84,171011.3,171024.39,165163.38,165159.66,165167.09,41432.82,41279.816,41585.824,41569.441,41568.293,41570.59,166953.97,166950.47,166957.47 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv index e8e7bc9c0e..5c97c3ca98 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_SQC_TCP_CPC,./sample/vcopy -n 1048576 -b 256 -i 3,sq|sqc|tcp|cpc|roofline,Thu 07 Mar 2024 02:10:04 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_SQ_SQC_TCP_CPC,./tests/vcopy -n 1048576 -b 256 -i 3,sq|sqc|tcp|cpc|roofline,Thu 21 Mar 2024 04:14:50 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv index 8bf03b3b27..52a457fece 100644 --- a/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_SQC_TCP_CPC/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,277271,277271,1048576,256,0,0,8,0,16,64,0x0,0x7f5312804ec0,197946401394660,197946401420195,197946401440355,197946401458611 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,277271,277271,1048576,256,0,0,8,0,16,64,0x0,0x7f5312804ec0,197946401451037,197946401459235,197946401475075,197946401537901 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,277271,277271,1048576,256,0,0,8,0,16,64,0x0,0x7f5312804ec0,197946401485091,197946401540515,197946401557155,197946401557939 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4100762,4100762,1048576,256,0,0,8,0,16,64,0x0,0x7fd390510ec0,1411431718593075,1411431718618788,1411431718638948,1411431718650203 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4100762,4100762,1048576,256,0,0,8,0,16,64,0x0,0x7fd390510ec0,1411431718649792,1411431718721828,1411431718738308,1411431718739492 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4100762,4100762,1048576,256,0,0,8,0,16,64,0x0,0x7fd390510ec0,1411431718748829,1411431718758628,1411431718774148,1411431718775169 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv index e1f38f84f6..75c7709a29 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,111832,111832,1048576,256,0,0,8,8,16,64,0x0,0x7faca850ee80,47672,47672,16384,65536,13016,1662396,194086530612610,194093425213997,194093425237997,194086538366892 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,111832,111832,1048576,256,0,0,8,8,16,64,0x0,0x7faca850ee80,42063,42063,16384,65536,8271,1048608,194086538389365,194093425324077,194093425343117,194086538701616 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,111832,111832,1048576,256,0,0,8,8,16,64,0x0,0x7faca850ee80,42511,42511,16384,65536,8182,1048588,194086538733907,194093425365197,194093425384237,194086538913838 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1207547,1207547,1048576,256,0,0,8,8,16,64,0x0,0x7fdbac09cec0,49064,49064,16384,65536,14409,1848712,1410014904630102,1410021594538836,1410021594563316,1410014912282564 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1207547,1207547,1048576,256,0,0,8,8,16,64,0x0,0x7fdbac09cec0,42585,42585,16384,65536,8224,1048576,1410014912306910,1410021594645876,1410021594664916,1410014912618448 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1207547,1207547,1048576,256,0,0,8,8,16,64,0x0,0x7fdbac09cec0,43292,43292,16384,65536,8233,1048588,1410014912647873,1410021594684756,1410021594703956,1410014912833594 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv index 0ff257e463..883ec76106 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,112032,112032,1048576,256,0,0,8,8,16,64,0x0,0x7fb86e3d2e80,0,0,0,194087028102668,194093425213997,194093425237997,194087035834237 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,112032,112032,1048576,256,0,0,8,8,16,64,0x0,0x7fb86e3d2e80,0,0,0,194087035852191,194093425324077,194093425343117,194087036186023 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,112032,112032,1048576,256,0,0,8,8,16,64,0x0,0x7fb86e3d2e80,0,0,0,194087036214236,194093425365197,194093425384237,194087036395239 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1207731,1207731,1048576,256,0,0,8,8,16,64,0x0,0x7f7d33490ec0,0,0,0,1410015385249944,1410021594538836,1410021594563316,1410015392954194 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1207731,1207731,1048576,256,0,0,8,8,16,64,0x0,0x7f7d33490ec0,0,0,0,1410015392976336,1410021594645876,1410021594664916,1410015393256895 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1207731,1207731,1048576,256,0,0,8,8,16,64,0x0,0x7f7d33490ec0,0,0,0,1410015393285259,1410021594684756,1410021594703956,1410015393456722 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv index e3c06eeb3e..57969313de 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,112232,112232,1048576,256,0,0,8,8,16,64,0x0,0x7efdde722e80,65536,191952,24597432,194087514744535,194093425213997,194093425237997,194087522319548 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,112232,112232,1048576,256,0,0,8,8,16,64,0x0,0x7efdde722e80,65536,170250,21804832,194087522338704,194093425324077,194093425343117,194087522640035 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,112232,112232,1048576,256,0,0,8,8,16,64,0x0,0x7efdde722e80,65536,172682,22115960,194087522668108,194093425365197,194093425384237,194087522839282 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1207931,1207931,1048576,256,0,0,8,8,16,64,0x0,0x7fcb22ad4ec0,65536,205886,26324448,1410015864715139,1410021594538836,1410021594563316,1410015872304282 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1207931,1207931,1048576,256,0,0,8,8,16,64,0x0,0x7fcb22ad4ec0,65536,197636,25222528,1410015872323739,1410021594645876,1410021594664916,1410015872629696 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1207931,1207931,1048576,256,0,0,8,8,16,64,0x0,0x7fcb22ad4ec0,65536,156264,20064176,1410015872658310,1410021594684756,1410021594703956,1410015872837267 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv index a6bd0b5928..6c7ddc374a 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,112432,112432,1048576,256,0,0,8,8,16,64,0x0,0x7fdc35118e80,32768,657184,84113380,194088000794372,194093425213997,194093425237997,194088008716061 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,112432,112432,1048576,256,0,0,8,8,16,64,0x0,0x7fdc35118e80,32768,677062,86659932,194088008733764,194093425324077,194093425343117,194088009053039 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,112432,112432,1048576,256,0,0,8,8,16,64,0x0,0x7fdc35118e80,32768,674346,86322100,194088009081683,194093425365197,194093425384237,194088009274979 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1208117,1208117,1048576,256,0,0,8,8,16,64,0x0,0x7f0e78dd8ec0,32768,643986,82435244,1410016342977174,1410021594538836,1410021594563316,1410016350764020 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1208117,1208117,1048576,256,0,0,8,8,16,64,0x0,0x7f0e78dd8ec0,32768,652166,83466992,1410016350773238,1410021594645876,1410021594664916,1410016351115153 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1208117,1208117,1048576,256,0,0,8,8,16,64,0x0,0x7f0e78dd8ec0,32768,656772,84041780,1410016351143606,1410021594684756,1410021594703956,1410016351328365 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv index e45c9d67d6..d1c2450175 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,112617,112617,1048576,256,0,0,8,8,16,64,0x0,0x7f931de7ee80,48195,48195,17010,385568,16384,24987261,235382,0,100448300,194088497423749,194093425213997,194093425237997,194088506641663 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,112617,112617,1048576,256,0,0,8,8,16,64,0x0,0x7f931de7ee80,42266,42266,13728,338136,16384,24959166,232279,0,100332820,194088506673243,194093425324077,194093425343117,194088506961308 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,112617,112617,1048576,256,0,0,8,8,16,64,0x0,0x7f931de7ee80,41786,41786,13364,334296,16384,24285447,225010,0,97631512,194088507000733,194093425365197,194093425384237,194088507187757 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1208302,1208302,1048576,256,0,0,8,8,16,64,0x0,0x7f0231424ec0,48478,48478,17989,387832,16384,25140572,231181,0,101090820,1410016824114723,1410021594538836,1410021594563316,1410016831696963 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1208302,1208302,1048576,256,0,0,8,8,16,64,0x0,0x7f0231424ec0,42250,42250,12550,338008,16384,25316382,232237,0,101789896,1410016831731518,1410021594645876,1410021594664916,1410016832038307 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1208302,1208302,1048576,256,0,0,8,8,16,64,0x0,0x7f0231424ec0,41602,41602,12858,332824,16384,24984642,228427,0,100473264,1410016832079104,1410021594684756,1410021594703956,1410016832257971 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/log.txt b/tests/workloads/ipblocks_SQ_TA/MI100/log.txt new file mode 100644 index 0000000000..63dd08a9cf --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI100/log.txt @@ -0,0 +1,447 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_TA/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'ta'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155120' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155120_1207387' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155120_1207387/input0_results_240321_155120' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155120_1207387/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155120_1207387/input0_results_240321_155120 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155121' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155121_1207571' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155121_1207571/input0_results_240321_155121' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155121_1207571/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155121_1207571/input0_results_240321_155121 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155121' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155121_1207771' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155121_1207771/input0_results_240321_155121' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155121_1207771/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155121_1207771/input0_results_240321_155121 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155122' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155122_1207957' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155122_1207957/input0_results_240321_155122' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155122_1207957/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155122_1207957/input0_results_240321_155122 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155122' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155122_1208142' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155122_1208142/input0_results_240321_155122' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155122_1208142/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155122_1208142/input0_results_240321_155122 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155123' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155123_1208327' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155123_1208327/input0_results_240321_155123' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155123_1208327/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, GRBM_COUNT, GRBM_GUI_ACTIVE, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155123_1208327/input0_results_240321_155123 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155123' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155123_1208514' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155123_1208514/input0_results_240321_155123' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155123_1208514/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155123_1208514/input0_results_240321_155123 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155124' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155124_1208715' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155124_1208715/input0_results_240321_155124' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155124_1208715/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155124_1208715/input0_results_240321_155124 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155124' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155124_1208899' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155124_1208899/input0_results_240321_155124' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155124_1208899/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155124_1208899/input0_results_240321_155124 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155125' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155125_1209085' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155125_1209085/input0_results_240321_155125' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155125_1209085/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155125_1209085/input0_results_240321_155125 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155125' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155125_1209268' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155125_1209268/input0_results_240321_155125' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155125_1209268/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155125_1209268/input0_results_240321_155125 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155126' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155126_1209454' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155126_1209454/input0_results_240321_155126' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155126_1209454/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155126_1209454/input0_results_240321_155126 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155126' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155126_1209641' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155126_1209641/input0_results_240321_155126' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155126_1209641/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155126_1209641/input0_results_240321_155126 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155127' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155127_1209829' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155127_1209829/input0_results_240321_155127' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155127_1209829/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 7 metrics + |-> [rocprof] SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155127_1209829/input0_results_240321_155127 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155127' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155127_1210017' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155127_1210017/input0_results_240321_155127' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155127_1210017/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155127_1210017/input0_results_240321_155127 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv b/tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv index 2296381e3d..7f1324ae4c 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_2,obj_2,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_3,obj_3,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_4,obj_4,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_5,obj_5,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_6,obj_6,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_8,obj_8,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f57df22ce80,0,131072,144,48,0,0,0,192,32768.0,16384.0,64,0x7f578ac6ce80,384208,233514,3414819,16384,25361297,16384,16384,32768,48025,48025,2054029.0,0.0,64,0x7f152ac70e80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7fb03f932e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fecd7b64e80,0,0,0,1048576,0,0,0,0,0.0,580352.0,64,0x7f53aa404e80,49152,11534336,65536,0,0,0,16384,0,931521.0,32768.0,64,0x7ff4bf300e80,65536,64048,48,1440,32768,32768,0,64,0x7f0c6b402e80,0,65536,64480,48,1358,185497,0,0,16384.0,0.0,64,0x7fd299446e80,16384,393216,22671296,1650806,360448,163840,0,0,0.0,0.0,194093425213997,194093425237997 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f57df22ce80,0,131072,0,48,0,0,0,48,32768.0,16384.0,64,0x7f578ac6ce80,341200,231657,3384515,16384,25334508,16384,16384,32768,42649,42649,2136241.0,0.0,64,0x7f152ac70e80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7fb03f932e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fecd7b64e80,0,0,0,1048576,0,0,0,0,0.0,615386.0,64,0x7f53aa404e80,49152,11534336,65536,0,0,0,16384,0,1137406.0,32768.0,64,0x7ff4bf300e80,65536,64048,48,1440,32768,32768,0,64,0x7f0c6b402e80,0,65536,65536,0,0,190996,0,0,16384.0,0.0,64,0x7fd299446e80,16384,393216,23016849,1129850,360448,163840,0,0,0.0,0.0,194093425324077,194093425343117 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f57df22ce80,0,131072,0,48,0,0,0,48,32768.0,16384.0,64,0x7f578ac6ce80,349200,233179,3382702,16384,24402589,16384,16384,32768,43649,43649,2132975.0,0.0,64,0x7f152ac70e80,49152,0,65536,32768,0,0,0,16384,0.0,0.0,64,0x7fb03f932e80,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fecd7b64e80,0,0,0,1048576,0,0,0,0,0.0,626002.0,64,0x7f53aa404e80,49152,11534336,65536,0,0,0,16384,0,960706.0,32768.0,64,0x7ff4bf300e80,65536,64048,48,1440,32768,32768,0,64,0x7f0c6b402e80,0,65536,65536,0,0,190685,0,0,16384.0,0.0,64,0x7fd299446e80,16384,393216,22578421,1415558,360448,163840,0,0,0.0,0.0,194093425365197,194093425384237 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_1,obj_1,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_2,obj_2,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_4,obj_4,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_5,obj_5,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_6,obj_6,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_7,obj_7,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_8,obj_8,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f025f5b4ec0,65536,64048,48,1440,32768,32768,0,64,0x7fcbcd2c8ec0,49152,11534336,65536,0,0,0,16384,0,1029496.0,32768.0,64,0x7fa811618ec0,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fb8abfd0ec0,395552,244365,3555970,16384,26487640,16384,16384,32768,49443,49443,2135930.0,0.0,64,0x7faaa3b78ec0,0,65536,64391,48,1514,127720,0,0,16384.0,0.0,64,0x7fb8cf1e8ec0,0,131072,144,48,0,0,0,192,32768.0,16384.0,64,0x7f296b9d8ec0,0,0,0,1048576,0,0,0,0,0.0,655375.0,64,0x7f327e610ec0,16384,393216,22530548,1805743,360448,163840,0,0,0.0,0.0,64,0x7f0ae8fbcec0,49152,0,65536,32768,0,0,0,16384,0.0,0.0,1410021594538836,1410021594563316 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f025f5b4ec0,65536,64048,48,1440,32768,32768,0,64,0x7fcbcd2c8ec0,49152,11534336,65536,0,0,0,16384,0,1033886.0,32768.0,64,0x7fa811618ec0,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fb8abfd0ec0,346728,234729,3422670,16384,24689287,16384,16384,32768,43340,43340,2125177.0,0.0,64,0x7faaa3b78ec0,0,65536,65536,0,0,147268,0,0,16384.0,0.0,64,0x7fb8cf1e8ec0,0,131072,0,48,0,0,0,48,32768.0,16384.0,64,0x7f296b9d8ec0,0,0,0,1048576,0,0,0,0,0.0,595032.0,64,0x7f327e610ec0,16384,393216,23042576,1153610,360448,163840,0,0,0.0,0.0,64,0x7f0ae8fbcec0,49152,0,65536,32768,0,0,0,16384,0.0,0.0,1410021594645876,1410021594664916 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f025f5b4ec0,65536,64048,48,1440,32768,32768,0,64,0x7fcbcd2c8ec0,49152,11534336,65536,0,0,0,16384,0,1040846.0,32768.0,64,0x7fa811618ec0,180224,114688,0,32768,32768,16384,16384,65536,0.0,0.0,64,0x7fb8abfd0ec0,342104,229786,3369384,16384,24922927,16384,16384,32768,42762,42762,2145398.0,0.0,64,0x7faaa3b78ec0,0,65536,65536,0,0,190430,0,0,16384.0,0.0,64,0x7fb8cf1e8ec0,0,131072,0,48,0,0,0,48,32768.0,16384.0,64,0x7f296b9d8ec0,0,0,0,1048576,0,0,0,0,0.0,582901.0,64,0x7f327e610ec0,16384,393216,22093481,1254709,360448,163840,0,0,0.0,0.0,64,0x7f0ae8fbcec0,49152,0,65536,32768,0,0,0,16384,0.0,0.0,1410021594684756,1410021594703956 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/sysinfo.csv b/tests/workloads/ipblocks_SQ_TA/MI100/sysinfo.csv index 1f0a73a519..798fb70553 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_TA,./tests/vcopy -n 1048576 -b 256 -i 3,sq|ta,Thu 07 Mar 2024 01:05:51 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_SQ_TA,./tests/vcopy -n 1048576 -b 256 -i 3,sq|ta,Thu 21 Mar 2024 03:51:20 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv b/tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv index b25ca7356b..6c87ea6118 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,114517,114517,1048576,256,0,0,8,8,16,64,0x0,0x7fb248498e80,194093425188607,194093425213997,194093425237997,194093425249272 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,114517,114517,1048576,256,0,0,8,8,16,64,0x0,0x7fb248498e80,194093425250645,194093425324077,194093425343117,194093425344372 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,114517,114517,1048576,256,0,0,8,8,16,64,0x0,0x7fb248498e80,194093425355103,194093425365197,194093425384237,194093425385330 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1210177,1210177,1048576,256,0,0,8,8,16,64,0x0,0x7fc109740ec0,1410021594512016,1410021594538836,1410021594563316,1410021594571989 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1210177,1210177,1048576,256,0,0,8,8,16,64,0x0,0x7fc109740ec0,1410021594575446,1410021594645876,1410021594664916,1410021594666297 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1210177,1210177,1048576,256,0,0,8,8,16,64,0x0,0x7fc109740ec0,1410021594676957,1410021594684756,1410021594703956,1410021594704970 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv index f089fe1f1f..986679920b 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,260873,260873,1048576,256,0,0,8,0,16,64,0x0,0x7fca39d14ec0,27599,27599,16384,65536,13477,1515696,197627776181140,197636385194490,197636385214970,197627792265678 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,260873,260873,1048576,256,0,0,8,0,16,64,0x0,0x7fca39d14ec0,41312,41312,16384,65536,9545,1048732,197627792287700,197636385234650,197636385250330,197627792597797 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,260873,260873,1048576,256,0,0,8,0,16,64,0x0,0x7fca39d14ec0,41112,41112,16384,65536,9748,1048736,197627792627844,197636385313530,197636385329850,197627792788167 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4084419,4084419,1048576,256,0,0,8,0,16,64,0x0,0x7f546b978ec0,27898,27898,16384,65536,13881,1553540,1411113037595970,1411121747578549,1411121747599029,1411113053529633 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4084419,4084419,1048576,256,0,0,8,0,16,64,0x0,0x7f546b978ec0,42255,42255,16384,65536,9431,1048648,1411113053550553,1411121747618549,1411121747634229,1411113053851702 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4084419,4084419,1048576,256,0,0,8,0,16,64,0x0,0x7f546b978ec0,41112,41112,16384,65536,9030,1048652,1411113053881379,1411121747692949,1411121747709429,1411113054037985 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv index bb25873c2e..23836ab602 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,261074,261074,1048576,256,0,0,8,0,16,64,0x0,0x7ff069a4cec0,0,0,0,197628254734295,197636385194490,197636385214970,197628271117038 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,261074,261074,1048576,256,0,0,8,0,16,64,0x0,0x7ff069a4cec0,0,0,0,197628271143789,197636385234650,197636385250330,197628271426203 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,261074,261074,1048576,256,0,0,8,0,16,64,0x0,0x7ff069a4cec0,0,0,0,197628271452042,197636385313530,197636385329850,197628271607847 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4084611,4084611,1048576,256,0,0,8,0,16,64,0x0,0x7fab937b4ec0,0,0,0,1411113523349708,1411121747578549,1411121747599029,1411113539823763 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4084611,4084611,1048576,256,0,0,8,0,16,64,0x0,0x7fab937b4ec0,0,0,0,1411113539843981,1411121747618549,1411121747634229,1411113540083915 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4084611,4084611,1048576,256,0,0,8,0,16,64,0x0,0x7fab937b4ec0,0,0,0,1411113540110776,1411121747692949,1411121747709429,1411113540282731 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv index 95b2cc313a..4a829d784a 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,261275,261275,1048576,256,0,0,8,0,16,64,0x0,0x7fa709da8ec0,65536,193830,21666056,197628730626066,197636385194490,197636385214970,197628746888422 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,261275,261275,1048576,256,0,0,8,0,16,64,0x0,0x7fa709da8ec0,65536,260130,29024072,197628746909942,197636385234650,197636385250330,197628747192296 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,261275,261275,1048576,256,0,0,8,0,16,64,0x0,0x7fa709da8ec0,65536,285904,32101264,197628747218776,197636385313530,197636385329850,197628747375483 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4084807,4084807,1048576,256,0,0,8,0,16,64,0x0,0x7fcdbf778ec0,65536,196012,21926688,1411114004218708,1411121747578549,1411121747599029,1411114019945400 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4084807,4084807,1048576,256,0,0,8,0,16,64,0x0,0x7fcdbf778ec0,65536,282656,31734496,1411114019962312,1411121747618549,1411121747634229,1411114020266808 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4084807,4084807,1048576,256,0,0,8,0,16,64,0x0,0x7fcdbf778ec0,65536,291488,32721736,1411114020292697,1411121747692949,1411121747709429,1411114020449754 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv index e4f05f614b..f446bcb80b 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,261476,261476,1048576,256,0,0,8,0,16,64,0x0,0x7fada3084ec0,32768,286992,32144468,197629205844033,197636385194490,197636385214970,197629221870281 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,261476,261476,1048576,256,0,0,8,0,16,64,0x0,0x7fada3084ec0,32768,586845,65733004,197629221888145,197636385234650,197636385250330,197629222196458 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,261476,261476,1048576,256,0,0,8,0,16,64,0x0,0x7fada3084ec0,32768,577854,64705004,197629222222728,197636385313530,197636385329850,197629222383442 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4084998,4084998,1048576,256,0,0,8,0,16,64,0x0,0x7f4507058ec0,32768,297670,33321748,1411114481492309,1411121747578549,1411121747599029,1411114497565135 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4084998,4084998,1048576,256,0,0,8,0,16,64,0x0,0x7f4507058ec0,32768,595370,66696916,1411114497586986,1411121747618549,1411121747634229,1411114497803285 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4084998,4084998,1048576,256,0,0,8,0,16,64,0x0,0x7f4507058ec0,32768,575100,64405244,1411114497830146,1411121747692949,1411121747709429,1411114497960522 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv index 7a3eb7e45b..9b217ef8aa 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,261677,261677,1048576,256,0,0,8,0,16,64,0x0,0x7f8418fd8ec0,26820,26820,10945,214568,16384,10185915,122068,0,41244244,197629680567754,197636385194490,197636385214970,197629696489424 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,261677,261677,1048576,256,0,0,8,0,16,64,0x0,0x7f8418fd8ec0,40790,40790,13103,326328,16384,18741062,218779,0,75437420,197629696518710,197636385234650,197636385250330,197629696813588 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,261677,261677,1048576,256,0,0,8,0,16,64,0x0,0x7f8418fd8ec0,40129,40129,13421,321040,16384,18585030,215100,0,74824632,197629696849115,197636385313530,197636385329850,197629697015940 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4085204,4085204,1048576,256,0,0,8,0,16,64,0x0,0x7ffbcf700ec0,27873,27873,11105,222992,16384,10933805,129921,0,44244972,1411114961813393,1411121747578549,1411121747599029,1411114977906337 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4085204,4085204,1048576,256,0,0,8,0,16,64,0x0,0x7ffbcf700ec0,42135,42135,13603,337088,16384,19892921,227819,0,80051464,1411114977935131,1411121747618549,1411121747634229,1411114978231521 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4085204,4085204,1048576,256,0,0,8,0,16,64,0x0,0x7ffbcf700ec0,42319,42319,14543,338560,16384,19553039,225200,0,78701676,1411114978266568,1411121747692949,1411121747709429,1411114978472788 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/log.txt b/tests/workloads/ipblocks_SQ_TA/MI200/log.txt new file mode 100644 index 0000000000..c91bc928c8 --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/log.txt @@ -0,0 +1,565 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ_TA/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['sq', 'ta'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_160940' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160940_4084259' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160940_4084259/input0_results_240321_160940' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160940_4084259/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160940_4084259/input0_results_240321_160940 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_160941' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160941_4084451' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160941_4084451/input0_results_240321_160941' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160941_4084451/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160941_4084451/input0_results_240321_160941 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_160941' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160941_4084647' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160941_4084647/input0_results_240321_160941' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160941_4084647/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160941_4084647/input0_results_240321_160941 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_160942' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160942_4084838' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160942_4084838/input0_results_240321_160942' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160942_4084838/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160942_4084838/input0_results_240321_160942 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_160942' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160942_4085044' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160942_4085044/input0_results_240321_160942' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160942_4085044/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160942_4085044/input0_results_240321_160942 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_160943' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160943_4085245' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160943_4085245/input0_results_240321_160943' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160943_4085245/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160943_4085245/input0_results_240321_160943 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_160943' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160943_4085448' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160943_4085448/input0_results_240321_160943' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160943_4085448/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160943_4085448/input0_results_240321_160943 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_160944' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160944_4085642' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160944_4085642/input0_results_240321_160944' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160944_4085642/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160944_4085642/input0_results_240321_160944 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_160944' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160944_4085828' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160944_4085828/input0_results_240321_160944' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160944_4085828/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160944_4085828/input0_results_240321_160944 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_160945' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160945_4086029' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160945_4086029/input0_results_240321_160945' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160945_4086029/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160945_4086029/input0_results_240321_160945 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_160945' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160945_4086222' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160945_4086222/input0_results_240321_160945' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160945_4086222/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160945_4086222/input0_results_240321_160945 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_160946' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160946_4086423' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160946_4086423/input0_results_240321_160946' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160946_4086423/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160946_4086423/input0_results_240321_160946 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_160946' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160946_4086625' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160946_4086625/input0_results_240321_160946' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160946_4086625/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160946_4086625/input0_results_240321_160946 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_160947' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160947_4086827' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160947_4086827/input0_results_240321_160947' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160947_4086827/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160947_4086827/input0_results_240321_160947 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_160947' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160947_4087018' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160947_4087018/input0_results_240321_160947' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160947_4087018/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160947_4087018/input0_results_240321_160947 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_160948' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160948_4087219' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160948_4087219/input0_results_240321_160948' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160948_4087219/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 10 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160948_4087219/input0_results_240321_160948 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_160948' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160948_4087419' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160948_4087419/input0_results_240321_160948' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160948_4087419/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160948_4087419/input0_results_240321_160948 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_160949' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160949_4087624' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160949_4087624/input0_results_240321_160949' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160949_4087624/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160949_4087624/input0_results_240321_160949 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_SQ_TA/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_160949' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ_TA/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160949_4087822' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160949_4087822/input0_results_240321_160949' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160949_4087822/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160949_4087822/input0_results_240321_160949 + |-> [rocprof] File 'tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_SQ_TA/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_SQ_TA/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_SQ_TA/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv b/tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv index 53a9f7675e..4fedfacb84 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_1,obj_1,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_2,obj_2,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_3,obj_3,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_4,obj_4,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_5,obj_5,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_8,obj_8,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_9,obj_9,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_10,obj_10,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_11,obj_11,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_12,obj_12,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7151634ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f61b0404ec0,0,0,0,224,0,65536,64209,56,64,0x7f84a35c4ec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,64,0x7fa133074ec0,344064,226464,134756,1702621,0,0,163840,114688,259449.0,32768.0,64,0x7ff1a5bd8ec0,0,16384,16384,32768,49152,0,393216,163840,27784,27784,1038475.0,0.0,64,0x7fb51c518ec0,0,0,0,16384,16384,10612853,9512844,755945,0.0,0.0,64,0x7fdf34ae4ec0,32768,32768,0,64,0x7f4c20ba8ec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,225616.0,64,0x7f0416f28ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7fdd9bf3cec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7f0a3d084ec0,0,0,0,0,0,0,168,56,64,0x7fb675a04ec0,1308,119573,0,0,65536,63800,56,1680,64,0x7f142814cec0,131072,0,0,0,0,0,0,0,197636385194490,197636385214970 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7151634ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f61b0404ec0,0,0,0,56,0,65536,65536,0,64,0x7f84a35c4ec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,64,0x7fa133074ec0,344064,299936,206150,2558989,0,0,163840,114688,446443.0,32768.0,64,0x7ff1a5bd8ec0,0,16384,16384,32768,49152,0,393216,163840,38484,38484,1736112.0,0.0,64,0x7fb51c518ec0,0,0,0,16384,16384,17686698,17104122,238512,0.0,0.0,64,0x7fdf34ae4ec0,32768,32768,0,64,0x7f4c20ba8ec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,470988.0,64,0x7f0416f28ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7fdd9bf3cec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7f0a3d084ec0,0,0,0,0,0,0,0,56,64,0x7fb675a04ec0,0,192083,0,0,65536,63800,56,1680,64,0x7f142814cec0,131072,0,0,0,0,0,0,0,197636385234650,197636385250330 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7151634ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f61b0404ec0,0,0,0,56,0,65536,65536,0,64,0x7f84a35c4ec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,64,0x7fa133074ec0,344064,337144,231351,2886370,0,0,163840,114688,625844.0,32768.0,64,0x7ff1a5bd8ec0,0,16384,16384,32768,49152,0,393216,163840,40532,40532,1638787.0,0.0,64,0x7fb51c518ec0,0,0,0,16384,16384,19861626,18505828,1011734,0.0,0.0,64,0x7fdf34ae4ec0,32768,32768,0,64,0x7f4c20ba8ec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,492901.0,64,0x7f0416f28ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7fdd9bf3cec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7f0a3d084ec0,0,0,0,0,0,0,0,56,64,0x7fb675a04ec0,0,190677,0,0,65536,63800,56,1680,64,0x7f142814cec0,131072,0,0,0,0,0,0,0,197636385313530,197636385329850 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_1,obj_1,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,wave_size_2,obj_2,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_3,obj_3,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_4,obj_4,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,wave_size_5,obj_5,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_8,obj_8,SQ_ACTIVE_INST_ANY,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_9,obj_9,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_10,obj_10,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_11,obj_11,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_12,obj_12,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f079c7d4ec0,32768,32768,0,64,0x7f41578a8ec0,131072,0,0,0,0,0,0,0,64,0x7f8334b14ec0,0,0,0,224,0,65536,64209,56,64,0x7f2c267d0ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7f9292d64ec0,0,0,0,0,0,0,168,56,64,0x7feb8406cec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,215202.0,64,0x7f3b82a2cec0,1270,117219,0,0,65536,63800,56,1680,64,0x7fef1b3d8ec0,0,0,0,16384,16384,10890018,9697521,848433,0.0,0.0,64,0x7fc4fdb04ec0,344064,218456,126748,1604762,0,0,163840,114688,261933.0,32768.0,64,0x7f7570968ec0,0,16384,16384,32768,49152,0,393216,163840,27681,27681,1043868.0,0.0,64,0x7f2ef1860ec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7ffbc4cc4ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f9e0286cec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,1411121747578549,1411121747599029 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f079c7d4ec0,32768,32768,0,64,0x7f41578a8ec0,131072,0,0,0,0,0,0,0,64,0x7f8334b14ec0,0,0,0,56,0,65536,65536,0,64,0x7f2c267d0ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7f9292d64ec0,0,0,0,0,0,0,0,56,64,0x7feb8406cec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,503117.0,64,0x7f3b82a2cec0,0,182882,0,0,65536,63800,56,1680,64,0x7fef1b3d8ec0,0,0,0,16384,16384,17559288,16965320,249904,0.0,0.0,64,0x7fc4fdb04ec0,344064,297608,206066,2552676,0,0,163840,114688,507252.0,32768.0,64,0x7f7570968ec0,0,16384,16384,32768,49152,0,393216,163840,37652,37652,1704465.0,0.0,64,0x7f2ef1860ec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7ffbc4cc4ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f9e0286cec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,1411121747618549,1411121747634229 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f079c7d4ec0,32768,32768,0,64,0x7f41578a8ec0,131072,0,0,0,0,0,0,0,64,0x7f8334b14ec0,0,0,0,56,0,65536,65536,0,64,0x7f2c267d0ec0,0,0,0,0,114688,0,65536,32768,0.0,0.0,64,0x7f9292d64ec0,0,0,0,0,0,0,0,56,64,0x7feb8406cec0,0,32768,32768,16384,16384,65536,49152,10485760,0.0,533694.0,64,0x7f3b82a2cec0,0,181788,0,0,65536,63800,56,1680,64,0x7fef1b3d8ec0,0,0,0,16384,16384,19578362,18272797,961501,0.0,0.0,64,0x7fc4fdb04ec0,344064,326312,218177,2742252,0,0,163840,114688,541899.0,32768.0,64,0x7f7570968ec0,0,16384,16384,32768,49152,0,393216,163840,41745,41745,1628141.0,0.0,64,0x7f2ef1860ec0,0,0,0,0,0,0,0,0,0.0,0.0,64,0x7ffbc4cc4ec0,0,0,1048576,0,0,0,0,0,16384.0,0.0,64,0x7f9e0286cec0,65536,0,0,0,16384,16384,0,0,32768.0,16384.0,1411121747692949,1411121747709429 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/roofline.csv b/tests/workloads/ipblocks_SQ_TA/MI200/roofline.csv index e1bb33e76c..a22c80db22 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/roofline.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.9526,1388.4111,1389.4941,5015.6484,5012.5898,5018.707,9223.4463,9222.7646,9224.1279,18051.945,18050.785,18053.105,20935.199,20875.307,20995.092,20264.828,20264.057,20265.6,170420.14,170416.5,170423.78,164861.64,164856.98,164866.3,41416.578,41416.203,41416.953,41476.453,41475.875,41477.031,166325.31,165837.67,166812.95 -1,1389.5095,1388.9309,1390.0881,5026.0811,5023.9771,5028.1851,9233.0938,9232.4082,9233.7793,18087.664,18083.631,18091.697,20970.012,20903.859,21036.164,20289.217,20288.719,20289.715,170813.81,170809.28,170818.34,165056.77,165053.3,165060.23,41467.969,41467.148,41468.789,41530.449,41529.344,41531.555,166829.2,166826.05,166832.36 -2,1388.5624,1388.0015,1389.1233,5035.5742,5033.3438,5037.8047,9259.7334,9258.9971,9260.4697,18101.963,18101.021,18102.904,21044.383,21044.031,21044.734,20349.049,20348.586,20349.512,171079.44,171075.62,171083.25,165481.09,165477.31,165484.88,41577.289,41576.395,41578.184,41631.129,41630.27,41631.988,166923,166338.03,167507.97 -3,1389.2155,1388.5825,1389.8484,5032.1416,5030.8301,5033.4531,9240.2666,9239.7314,9240.8018,18025.797,18022.486,18029.107,21033.242,21032.709,21033.775,20313.852,20313.191,20314.512,171032.44,171029.55,171035.33,165228.91,165224.12,165233.69,41438.621,41286.715,41590.527,41581.562,41580.84,41582.285,167020.28,167018.2,167022.36 +0,1388.8236,1388.228,1389.4192,5015.7485,5012.6987,5018.7983,9227.8623,9227.2158,9228.5088,17722.225,17718.977,17725.473,20950.221,20889.938,21010.504,20277.814,20277.301,20278.328,170540.56,170536.69,170544.44,164952.59,164947.89,164957.3,41439.754,41439.266,41440.242,41496.777,41496.266,41497.289,166424.38,165934.34,166914.41 +1,1389.355,1388.7817,1389.9282,5028.1899,5026.1538,5030.2261,9235.2373,9234.3057,9236.1689,18235.859,18233.621,18238.098,20983.66,20917.043,21050.277,20298.939,20298.381,20299.498,170907.36,170901.98,170912.73,165142.94,165139.75,165146.12,41492.828,41491.984,41493.672,41547.934,41547.035,41548.832,166891.83,166888.17,166895.48 +2,1388.6282,1388.1112,1389.1451,5035.7485,5033.6655,5037.8315,9260.1416,9259.3652,9260.918,18216.57,18215.541,18217.6,21053.145,21052.498,21053.791,20355.158,20354.631,20355.686,171175.77,171172.36,171179.17,165540.06,165536.59,165543.53,41593.594,41592.891,41594.297,41654.746,41653.758,41655.734,166994.94,166404.39,167585.48 +3,1388.6238,1388.0551,1389.1925,5033.6577,5032.2451,5035.0703,9237.0059,9236.1045,9237.9072,18325.463,18324.432,18326.494,21030.277,21029.939,21030.615,20306.119,20305.402,20306.836,171000.62,170995.62,171005.62,165132.41,165127.48,165137.33,41421.191,41268.234,41574.148,41561.289,41560.379,41562.199,166929.28,166924.44,166934.12 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/sysinfo.csv b/tests/workloads/ipblocks_SQ_TA/MI200/sysinfo.csv index 21fd52dabf..b48885be2b 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_SQ_TA,./sample/vcopy -n 1048576 -b 256 -i 3,sq|ta|roofline,Thu 07 Mar 2024 02:04:54 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_SQ_TA,./tests/vcopy -n 1048576 -b 256 -i 3,sq|ta|roofline,Thu 21 Mar 2024 04:09:40 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv b/tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv index 8e87960e7e..d88b814728 100644 --- a/tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_SQ_TA/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,264493,264493,1048576,256,0,0,8,0,16,64,0x0,0x7f93825d8ec0,197636385166327,197636385194490,197636385214970,197636385228815 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,264493,264493,1048576,256,0,0,8,0,16,64,0x0,0x7f93825d8ec0,197636385226540,197636385234650,197636385250330,197636385312433 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,264493,264493,1048576,256,0,0,8,0,16,64,0x0,0x7f93825d8ec0,197636385260815,197636385313530,197636385329850,197636385331229 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4087982,4087982,1048576,256,0,0,8,0,16,64,0x0,0x7f0f888dcec0,1411121747552921,1411121747578549,1411121747599029,1411121747612804 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4087982,4087982,1048576,256,0,0,8,0,16,64,0x0,0x7f0f888dcec0,1411121747610049,1411121747618549,1411121747634229,1411121747690271 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4087982,4087982,1048576,256,0,0,8,0,16,64,0x0,0x7f0f888dcec0,1411121747644674,1411121747692949,1411121747709429,1411121747710429 diff --git a/tests/workloads/ipblocks_TA/MI100/log.txt b/tests/workloads/ipblocks_TA/MI100/log.txt new file mode 100644 index 0000000000..3329c0b5b0 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI100/log.txt @@ -0,0 +1,273 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_TA/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['ta'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155449' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155449_1277530' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155449_1277530/input0_results_240321_155449' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155449_1277530/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, GRBM_COUNT, GRBM_GUI_ACTIVE, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155449_1277530/input0_results_240321_155449 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155450' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155450_1277713' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155450_1277713/input0_results_240321_155450' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155450_1277713/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155450_1277713/input0_results_240321_155450 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155450' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155450_1277897' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155450_1277897/input0_results_240321_155450' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155450_1277897/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155450_1277897/input0_results_240321_155450 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155451' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155451_1278082' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155451_1278082/input0_results_240321_155451' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155451_1278082/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155451_1278082/input0_results_240321_155451 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155451' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155451_1278266' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155451_1278266/input0_results_240321_155451' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155451_1278266/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155451_1278266/input0_results_240321_155451 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155452' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155452_1278450' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155452_1278450/input0_results_240321_155452' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155452_1278450/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155452_1278450/input0_results_240321_155452 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155452' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155452_1278637' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155452_1278637/input0_results_240321_155452' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155452_1278637/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155452_1278637/input0_results_240321_155452 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155453' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155453_1278823' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155453_1278823/input0_results_240321_155453' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155453_1278823/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155453_1278823/input0_results_240321_155453 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155453' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155453_1279006' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155453_1279006/input0_results_240321_155453' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155453_1279006/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155453_1279006/input0_results_240321_155453 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_TA/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TA/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_TA/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_TA/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_TA/MI100/pmc_perf.csv b/tests/workloads/ipblocks_TA/MI100/pmc_perf.csv index 6ed25350c3..67649d4fd8 100644 --- a/tests/workloads/ipblocks_TA/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_TA/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_1,obj_1,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_2,obj_2,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_3,obj_3,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_4,obj_4,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_5,obj_5,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_6,obj_6,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea74eb4e80,0.0,0.0,64,0x7ff137308e80,841565.0,32768.0,64,0x7f786c57ce80,0.0,0.0,64,0x7f4bd9d10e80,16384.0,0.0,64,0x7fb094e62e80,32768.0,16384.0,64,0x7f54f69c8e80,0.0,0.0,64,0x7fbfa0282e80,0.0,593523.0,64,0x7f90dee3ae80,381672,234420,3428747,16384,25273222,47708,47708,2052968.0,0.0,194308620288632,194308620312472 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea74eb4e80,0.0,0.0,64,0x7ff137308e80,917516.0,32768.0,64,0x7f786c57ce80,0.0,0.0,64,0x7f4bd9d10e80,16384.0,0.0,64,0x7fb094e62e80,32768.0,16384.0,64,0x7f54f69c8e80,0.0,0.0,64,0x7fbfa0282e80,0.0,619240.0,64,0x7f90dee3ae80,346216,231235,3364080,16384,24621168,43276,43276,2118458.0,0.0,194308620481592,194308620501272 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fea74eb4e80,0.0,0.0,64,0x7ff137308e80,868090.0,32768.0,64,0x7f786c57ce80,0.0,0.0,64,0x7f4bd9d10e80,16384.0,0.0,64,0x7fb094e62e80,32768.0,16384.0,64,0x7f54f69c8e80,0.0,0.0,64,0x7fbfa0282e80,0.0,558978.0,64,0x7f90dee3ae80,336168,225346,3302853,16384,24110920,42020,42020,2048198.0,0.0,194308620522712,194308620541432 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_1,obj_1,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_2,obj_2,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_3,obj_3,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_4,obj_4,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_5,obj_5,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_6,obj_6,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_7,obj_7,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f0b0e284ec0,0.0,0.0,64,0x7fc8546a0ec0,16384.0,0.0,64,0x7ff0b77d8ec0,32768.0,16384.0,64,0x7faae049cec0,982203.0,32768.0,64,0x7fcca7374ec0,0.0,0.0,64,0x7f43b0d78ec0,0.0,779093.0,64,0x7f4777824ec0,398728,246004,3545889,16384,25879305,49840,49840,2478664.0,0.0,64,0x7f9562b1cec0,0.0,0.0,1410227608326722,1410227608351842 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f0b0e284ec0,0.0,0.0,64,0x7fc8546a0ec0,16384.0,0.0,64,0x7ff0b77d8ec0,32768.0,16384.0,64,0x7faae049cec0,944590.0,32768.0,64,0x7fcca7374ec0,0.0,0.0,64,0x7f43b0d78ec0,0.0,737857.0,64,0x7f4777824ec0,349832,239358,3486682,16384,24439474,43728,43728,2312533.0,0.0,64,0x7f9562b1cec0,0.0,0.0,1410227608448482,1410227608467682 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f0b0e284ec0,0.0,0.0,64,0x7fc8546a0ec0,16384.0,0.0,64,0x7ff0b77d8ec0,32768.0,16384.0,64,0x7faae049cec0,944261.0,32768.0,64,0x7fcca7374ec0,0.0,0.0,64,0x7f43b0d78ec0,0.0,660403.0,64,0x7f4777824ec0,349000,236931,3440762,16384,24243210,43624,43624,2237249.0,0.0,64,0x7f9562b1cec0,0.0,0.0,1410227608488962,1410227608507842 diff --git a/tests/workloads/ipblocks_TA/MI100/sysinfo.csv b/tests/workloads/ipblocks_TA/MI100/sysinfo.csv index 60476624be..186d2cdfd1 100644 --- a/tests/workloads/ipblocks_TA/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_TA/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TA,./tests/vcopy -n 1048576 -b 256 -i 3,ta,Thu 07 Mar 2024 01:09:29 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_TA,./tests/vcopy -n 1048576 -b 256 -i 3,ta,Thu 21 Mar 2024 03:54:49 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_TA/MI100/timestamps.csv b/tests/workloads/ipblocks_TA/MI100/timestamps.csv index 6e31e34042..0a6fa9eef2 100644 --- a/tests/workloads/ipblocks_TA/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_TA/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,183593,183593,1048576,256,0,0,8,8,16,64,0x0,0x7f9431e1ce80,194308620262246,194308620288632,194308620312472,194308620326317 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,183593,183593,1048576,256,0,0,8,8,16,64,0x0,0x7f9431e1ce80,194308620325285,194308620481592,194308620501272,194308620502911 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,183593,183593,1048576,256,0,0,8,8,16,64,0x0,0x7f9431e1ce80,194308620514063,194308620522712,194308620541432,194308620542998 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1279166,1279166,1048576,256,0,0,8,8,16,64,0x0,0x7fc91fd18ec0,1410227608299133,1410227608326722,1410227608351842,1410227608365247 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1279166,1279166,1048576,256,0,0,8,8,16,64,0x0,0x7fc91fd18ec0,1410227608364405,1410227608448482,1410227608467682,1410227608469263 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1279166,1279166,1048576,256,0,0,8,8,16,64,0x0,0x7fc91fd18ec0,1410227608480134,1410227608488962,1410227608507842,1410227608509038 diff --git a/tests/workloads/ipblocks_TA/MI200/log.txt b/tests/workloads/ipblocks_TA/MI200/log.txt new file mode 100644 index 0000000000..81e8a09788 --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/log.txt @@ -0,0 +1,275 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_TA/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['ta'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_164135' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164135_4168185' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164135_4168185/input0_results_240321_164135' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164135_4168185/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, GRBM_COUNT, GRBM_GUI_ACTIVE, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164135_4168185/input0_results_240321_164135 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_164135' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164135_4168386' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164135_4168386/input0_results_240321_164135' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164135_4168386/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164135_4168386/input0_results_240321_164135 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_164136' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164136_4168578' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164136_4168578/input0_results_240321_164136' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164136_4168578/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164136_4168578/input0_results_240321_164136 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_164136' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164136_4168765' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164136_4168765/input0_results_240321_164136' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164136_4168765/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164136_4168765/input0_results_240321_164136 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_164137' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164137_4168966' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164137_4168966/input0_results_240321_164137' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164137_4168966/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164137_4168966/input0_results_240321_164137 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_164137' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164137_4169167' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164137_4169167/input0_results_240321_164137' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164137_4169167/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164137_4169167/input0_results_240321_164137 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_164138' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164138_4169355' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164138_4169355/input0_results_240321_164138' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164138_4169355/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164138_4169355/input0_results_240321_164138 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_164138' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164138_4169558' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164138_4169558/input0_results_240321_164138' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164138_4169558/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164138_4169558/input0_results_240321_164138 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TA/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_164139' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TA/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164139_4169744' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164139_4169744/input0_results_240321_164139' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164139_4169744/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164139_4169744/input0_results_240321_164139 + |-> [rocprof] File 'tests/workloads/ipblocks_TA/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_TA/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_TA/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TA/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_TA/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_TA/MI200/pmc_perf.csv b/tests/workloads/ipblocks_TA/MI200/pmc_perf.csv index dc931e5cf9..3bb9a6c3d0 100644 --- a/tests/workloads/ipblocks_TA/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_TA/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,wave_size_1,obj_1,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_2,obj_2,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_3,obj_3,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_4,obj_4,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_5,obj_5,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_6,obj_6,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7ff436634ec0,0.0,226324.0,64,0x7fe878d30ec0,0.0,0.0,64,0x7fa24dbacec0,32768.0,16384.0,64,0x7fbdc1da0ec0,0.0,0.0,64,0x7f724f8e4ec0,16384.0,0.0,64,0x7f475bd44ec0,0.0,0.0,64,0x7f559dbb0ec0,255549.0,32768.0,64,0x7fc234e30ec0,219008,126900,1608328,16384,10694012,27375,27375,1045887.0,0.0,199451887941398,199451887961558 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7ff436634ec0,0.0,469789.0,64,0x7fe878d30ec0,0.0,0.0,64,0x7fa24dbacec0,32768.0,16384.0,64,0x7fbdc1da0ec0,0.0,0.0,64,0x7f724f8e4ec0,16384.0,0.0,64,0x7f475bd44ec0,0.0,0.0,64,0x7f559dbb0ec0,521967.0,32768.0,64,0x7fc234e30ec0,296264,205468,2560009,16384,17525786,37032,37032,1715803.0,0.0,199451888050358,199451888066678 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7ff436634ec0,0.0,442860.0,64,0x7fe878d30ec0,0.0,0.0,64,0x7fa24dbacec0,32768.0,16384.0,64,0x7fbdc1da0ec0,0.0,0.0,64,0x7f724f8e4ec0,16384.0,0.0,64,0x7f475bd44ec0,0.0,0.0,64,0x7f559dbb0ec0,679685.0,32768.0,64,0x7fc234e30ec0,332312,220734,2755623,16384,19165388,41538,41538,1709964.0,0.0,199451888085398,199451888101078 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,wave_size_1,obj_1,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,wave_size_2,obj_2,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,wave_size_3,obj_3,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,wave_size_4,obj_4,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,wave_size_6,obj_6,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,wave_size_7,obj_7,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f58b393cec0,0.0,0.0,64,0x7fede9b5cec0,0.0,0.0,64,0x7fd72ca28ec0,32768.0,16384.0,64,0x7f9bde250ec0,353221.0,32768.0,64,0x7f303d2d8ec0,0.0,0.0,64,0x7f4571758ec0,222096,127844,1609024,16384,10772218,27761,27761,1068163.0,0.0,64,0x7f8a8efa0ec0,16384.0,0.0,64,0x7fd4af530ec0,0.0,209015.0,1413031563507692,1413031563528332 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f58b393cec0,0.0,0.0,64,0x7fede9b5cec0,0.0,0.0,64,0x7fd72ca28ec0,32768.0,16384.0,64,0x7f9bde250ec0,494173.0,32768.0,64,0x7f303d2d8ec0,0.0,0.0,64,0x7f4571758ec0,301064,205789,2552286,16384,17388092,37632,37632,1681461.0,0.0,64,0x7f8a8efa0ec0,16384.0,0.0,64,0x7fd4af530ec0,0.0,491803.0,1413031563548012,1413031563563532 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f58b393cec0,0.0,0.0,64,0x7fede9b5cec0,0.0,0.0,64,0x7fd72ca28ec0,32768.0,16384.0,64,0x7f9bde250ec0,737336.0,32768.0,64,0x7f303d2d8ec0,0.0,0.0,64,0x7f4571758ec0,332040,224954,2837533,16384,19787618,41504,41504,1797044.0,0.0,64,0x7f8a8efa0ec0,16384.0,0.0,64,0x7fd4af530ec0,0.0,552729.0,1413031563620812,1413031563637292 diff --git a/tests/workloads/ipblocks_TA/MI200/roofline.csv b/tests/workloads/ipblocks_TA/MI200/roofline.csv index fc0c9a2c2b..29eefc771c 100644 --- a/tests/workloads/ipblocks_TA/MI200/roofline.csv +++ b/tests/workloads/ipblocks_TA/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.2339,1388.6835,1389.7843,5014.834,5011.9429,5017.7251,9222.5566,9221.916,9223.1973,18050.242,18049.102,18051.383,20932.727,20872.451,20993.002,20261.408,20260.77,20262.047,170379.27,170375.23,170383.3,164850,164845.41,164854.59,41415.238,41414.723,41415.754,41472.098,41471.441,41472.754,166318.23,165827.38,166809.09 -1,1389.1729,1388.5649,1389.7808,5026.5298,5024.5435,5028.5161,9232.5303,9231.9238,9233.1367,18090.807,18087.168,18094.445,20972.15,20905.209,21039.092,20293.615,20292.992,20294.238,170840.88,170835.75,170846,165114.09,165110.69,165117.5,41484.23,41483.559,41484.902,41542.656,41541.648,41543.664,166878.97,166875.61,166882.33 -2,1388.4468,1387.9023,1388.9912,5034.792,5032.4917,5037.0923,9261.7051,9261.0332,9262.377,18103.418,18102.588,18104.248,21046.811,21046.393,21047.229,20351.721,20351.152,20352.289,171101.66,171098.2,171105.11,165474.23,165470.09,165478.38,41578.957,41578.066,41579.848,41628.684,41627.777,41629.59,166910.78,166309.39,167512.17 -3,1388.8716,1388.2726,1389.4706,5032.1841,5030.8164,5033.5518,9241.4023,9240.6934,9242.1113,18022.926,18019.047,18026.805,21037.811,21037.062,21038.559,20314.686,20314.041,20315.33,171043.86,171039.8,171047.92,165241.16,165235.89,165246.42,41440.902,41287.016,41594.789,41585.141,41584.398,41585.883,167028.31,167025.28,167031.34 +0,1389.213,1388.6594,1389.7666,5018.3784,5015.4756,5021.2812,9228.5967,9227.9531,9229.2402,17720.84,17717.863,17723.816,20948.199,20887.322,21009.076,20276.836,20276.379,20277.293,170506.72,170503.31,170510.12,164939.81,164934.95,164944.67,41436.363,41435.762,41436.965,41491.121,41490.562,41491.68,166399.72,165909,166890.44 +1,1388.9519,1388.3982,1389.5056,5027.377,5025.4849,5029.269,9232.9297,9232.3193,9233.54,18230.117,18227.855,18232.379,20973.002,20906.213,21039.791,20290.498,20289.859,20291.137,170801.55,170797.53,170805.56,165077.48,165073.53,165081.44,41478.766,41478.125,41479.406,41538.441,41537.875,41539.008,166871.84,166869.31,166874.38 +2,1388.9376,1388.3989,1389.4763,5036.4414,5033.9766,5038.9062,9262.2139,9261.5674,9262.8604,18220.748,18219.93,18221.566,21049.568,21049.127,21050.01,20351.842,20351.357,20352.326,171136.02,171132.72,171139.31,165535.94,165531.81,165540.06,41589.008,41588.379,41589.637,41647.617,41646.273,41648.961,166984.97,166389.02,167580.92 +3,1389.316,1388.6846,1389.9475,5033.3354,5031.7998,5034.8711,9240.9824,9240.3955,9241.5693,18329.582,18328.771,18330.393,21034.633,21034.322,21034.943,20312.102,20311.58,20312.623,171066.38,171061.19,171071.56,165199.56,165194.97,165204.16,41440.273,41286.602,41593.945,41574.691,41573.711,41575.672,166999.64,166994.5,167004.78 diff --git a/tests/workloads/ipblocks_TA/MI200/sysinfo.csv b/tests/workloads/ipblocks_TA/MI200/sysinfo.csv index bfa856c146..dc817c94ff 100644 --- a/tests/workloads/ipblocks_TA/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_TA/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TA,./sample/vcopy -n 1048576 -b 256 -i 3,ta|roofline,Thu 07 Mar 2024 02:35:15 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_TA,./tests/vcopy -n 1048576 -b 256 -i 3,ta|roofline,Thu 21 Mar 2024 04:41:34 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_TA/MI200/timestamps.csv b/tests/workloads/ipblocks_TA/MI200/timestamps.csv index bd392f6583..c3e06ff310 100644 --- a/tests/workloads/ipblocks_TA/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_TA/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,345465,345465,1048576,256,0,0,8,0,16,64,0x0,0x7f35bbee8ec0,199451887917687,199451887941398,199451887961558,199451887973773 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,345465,345465,1048576,256,0,0,8,0,16,64,0x0,0x7f35bbee8ec0,199451887972370,199451888050358,199451888066678,199451888068051 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,345465,345465,1048576,256,0,0,8,0,16,64,0x0,0x7f35bbee8ec0,199451888077589,199451888085398,199451888101078,199451888102156 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4169904,4169904,1048576,256,0,0,8,0,16,64,0x0,0x7fdab7d38ec0,1413031563482613,1413031563507692,1413031563528332,1413031563542887 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4169904,4169904,1048576,256,0,0,8,0,16,64,0x0,0x7fdab7d38ec0,1413031563539240,1413031563548012,1413031563563532,1413031563617267 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4169904,4169904,1048576,256,0,0,8,0,16,64,0x0,0x7fdab7d38ec0,1413031563573785,1413031563620812,1413031563637292,1413031563638137 diff --git a/tests/workloads/ipblocks_TCC/MI100/log.txt b/tests/workloads/ipblocks_TCC/MI100/log.txt new file mode 100644 index 0000000000..aea87d496d --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI100/log.txt @@ -0,0 +1,360 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_TCC/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['tcc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155039' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155039_1193398' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155039_1193398/input0_results_240321_155039' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155039_1193398/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, GRBM_COUNT, GRBM_GUI_ACTIVE, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155039_1193398/input0_results_240321_155039 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155040' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155040_1193597' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155040_1193597/input0_results_240321_155040' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155040_1193597/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155040_1193597/input0_results_240321_155040 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155041' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155041_1193798' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155041_1193798/input0_results_240321_155041' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155041_1193798/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155041_1193798/input0_results_240321_155041 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155042' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155042_1193998' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155042_1193998/input0_results_240321_155042' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155042_1193998/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155042_1193998/input0_results_240321_155042 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155042' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155042_1194199' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155042_1194199/input0_results_240321_155042' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155042_1194199/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155042_1194199/input0_results_240321_155042 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155043' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155043_1194400' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155043_1194400/input0_results_240321_155043' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155043_1194400/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155043_1194400/input0_results_240321_155043 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155043' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155043_1194601' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155043_1194601/input0_results_240321_155043' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155043_1194601/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155043_1194601/input0_results_240321_155043 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155043' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155043_1194802' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155043_1194802/input0_results_240321_155043' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155043_1194802/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155043_1194802/input0_results_240321_155043 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155044' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155044_1194986' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155044_1194986/input0_results_240321_155044' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155044_1194986/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155044_1194986/input0_results_240321_155044 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155044' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155044_1195170' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155044_1195170/input0_results_240321_155044' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155044_1195170/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155044_1195170/input0_results_240321_155044 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155045' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155045_1195370' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155045_1195370/input0_results_240321_155045' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155045_1195370/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155045_1195370/input0_results_240321_155045 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155045' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155045_1195570' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155045_1195570/input0_results_240321_155045' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155045_1195570/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155045_1195570/input0_results_240321_155045 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_TCC/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TCC/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_TCC/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_TCC/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv b/tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv index 1d10766679..558f147b17 100644 --- a/tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_TCC/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_8,obj_8,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_9,obj_9,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_10,obj_10,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd7b2a82e80,131072.0,131072.0,0.0,131072.0,64,0x7f7014f62e80,0.0,64,0x7f44b3226e80,131480.0,131072.0,0.0,131104.0,64,0x7ff185560e80,86770.0,44302.0,131112.0,0.0,64,0x7fae2a094e80,378088,232735,16384,47260,47260,1512320.0,967311.0,0.0,0.0,64,0x7fbac7f20e80,131340.0,0.0,528.0,131339.0,64,0x7f3d3e006e80,262667.0,0.0,188.0,262479.0,64,0x7fb39b6f0e80,0.0,0.0,44974.0,110378.0,64,0x7f58921a2e80,0.0,0.0,131706455.0,62205335.0,64,0x7ff374bcce80,48.0,232.0,0.0,262288.0,64,0x7f871fd60e80,70997.0,0.0,0.0,70997.0,194049837194911,194049837219071 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd7b2a82e80,86461.0,86461.0,0.0,86461.0,64,0x7f7014f62e80,0.0,64,0x7f44b3226e80,131336.0,131072.0,0.0,87201.0,64,0x7ff185560e80,86334.0,0.0,131112.0,0.0,64,0x7fae2a094e80,345920,230957,16384,43239,43239,1383648.0,824837.0,0.0,0.0,64,0x7fbac7f20e80,131342.0,0.0,538.0,131341.0,64,0x7f3d3e006e80,262574.0,0.0,47.0,262527.0,64,0x7fb39b6f0e80,0.0,0.0,73288.0,143478.0,64,0x7f58921a2e80,0.0,0.0,135537432.0,48703834.0,64,0x7ff374bcce80,48.0,273.0,0.0,262144.0,64,0x7f871fd60e80,57845.0,0.0,0.0,57845.0,194049837306111,194049837325471 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd7b2a82e80,86761.0,86761.0,0.0,86761.0,64,0x7f7014f62e80,0.0,64,0x7f44b3226e80,131354.0,131072.0,0.0,87437.0,64,0x7ff185560e80,86609.0,0.0,131112.0,0.0,64,0x7fae2a094e80,342752,228195,16384,42843,42843,1370976.0,808889.0,0.0,0.0,64,0x7fbac7f20e80,131342.0,0.0,538.0,131341.0,64,0x7f3d3e006e80,262567.0,0.0,47.0,262520.0,64,0x7fb39b6f0e80,0.0,0.0,63293.0,128704.0,64,0x7f58921a2e80,0.0,0.0,137180155.0,48683210.0,64,0x7ff374bcce80,48.0,244.0,0.0,262144.0,64,0x7f871fd60e80,69388.0,0.0,0.0,69388.0,194049837347391,194049837366591 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_2,obj_2,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_3,obj_3,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_5,obj_5,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_6,obj_6,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_10,obj_10,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f1868864ec0,262684.0,0.0,188.0,262496.0,64,0x7f17ba984ec0,131413.0,0.0,674.0,131412.0,64,0x7f0e77e04ec0,0.0,0.0,129159811.0,60109603.0,64,0x7f7dbf5d8ec0,92544.0,0.0,0.0,92544.0,64,0x7f2644fd8ec0,86437.0,44635.0,131111.0,0.0,64,0x7f030f53cec0,48.0,266.0,0.0,262288.0,64,0x7f0fc5520ec0,131597.0,131072.0,0.0,131104.0,64,0x7f7cd8e40ec0,0.0,0.0,77297.0,145412.0,64,0x7f5079f58ec0,385080,233105,16384,48134,48134,1540288.0,951621.0,0.0,0.0,64,0x7f1295050ec0,131072.0,131072.0,0.0,131072.0,64,0x7f7206b34ec0,0.0,1409979859160872,1409979859184712 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f1868864ec0,262563.0,0.0,47.0,262516.0,64,0x7f17ba984ec0,131416.0,0.0,686.0,131415.0,64,0x7f0e77e04ec0,0.0,0.0,124113089.0,46916474.0,64,0x7f7dbf5d8ec0,62759.0,0.0,0.0,62759.0,64,0x7f2644fd8ec0,86428.0,0.0,131112.0,0.0,64,0x7f030f53cec0,48.0,334.0,0.0,262144.0,64,0x7f0fc5520ec0,131391.0,131072.0,0.0,86766.0,64,0x7f7cd8e40ec0,0.0,0.0,58671.0,124422.0,64,0x7f5079f58ec0,352544,236716,16384,44067,44067,1410144.0,824545.0,0.0,0.0,64,0x7f1295050ec0,86801.0,86801.0,0.0,86801.0,64,0x7f7206b34ec0,0.0,1409979859277512,1409979859296232 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f1868864ec0,262560.0,0.0,47.0,262513.0,64,0x7f17ba984ec0,131415.0,0.0,684.0,131414.0,64,0x7f0e77e04ec0,0.0,0.0,106919299.0,46900745.0,64,0x7f7dbf5d8ec0,74628.0,0.0,0.0,74628.0,64,0x7f2644fd8ec0,86359.0,0.0,131112.0,0.0,64,0x7f030f53cec0,48.0,273.0,0.0,262144.0,64,0x7f0fc5520ec0,131403.0,131072.0,0.0,87438.0,64,0x7f7cd8e40ec0,0.0,0.0,67174.0,132897.0,64,0x7f5079f58ec0,341600,229502,16384,42699,42699,1366368.0,804630.0,0.0,0.0,64,0x7f1295050ec0,86393.0,86393.0,0.0,86393.0,64,0x7f7206b34ec0,0.0,1409979859317672,1409979859336392 diff --git a/tests/workloads/ipblocks_TCC/MI100/sysinfo.csv b/tests/workloads/ipblocks_TCC/MI100/sysinfo.csv index 466aef0b4b..7947c06dab 100644 --- a/tests/workloads/ipblocks_TCC/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_TCC/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TCC,./tests/vcopy -n 1048576 -b 256 -i 3,tcc,Thu 07 Mar 2024 01:05:09 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_TCC,./tests/vcopy -n 1048576 -b 256 -i 3,tcc,Thu 21 Mar 2024 03:50:39 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_TCC/MI100/timestamps.csv b/tests/workloads/ipblocks_TCC/MI100/timestamps.csv index 90b1d3d4b7..ca009321cb 100644 --- a/tests/workloads/ipblocks_TCC/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_TCC/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,100093,100093,1048576,256,0,0,8,8,16,64,0x0,0x7f1bd1faae80,194049837169557,194049837194911,194049837219071,194049837231976 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,100093,100093,1048576,256,0,0,8,8,16,64,0x0,0x7f1bd1faae80,194049837232156,194049837306111,194049837325471,194049837326685 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,100093,100093,1048576,256,0,0,8,8,16,64,0x0,0x7f1bd1faae80,194049837337425,194049837347391,194049837366591,194049837367592 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1195730,1195730,1048576,256,0,0,8,8,16,64,0x0,0x7f2885d54ec0,1409979859132112,1409979859160872,1409979859184712,1409979859198717 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1195730,1195730,1048576,256,0,0,8,8,16,64,0x0,0x7f2885d54ec0,1409979859197024,1409979859277512,1409979859296232,1409979859297654 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1195730,1195730,1048576,256,0,0,8,8,16,64,0x0,0x7f2885d54ec0,1409979859308294,1409979859317672,1409979859336392,1409979859337659 diff --git a/tests/workloads/ipblocks_TCC/MI200/log.txt b/tests/workloads/ipblocks_TCC/MI200/log.txt new file mode 100644 index 0000000000..14892f76bb --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/log.txt @@ -0,0 +1,304 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_TCC/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['tcc'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_160116' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160116_4068510' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160116_4068510/input0_results_240321_160116' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160116_4068510/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, GRBM_COUNT, GRBM_GUI_ACTIVE, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160116_4068510/input0_results_240321_160116 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_160116' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160116_4068711' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160116_4068711/input0_results_240321_160116' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160116_4068711/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160116_4068711/input0_results_240321_160116 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_160117' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160117_4068912' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160117_4068912/input0_results_240321_160117' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160117_4068912/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160117_4068912/input0_results_240321_160117 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_160117' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160117_4069113' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160117_4069113/input0_results_240321_160117' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160117_4069113/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160117_4069113/input0_results_240321_160117 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_160118' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160118_4069314' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160118_4069314/input0_results_240321_160118' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160118_4069314/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160118_4069314/input0_results_240321_160118 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_160118' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160118_4069515' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160118_4069515/input0_results_240321_160118' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160118_4069515/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160118_4069515/input0_results_240321_160118 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_160119' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160119_4069719' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160119_4069719/input0_results_240321_160119' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160119_4069719/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160119_4069719/input0_results_240321_160119 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_160119' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160119_4069920' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160119_4069920/input0_results_240321_160119' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160119_4069920/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160119_4069920/input0_results_240321_160119 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_160120' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160120_4070105' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160120_4070105/input0_results_240321_160120' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160120_4070105/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160120_4070105/input0_results_240321_160120 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCC/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_160120' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCC/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160120_4070289' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160120_4070289/input0_results_240321_160120' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160120_4070289/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160120_4070289/input0_results_240321_160120 + |-> [rocprof] File 'tests/workloads/ipblocks_TCC/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_TCC/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_TCC/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TCC/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_TCC/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv b/tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv index 5030017cf0..9cf8ee6ba6 100644 --- a/tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_TCC/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_3,obj_3,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_6,obj_6,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_7,obj_7,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4e138d8ec0,131072.0,131072.0,0.0,131072.0,64,0x7f9bbb83cec0,39574578.0,35049244.0,0.0,64,0x7f233bc40ec0,131083.0,34173.0,46381.0,19155.0,64,0x7f89c7560ec0,73109.0,131072.0,0.0,65568.0,64,0x7f5f10404ec0,56.0,6.0,0.0,204354.0,64,0x7fc9638d0ec0,65551.0,0.0,0.0,0.0,64,0x7f45aad84ec0,223400,130306,16384,27924,27924,893568.0,484905.0,0.0,0.0,64,0x7f5ebb060ec0,204668.0,0.0,73587.0,131081.0,64,0x7f3df06d8ec0,511.0,131081.0,0.0,10.0,197221464101706,197221464121866 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4e138d8ec0,91182.0,91182.0,0.0,91182.0,64,0x7f9bbb83cec0,120415173.0,58005504.0,0.0,64,0x7f233bc40ec0,131084.0,85270.0,45690.0,0.0,64,0x7f89c7560ec0,69560.0,131072.0,0.0,45420.0,64,0x7f5f10404ec0,56.0,9.0,0.0,200481.0,64,0x7fc9638d0ec0,65552.0,0.0,0.0,0.0,64,0x7f45aad84ec0,330360,222253,16384,41294,41294,1321408.0,780115.0,0.0,0.0,64,0x7f5ebb060ec0,201082.0,0.0,69998.0,131084.0,64,0x7f3df06d8ec0,5930.0,131083.0,0.0,20.0,197221464151626,197221464166986 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4e138d8ec0,91226.0,91226.0,0.0,91226.0,64,0x7f9bbb83cec0,118873813.0,60394998.0,0.0,64,0x7f233bc40ec0,131083.0,95089.0,45502.0,0.0,64,0x7f89c7560ec0,69737.0,131072.0,0.0,45790.0,64,0x7f5f10404ec0,56.0,10.0,0.0,200441.0,64,0x7fc9638d0ec0,65552.0,0.0,0.0,0.0,64,0x7f45aad84ec0,334568,224123,16384,41820,41820,1338240.0,778279.0,0.0,0.0,64,0x7f5ebb060ec0,200553.0,0.0,69469.0,131084.0,64,0x7f3df06d8ec0,4408.0,131083.0,0.0,20.0,197221464220586,197221464237226 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_2,obj_2,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_4,obj_4,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_5,obj_5,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_6,obj_6,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fe38a840ec0,40605653.0,34535846.0,0.0,64,0x7f2dfbcecec0,224568,132086,16384,28070,28070,898240.0,492681.0,0.0,0.0,64,0x7f0c16030ec0,56.0,9.0,0.0,204420.0,64,0x7f44171d4ec0,131072.0,131072.0,0.0,131072.0,64,0x7f81c2e60ec0,65551.0,0.0,0.0,0.0,64,0x7f30d699cec0,131081.0,35614.0,46183.0,19353.0,64,0x7ff1c7ef0ec0,203805.0,0.0,72724.0,131081.0,64,0x7f24b1d5cec0,73358.0,131072.0,0.0,65568.0,64,0x7fc291930ec0,334.0,131084.0,0.0,16.0,1410612963008296,1410612963028616 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fe38a840ec0,119903683.0,61939255.0,0.0,64,0x7f2dfbcecec0,330224,221188,16384,41277,41277,1320864.0,771339.0,0.0,0.0,64,0x7f0c16030ec0,56.0,13.0,0.0,200626.0,64,0x7f44171d4ec0,91198.0,91198.0,0.0,91198.0,64,0x7f81c2e60ec0,65552.0,0.0,0.0,0.0,64,0x7f30d699cec0,131083.0,99610.0,45639.0,0.0,64,0x7ff1c7ef0ec0,201162.0,0.0,70079.0,131083.0,64,0x7f24b1d5cec0,69362.0,131072.0,0.0,45610.0,64,0x7fc291930ec0,53032.0,131086.0,0.0,26.0,1410612963047976,1410612963063336 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fe38a840ec0,114170771.0,61439885.0,0.0,64,0x7f2dfbcecec0,328096,222190,16384,41011,41011,1312352.0,777967.0,0.0,0.0,64,0x7f0c16030ec0,56.0,14.0,0.0,200825.0,64,0x7f44171d4ec0,91144.0,91144.0,0.0,91144.0,64,0x7f81c2e60ec0,65552.0,0.0,0.0,0.0,64,0x7f30d699cec0,131083.0,117831.0,45617.0,0.0,64,0x7ff1c7ef0ec0,201095.0,0.0,70012.0,131083.0,64,0x7f24b1d5cec0,69751.0,131072.0,0.0,45661.0,64,0x7fc291930ec0,7366.0,131085.0,0.0,24.0,1410612963116776,1410612963133256 diff --git a/tests/workloads/ipblocks_TCC/MI200/roofline.csv b/tests/workloads/ipblocks_TCC/MI200/roofline.csv index 33d4ca68f6..f02b5b4cb5 100644 --- a/tests/workloads/ipblocks_TCC/MI200/roofline.csv +++ b/tests/workloads/ipblocks_TCC/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.6752,1388.1373,1389.213,5017.1997,5014.0039,5020.3955,9224.4521,9223.7148,9225.1895,18054.023,18053.035,18055.012,20937.457,20877.061,20997.854,20266.201,20265.646,20266.756,170439.42,170434.2,170444.64,164884.09,164879.08,164889.11,41419.691,41418.996,41420.387,41480.391,41479.809,41480.973,166345.41,165853.98,166836.83 -1,1389.1864,1388.6312,1389.7416,5027.6445,5025.6069,5029.6821,9233.4541,9232.8564,9234.0518,18093.193,18089.07,18097.316,20973.025,20905.926,21040.125,20290.9,20290.348,20291.453,170828.36,170823.75,170832.97,165075.27,165070.19,165080.34,41479.719,41478.855,41480.582,41539.012,41537.801,41540.223,166861.7,166858.67,166864.73 -2,1388.9811,1388.4561,1389.5061,5036.355,5034.291,5038.4189,9261.3633,9260.626,9262.1006,18108.422,18107.715,18109.129,21048.971,21048.531,21049.41,20354.988,20354.508,20355.469,171128.56,171124.98,171132.14,165508.55,165504.98,165512.11,41587.398,41585.887,41588.91,41649.879,41648.688,41651.07,166974.3,166380.06,167568.53 -3,1388.9543,1388.3977,1389.511,5032.1895,5030.8799,5033.499,9239.9756,9239.4219,9240.5293,18023.918,18020.02,18027.816,21033.564,21032.939,21034.189,20313.762,20313.125,20314.398,171030.3,171027.31,171033.28,165229.09,165223.56,165234.62,41438.047,41282.539,41593.555,41581.246,41580.742,41581.75,167015.31,167013.75,167016.88 +0,1388.5308,1387.9637,1389.0978,5016.0796,5013.1602,5018.999,9225.3223,9224.7207,9225.9238,17714.514,17711.285,17717.742,20939.455,20879.264,20999.646,20269.252,20268.49,20270.014,170461.02,170456.23,170465.8,164917.16,164912.66,164921.66,41432.449,41431.758,41433.141,41487.473,41486.824,41488.121,166380.84,165891.78,166869.91 +1,1389.3137,1388.7161,1389.9114,5028.1567,5026.1626,5030.1509,9234.4111,9233.7793,9235.043,18233.73,18231.342,18236.119,20978.275,20911.553,21044.998,20295.094,20294.48,20295.707,170857.81,170853.05,170862.58,165114.77,165110.95,165118.58,41488.934,41488.027,41489.84,41553.828,41552.875,41554.781,166912.98,166909.36,166916.61 +2,1388.7283,1388.21,1389.2466,5035.7129,5033.5591,5037.8667,9261.4785,9260.7559,9262.2012,18218.422,18217.48,18219.363,21051.08,21050.631,21051.529,20352.553,20352.023,20353.082,171158.55,171153.28,171163.81,165538.66,165534.73,165542.58,41593.414,41592.414,41594.414,41651.828,41650.789,41652.867,167005.81,166413.23,167598.39 +3,1389.2,1388.5686,1389.8313,5033.0186,5031.4722,5034.5649,9240.1025,9239.4434,9240.7617,18329.734,18328.959,18330.51,21033.336,21033.047,21033.625,20309.037,20308.498,20309.576,171032.92,171028.52,171037.33,165158.66,165154.62,165162.69,41429.262,41274.348,41584.176,41572.746,41571.828,41573.664,166961.53,166956.75,166966.31 diff --git a/tests/workloads/ipblocks_TCC/MI200/sysinfo.csv b/tests/workloads/ipblocks_TCC/MI200/sysinfo.csv index 7ebfa17df1..197b7a9acb 100644 --- a/tests/workloads/ipblocks_TCC/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_TCC/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TCC,./sample/vcopy -n 1048576 -b 256 -i 3,tcc|roofline,Thu 07 Mar 2024 01:58:04 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_TCC,./tests/vcopy -n 1048576 -b 256 -i 3,tcc|roofline,Thu 21 Mar 2024 04:01:15 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_TCC/MI200/timestamps.csv b/tests/workloads/ipblocks_TCC/MI200/timestamps.csv index 3c285df99c..67b98cd8d0 100644 --- a/tests/workloads/ipblocks_TCC/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_TCC/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,247861,247861,1048576,256,0,0,8,0,16,64,0x0,0x7fcdc9168ec0,197221464077878,197221464101706,197221464121866,197221464147971 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,247861,247861,1048576,256,0,0,8,0,16,64,0x0,0x7fcdc9168ec0,197221464140487,197221464151626,197221464166986,197221464217122 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,247861,247861,1048576,256,0,0,8,0,16,64,0x0,0x7fcdc9168ec0,197221464177567,197221464220586,197221464237226,197221464238242 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4070449,4070449,1048576,256,0,0,8,0,16,64,0x0,0x7f2d967c0ec0,1410612962984732,1410612963008296,1410612963028616,1410612963042251 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4070449,4070449,1048576,256,0,0,8,0,16,64,0x0,0x7f2d967c0ec0,1410612963039546,1410612963047976,1410612963063336,1410612963113827 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4070449,4070449,1048576,256,0,0,8,0,16,64,0x0,0x7f2d967c0ec0,1410612963073841,1410612963116776,1410612963133256,1410612963142020 diff --git a/tests/workloads/ipblocks_TCP/MI100/log.txt b/tests/workloads/ipblocks_TCP/MI100/log.txt new file mode 100644 index 0000000000..b035b3b01c --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI100/log.txt @@ -0,0 +1,331 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_TCP/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['tcp'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155100' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155100_1200526' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155100_1200526/input0_results_240321_155100' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155100_1200526/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 11 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155100_1200526/input0_results_240321_155100 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155101' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155101_1200712' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155101_1200712/input0_results_240321_155101' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155101_1200712/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155101_1200712/input0_results_240321_155101 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155101' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155101_1200899' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155101_1200899/input0_results_240321_155101' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155101_1200899/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155101_1200899/input0_results_240321_155101 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155102' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155102_1201112' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155102_1201112/input0_results_240321_155102' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155102_1201112/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155102_1201112/input0_results_240321_155102 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155102' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155102_1201313' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155102_1201313/input0_results_240321_155102' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155102_1201313/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155102_1201313/input0_results_240321_155102 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155103' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155103_1201513' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155103_1201513/input0_results_240321_155103' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155103_1201513/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155103_1201513/input0_results_240321_155103 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155103' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155103_1201713' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155103_1201713/input0_results_240321_155103' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155103_1201713/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155103_1201713/input0_results_240321_155103 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155104' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155104_1201916' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155104_1201916/input0_results_240321_155104' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155104_1201916/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155104_1201916/input0_results_240321_155104 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155104' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155104_1202117' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155104_1202117/input0_results_240321_155104' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155104_1202117/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155104_1202117/input0_results_240321_155104 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155104' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155104_1202318' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155104_1202318/input0_results_240321_155104' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155104_1202318/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155104_1202318/input0_results_240321_155104 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155105' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155105_1202501' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155105_1202501/input0_results_240321_155105' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155105_1202501/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155105_1202501/input0_results_240321_155105 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_TCP/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TCP/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_TCP/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_TCP/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv b/tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv index 02289b4959..7678815502 100644 --- a/tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_TCP/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,wave_size_1,obj_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,wave_size_3,obj_3,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,wave_size_4,obj_4,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_5,obj_5,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_6,obj_6,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,wave_size_7,obj_7,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_8,obj_8,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,wave_size_9,obj_9,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f12cc0f6e80,0.0,0.0,120.0,524288.0,64,0x7f495b82ae80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f9b0bfd2e80,406872,240230,3508070,16384,25521642,50858,50858,3956486.0,3023959.0,8290.0,1189874.0,64,0x7f828a5d8e80,960.0,513952.0,0.0,524288.0,64,0x7f3e0b46ae80,131072.0,131072.0,0.0,2589805.0,64,0x7f9b95378e80,0.0,0.0,0.0,0.0,64,0x7f08eb366e80,0.0,0.0,0.0,32768.0,64,0x7fdc3fb00e80,131072.0,0.0,0.0,0.0,64,0x7f6afaf00e80,71052435.0,201658168.0,81356112.0,131072.0,64,0x7fcec552ae80,0.0,0.0,0.0,0.0,194070298825333,194070298849653 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f12cc0f6e80,0.0,0.0,120.0,524288.0,64,0x7f495b82ae80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f9b0bfd2e80,396416,218905,3203855,16384,23148465,49551,49551,3573611.0,3040613.0,6466.0,1230212.0,64,0x7f828a5d8e80,960.0,513897.0,0.0,524288.0,64,0x7f3e0b46ae80,131072.0,131072.0,0.0,2568024.0,64,0x7f9b95378e80,0.0,0.0,0.0,0.0,64,0x7f08eb366e80,0.0,0.0,0.0,32768.0,64,0x7fdc3fb00e80,131072.0,0.0,0.0,0.0,64,0x7f6afaf00e80,68065829.0,192283723.0,76332243.0,131072.0,64,0x7fcec552ae80,0.0,0.0,0.0,0.0,194070298947253,194070298966453 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f12cc0f6e80,0.0,0.0,120.0,524288.0,64,0x7f495b82ae80,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f9b0bfd2e80,344600,229289,3355582,16384,24502194,43074,43074,3737726.0,3019215.0,6611.0,1052353.0,64,0x7f828a5d8e80,960.0,513968.0,0.0,524288.0,64,0x7f3e0b46ae80,131072.0,131072.0,0.0,2449269.0,64,0x7f9b95378e80,0.0,0.0,0.0,0.0,64,0x7f08eb366e80,0.0,0.0,0.0,32768.0,64,0x7fdc3fb00e80,131072.0,0.0,0.0,0.0,64,0x7f6afaf00e80,69082609.0,188996267.0,77536972.0,131072.0,64,0x7fcec552ae80,0.0,0.0,0.0,0.0,194070298990293,194070299009493 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,wave_size_1,obj_1,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,wave_size_2,obj_2,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_3,obj_3,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_4,obj_4,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_5,obj_5,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,wave_size_6,obj_6,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,wave_size_8,obj_8,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_9,obj_9,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f082dde8ec0,0.0,0.0,120.0,524288.0,64,0x7f4ce7cd0ec0,62569420.0,177352872.0,73126606.0,131072.0,64,0x7f5659524ec0,131072.0,131072.0,0.0,2431295.0,64,0x7fbf6dbe8ec0,0.0,0.0,0.0,0.0,64,0x7ff977d08ec0,131072.0,0.0,0.0,0.0,64,0x7f34cb3d8ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7fd37d108ec0,0.0,0.0,0.0,32768.0,64,0x7fbc662a8ec0,388736,239917,3521723,16384,25498315,48591,48591,3951146.0,3076897.0,5152.0,1019652.0,64,0x7fb2b4a1cec0,0.0,0.0,0.0,0.0,64,0x7f0f78644ec0,960.0,513975.0,0.0,524288.0,1409999465186232,1409999465211512 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f082dde8ec0,0.0,0.0,120.0,524288.0,64,0x7f4ce7cd0ec0,62520313.0,168628497.0,68665656.0,131072.0,64,0x7f5659524ec0,131072.0,131072.0,0.0,2569317.0,64,0x7fbf6dbe8ec0,0.0,0.0,0.0,0.0,64,0x7ff977d08ec0,131072.0,0.0,0.0,0.0,64,0x7f34cb3d8ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7fd37d108ec0,0.0,0.0,0.0,32768.0,64,0x7fbc662a8ec0,393368,227504,3203308,16384,22758957,49170,49170,3702176.0,3054979.0,5741.0,1069753.0,64,0x7fb2b4a1cec0,0.0,0.0,0.0,0.0,64,0x7f0f78644ec0,960.0,513986.0,0.0,524288.0,1409999465380472,1409999465399672 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f082dde8ec0,0.0,0.0,120.0,524288.0,64,0x7f4ce7cd0ec0,59852047.0,167341765.0,67534746.0,131072.0,64,0x7f5659524ec0,131072.0,131072.0,0.0,2500254.0,64,0x7fbf6dbe8ec0,0.0,0.0,0.0,0.0,64,0x7ff977d08ec0,131072.0,0.0,0.0,0.0,64,0x7f34cb3d8ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7fd37d108ec0,0.0,0.0,0.0,32768.0,64,0x7fbc662a8ec0,340992,235913,3414629,16384,24427512,42623,42623,3836411.0,3115077.0,5181.0,1254701.0,64,0x7fb2b4a1cec0,0.0,0.0,0.0,0.0,64,0x7f0f78644ec0,960.0,513898.0,0.0,524288.0,1409999465420152,1409999465439192 diff --git a/tests/workloads/ipblocks_TCP/MI100/sysinfo.csv b/tests/workloads/ipblocks_TCP/MI100/sysinfo.csv index 9ebace481a..bc00696c3c 100644 --- a/tests/workloads/ipblocks_TCP/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_TCP/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TCP,./tests/vcopy -n 1048576 -b 256 -i 3,tcp,Thu 07 Mar 2024 01:05:30 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_TCP,./tests/vcopy -n 1048576 -b 256 -i 3,tcp,Thu 21 Mar 2024 03:51:00 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_TCP/MI100/timestamps.csv b/tests/workloads/ipblocks_TCP/MI100/timestamps.csv index 5f67cfaacb..60339e40c1 100644 --- a/tests/workloads/ipblocks_TCP/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_TCP/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,106948,106948,1048576,256,0,0,8,8,16,64,0x0,0x7f08c7b52e80,194070298794474,194070298825333,194070298849653,194070298865609 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,106948,106948,1048576,256,0,0,8,8,16,64,0x0,0x7f08c7b52e80,194070298865779,194070298947253,194070298966453,194070298967762 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,106948,106948,1048576,256,0,0,8,8,16,64,0x0,0x7f08c7b52e80,194070298979905,194070298990293,194070299009493,194070299010673 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1202661,1202661,1048576,256,0,0,8,8,16,64,0x0,0x7f37ef840ec0,1409999465159847,1409999465186232,1409999465211512,1409999465223306 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1202661,1202661,1048576,256,0,0,8,8,16,64,0x0,0x7f37ef840ec0,1409999465223888,1409999465380472,1409999465399672,1409999465401102 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1202661,1202661,1048576,256,0,0,8,8,16,64,0x0,0x7f37ef840ec0,1409999465411592,1409999465420152,1409999465439192,1409999465440306 diff --git a/tests/workloads/ipblocks_TCP/MI200/log.txt b/tests/workloads/ipblocks_TCP/MI200/log.txt new file mode 100644 index 0000000000..34e4443b5b --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/log.txt @@ -0,0 +1,333 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_TCP/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['tcp'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_160440' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160440_4075818' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160440_4075818/input0_results_240321_160440' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160440_4075818/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 11 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160440_4075818/input0_results_240321_160440 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_160440' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160440_4076021' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160440_4076021/input0_results_240321_160440' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160440_4076021/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160440_4076021/input0_results_240321_160440 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_160441' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160441_4076231' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160441_4076231/input0_results_240321_160441' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160441_4076231/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160441_4076231/input0_results_240321_160441 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_160441' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160441_4076432' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160441_4076432/input0_results_240321_160441' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160441_4076432/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160441_4076432/input0_results_240321_160441 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_160442' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160442_4076621' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160442_4076621/input0_results_240321_160442' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160442_4076621/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160442_4076621/input0_results_240321_160442 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_160442' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160442_4076805' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160442_4076805/input0_results_240321_160442' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160442_4076805/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160442_4076805/input0_results_240321_160442 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_160443' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160443_4077003' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160443_4077003/input0_results_240321_160443' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160443_4077003/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160443_4077003/input0_results_240321_160443 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_160443' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160443_4077186' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160443_4077186/input0_results_240321_160443' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160443_4077186/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160443_4077186/input0_results_240321_160443 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_160444' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160444_4077390' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160444_4077390/input0_results_240321_160444' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160444_4077390/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160444_4077390/input0_results_240321_160444 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_160444' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160444_4077591' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160444_4077591/input0_results_240321_160444' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160444_4077591/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 4 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160444_4077591/input0_results_240321_160444 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TCP/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_160445' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TCP/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160445_4077774' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160445_4077774/input0_results_240321_160445' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160445_4077774/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160445_4077774/input0_results_240321_160445 + |-> [rocprof] File 'tests/workloads/ipblocks_TCP/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_TCP/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_TCP/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TCP/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_TCP/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv b/tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv index 3df0bb08ca..fed70015f2 100644 --- a/tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_TCP/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,wave_size_1,obj_1,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_2,obj_2,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_4,obj_4,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_5,obj_5,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,wave_size_6,obj_6,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,wave_size_7,obj_7,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_8,obj_8,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,wave_size_9,obj_9,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9404948ec0,0.0,0.0,0.0,32768.0,64,0x7f2689a48ec0,0.0,0.0,0.0,0.0,64,0x7f60248f0ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f98f1a8cec0,131072.0,131072.0,0.0,916665.0,64,0x7f99e30d4ec0,0.0,0.0,0.0,0.0,64,0x7f49da658ec0,218024,126138,1592956,16384,10612728,27252,27252,1917310.0,1320290.0,3653.0,175563.0,64,0x7f87c2994ec0,27579886.0,86090451.0,39383215.0,131072.0,64,0x7fde3a900ec0,131072.0,0.0,0.0,0.0,64,0x7f3bbb108ec0,0.0,0.0,0.0,524288.0,64,0x7f6d3ba48ec0,832.0,515140.0,0.0,524288.0,197425575298507,197425575319307 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9404948ec0,0.0,0.0,0.0,32768.0,64,0x7f2689a48ec0,0.0,0.0,0.0,0.0,64,0x7f60248f0ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f98f1a8cec0,131072.0,131072.0,0.0,2085832.0,64,0x7f99e30d4ec0,0.0,0.0,0.0,0.0,64,0x7f49da658ec0,300064,204807,2541439,16384,17422948,37507,37507,2940098.0,2361650.0,4186.0,338609.0,64,0x7f87c2994ec0,58079980.0,197098793.0,45794862.0,131072.0,64,0x7fde3a900ec0,131072.0,0.0,0.0,0.0,64,0x7f3bbb108ec0,0.0,0.0,0.0,524288.0,64,0x7f6d3ba48ec0,0.0,524288.0,0.0,524288.0,197425575401067,197425575417707 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f9404948ec0,0.0,0.0,0.0,32768.0,64,0x7f2689a48ec0,0.0,0.0,0.0,0.0,64,0x7f60248f0ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f98f1a8cec0,131072.0,131072.0,0.0,1992345.0,64,0x7f99e30d4ec0,0.0,0.0,0.0,0.0,64,0x7f49da658ec0,327256,221096,2738473,16384,19028519,40906,40906,3152076.0,2440924.0,4152.0,379488.0,64,0x7f87c2994ec0,58426172.0,197564310.0,47383725.0,131072.0,64,0x7fde3a900ec0,131072.0,0.0,0.0,0.0,64,0x7f3bbb108ec0,0.0,0.0,0.0,524288.0,64,0x7f6d3ba48ec0,832.0,515152.0,0.0,524288.0,197425575438347,197425575454027 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,wave_size_1,obj_1,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,wave_size_2,obj_2,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,wave_size_3,obj_3,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,wave_size_4,obj_4,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,wave_size_5,obj_5,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,wave_size_6,obj_6,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,wave_size_7,obj_7,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,wave_size_8,obj_8,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,wave_size_9,obj_9,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7eff34ef0ec0,217264,124770,1573429,16384,10415320,27157,27157,1899500.0,1308294.0,3446.0,134964.0,64,0x7f621de2cec0,0.0,0.0,0.0,0.0,64,0x7f61a4140ec0,27789021.0,87908941.0,39254709.0,131072.0,64,0x7f41549e8ec0,0.0,0.0,0.0,32768.0,64,0x7f64613a4ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f3c1673cec0,0.0,0.0,0.0,524288.0,64,0x7f33ef008ec0,131072.0,0.0,0.0,0.0,64,0x7fcd84d90ec0,0.0,0.0,0.0,0.0,64,0x7f823cb68ec0,832.0,515136.0,0.0,524288.0,64,0x7fa26d558ec0,131072.0,131072.0,0.0,953117.0,1410817289782557,1410817289802557 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7eff34ef0ec0,299368,207400,2582109,16384,17688953,37420,37420,2973820.0,2357925.0,4691.0,333048.0,64,0x7f621de2cec0,0.0,0.0,0.0,0.0,64,0x7f61a4140ec0,58209677.0,202307110.0,47963277.0,131072.0,64,0x7f41549e8ec0,0.0,0.0,0.0,32768.0,64,0x7f64613a4ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f3c1673cec0,0.0,0.0,0.0,524288.0,64,0x7f33ef008ec0,131072.0,0.0,0.0,0.0,64,0x7fcd84d90ec0,0.0,0.0,0.0,0.0,64,0x7f823cb68ec0,0.0,524288.0,0.0,524288.0,64,0x7fa26d558ec0,131072.0,131072.0,0.0,2024827.0,1410817289822237,1410817289837597 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7eff34ef0ec0,324400,217191,2708536,16384,18627984,40549,40549,3101012.0,2411256.0,3763.0,295052.0,64,0x7f621de2cec0,0.0,0.0,0.0,0.0,64,0x7f61a4140ec0,57002881.0,196316448.0,49065419.0,131072.0,64,0x7f41549e8ec0,0.0,0.0,0.0,32768.0,64,0x7f64613a4ec0,2097152.0,2097152.0,1048576.0,1048576.0,64,0x7f3c1673cec0,0.0,0.0,0.0,524288.0,64,0x7f33ef008ec0,131072.0,0.0,0.0,0.0,64,0x7fcd84d90ec0,0.0,0.0,0.0,0.0,64,0x7f823cb68ec0,832.0,515164.0,0.0,524288.0,64,0x7fa26d558ec0,131072.0,131072.0,0.0,2070467.0,1410817289931037,1410817289947677 diff --git a/tests/workloads/ipblocks_TCP/MI200/roofline.csv b/tests/workloads/ipblocks_TCP/MI200/roofline.csv index e19a404bcd..2f0fa4bc08 100644 --- a/tests/workloads/ipblocks_TCP/MI200/roofline.csv +++ b/tests/workloads/ipblocks_TCP/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.191,1388.6029,1389.7792,5016.8271,5013.8096,5019.8447,9224.8887,9224.0996,9225.6777,18054.102,18053.037,18055.166,20938.258,20877.508,20999.008,20267.289,20266.496,20268.082,170451.02,170447.69,170454.34,164887.59,164882.64,164892.55,41427.105,41426.293,41427.918,41483.168,41482.504,41483.832,166362.02,165869.12,166854.91 -1,1389.2063,1388.6646,1389.748,5027.7417,5025.7686,5029.7148,9234.083,9233.3975,9234.7686,18089.377,18086.072,18092.682,20975.256,20908.32,21042.191,20295.521,20294.941,20296.102,170852.36,170848.52,170856.2,165103,165099.17,165106.83,41484.324,41483.551,41485.098,41539.77,41538.516,41541.023,166875.3,166872.31,166878.28 -2,1388.9279,1388.3605,1389.4952,5036.6958,5034.4482,5038.9434,9260.9668,9260.041,9261.8926,18104.98,18104.059,18105.902,21050.352,21050.016,21050.688,20357.52,20356.998,20358.041,171149.73,171146.53,171152.94,165557.28,165553.61,165560.95,41596.461,41595.207,41597.715,41654.727,41653.766,41655.688,167314.88,167310.36,167319.39 -3,1388.734,1388.205,1389.2631,5031.7368,5030.3604,5033.1133,9239.874,9239.3086,9240.4395,18022.992,18018.922,18027.062,21029.609,21029.219,21030,20311.082,20310.459,20311.705,171019.62,171016.36,171022.89,165217.78,165212.28,165223.28,41438.387,41283.484,41593.289,41580.906,41580.363,41581.449,167016.12,167013.67,167018.58 +0,1389.229,1388.6951,1389.7629,5016.5439,5013.6182,5019.4697,9225.2363,9224.5938,9225.8789,17711.488,17708.428,17714.549,20939.494,20879.295,20999.693,20269.387,20268.805,20269.969,170447.95,170445.09,170450.81,164897.44,164893.28,164901.59,41430.199,41429.719,41430.68,41486.699,41486.07,41487.328,166373.98,165885.83,166862.14 +1,1389.1674,1388.6852,1389.6495,5028.1787,5026.1685,5030.189,9235.4434,9234.7383,9236.1484,18235.691,18234.344,18237.039,20980.814,20913.59,21048.039,20297.303,20296.709,20297.896,170894.64,170890.31,170898.97,165133.64,165128.7,165138.58,41489.723,41488.773,41490.672,41547.977,41547.191,41548.762,166899.98,166896.86,166903.11 +2,1388.7267,1388.2098,1389.2435,5037.3843,5035.231,5039.5376,9262.4951,9261.8936,9263.0967,18219.873,18218.959,18220.787,21051.592,21051.145,21052.039,20352.357,20351.725,20352.99,171142.23,171138,171146.47,165534.73,165531.28,165538.19,41591.219,41590.383,41592.055,41645.547,41644.648,41646.445,167009.75,166418.42,167601.08 +3,1388.9153,1388.3167,1389.5139,5032.7505,5031.1323,5034.3687,9236.3203,9235.5762,9237.0645,18326.316,18325.15,18327.482,21030.846,21030.357,21031.334,20303.855,20303.328,20304.383,170991.69,170987.78,170995.59,165127.06,165122.45,165131.67,41422.16,41268.848,41575.473,41559.551,41558.504,41560.598,166945.06,166941.39,166948.73 diff --git a/tests/workloads/ipblocks_TCP/MI200/sysinfo.csv b/tests/workloads/ipblocks_TCP/MI200/sysinfo.csv index 31a43e0624..83e24f9bc5 100644 --- a/tests/workloads/ipblocks_TCP/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_TCP/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TCP,./sample/vcopy -n 1048576 -b 256 -i 3,tcp|roofline,Thu 07 Mar 2024 02:01:27 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_TCP,./tests/vcopy -n 1048576 -b 256 -i 3,tcp|roofline,Thu 21 Mar 2024 04:04:39 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_TCP/MI200/timestamps.csv b/tests/workloads/ipblocks_TCP/MI200/timestamps.csv index cee39d536c..6eebeb286d 100644 --- a/tests/workloads/ipblocks_TCP/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_TCP/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,255418,255418,1048576,256,0,0,8,0,16,64,0x0,0x7f14cf350ec0,197425575274886,197425575298507,197425575319307,197425575330561 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,255418,255418,1048576,256,0,0,8,0,16,64,0x0,0x7f14cf350ec0,197425575330261,197425575401067,197425575417707,197425575419189 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,255418,255418,1048576,256,0,0,8,0,16,64,0x0,0x7f14cf350ec0,197425575428927,197425575438347,197425575454027,197425575455397 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4077934,4077934,1048576,256,0,0,8,0,16,64,0x0,0x7f8b54fa0ec0,1410817289757663,1410817289782557,1410817289802557,1410817289825371 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4077934,4077934,1048576,256,0,0,8,0,16,64,0x0,0x7f8b54fa0ec0,1410817289813639,1410817289822237,1410817289837597,1410817289926994 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4077934,4077934,1048576,256,0,0,8,0,16,64,0x0,0x7f8b54fa0ec0,1410817289848044,1410817289931037,1410817289947677,1410817289948815 diff --git a/tests/workloads/ipblocks_TD/MI100/log.txt b/tests/workloads/ipblocks_TD/MI100/log.txt new file mode 100644 index 0000000000..ae589adee6 --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI100/log.txt @@ -0,0 +1,128 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_TD/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['td'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_TD/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155455' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155455_1279280' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155455_1279280/input0_results_240321_155455' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155455_1279280/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, GRBM_COUNT, GRBM_GUI_ACTIVE, TD_TD_BUSY_sum, TD_TC_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155455_1279280/input0_results_240321_155455 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TD/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155455' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155455_1279465' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155455_1279465/input0_results_240321_155455' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155455_1279465/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155455_1279465/input0_results_240321_155455 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TD/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155455' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155455_1279648' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155455_1279648/input0_results_240321_155455' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155455_1279648/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155455_1279648/input0_results_240321_155455 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TD/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155456' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155456_1279835' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155456_1279835/input0_results_240321_155456' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155456_1279835/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155456_1279835/input0_results_240321_155456 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/ipblocks_TD/MI100/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TD/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/ipblocks_TD/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/ipblocks_TD/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_TD/MI100/pmc_perf.csv b/tests/workloads/ipblocks_TD/MI100/pmc_perf.csv index 39d3142d42..e63cf66bcc 100644 --- a/tests/workloads/ipblocks_TD/MI100/pmc_perf.csv +++ b/tests/workloads/ipblocks_TD/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,wave_size_1,obj_1,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd71c252e80,0.0,16384.0,64,0x7f9093004e80,0.0,32768.0,64,0x7fd456aeee80,379632,228565,3336391,16384,24381609,47453,47453,2952060.0,2641101.0,194311556312654,194311556337134 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd71c252e80,0.0,16384.0,64,0x7f9093004e80,0.0,32768.0,64,0x7fd456aeee80,336336,227259,3312174,16384,24240462,42041,42041,2989256.0,2678517.0,194311556410734,194311556429614 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fd71c252e80,0.0,16384.0,64,0x7f9093004e80,0.0,32768.0,64,0x7fd456aeee80,335624,225631,3288156,16384,24209884,41952,41952,2975008.0,2666527.0,194311556450414,194311556469294 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,wave_size_1,obj_1,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,wave_size_2,obj_2,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fdbb1c88ec0,390984,235322,3414931,16384,24204011,48872,48872,3024303.0,2717178.0,64,0x7fc3a7d44ec0,0.0,16384.0,64,0x7fd5c9150ec0,0.0,32768.0,1410230455920120,1410230455943960 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fdbb1c88ec0,339472,229477,3352543,16384,24316459,42433,42433,3057153.0,2747036.0,64,0x7fc3a7d44ec0,0.0,16384.0,64,0x7fd5c9150ec0,0.0,32768.0,1410230456040440,1410230456059480 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fdbb1c88ec0,339688,224195,3238231,16384,22698141,42460,42460,2947508.0,2636047.0,64,0x7fc3a7d44ec0,0.0,16384.0,64,0x7fd5c9150ec0,0.0,32768.0,1410230456080440,1410230456099640 diff --git a/tests/workloads/ipblocks_TD/MI100/sysinfo.csv b/tests/workloads/ipblocks_TD/MI100/sysinfo.csv index a1607a79ad..d2937b20cc 100644 --- a/tests/workloads/ipblocks_TD/MI100/sysinfo.csv +++ b/tests/workloads/ipblocks_TD/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TD,./tests/vcopy -n 1048576 -b 256 -i 3,td,Thu 07 Mar 2024 01:09:35 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +ipblocks_TD,./tests/vcopy -n 1048576 -b 256 -i 3,td,Thu 21 Mar 2024 03:54:54 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/ipblocks_TD/MI100/timestamps.csv b/tests/workloads/ipblocks_TD/MI100/timestamps.csv index f583dc2261..201249529a 100644 --- a/tests/workloads/ipblocks_TD/MI100/timestamps.csv +++ b/tests/workloads/ipblocks_TD/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,184422,184422,1048576,256,0,0,8,8,16,64,0x0,0x7f5d4bd20e80,194311556287244,194311556312654,194311556337134,194311556347738 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,184422,184422,1048576,256,0,0,8,8,16,64,0x0,0x7f5d4bd20e80,194311556350103,194311556410734,194311556429614,194311556430645 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,184422,184422,1048576,256,0,0,8,8,16,64,0x0,0x7f5d4bd20e80,194311556441726,194311556450414,194311556469294,194311556470401 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1279995,1279995,1048576,256,0,0,8,8,16,64,0x0,0x7fb911e34ec0,1410230455893848,1410230455920120,1410230455943960,1410230455955794 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1279995,1279995,1048576,256,0,0,8,8,16,64,0x0,0x7fb911e34ec0,1410230455956566,1410230456040440,1410230456059480,1410230456060903 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1279995,1279995,1048576,256,0,0,8,8,16,64,0x0,0x7fb911e34ec0,1410230456071262,1410230456080440,1410230456099640,1410230456100928 diff --git a/tests/workloads/ipblocks_TD/MI200/log.txt b/tests/workloads/ipblocks_TD/MI200/log.txt new file mode 100644 index 0000000000..57dc24a468 --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/log.txt @@ -0,0 +1,159 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/ipblocks_TD/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: ['td'] + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_164312' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164312_4170186' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164312_4170186/input0_results_240321_164312' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164312_4170186/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, GRBM_COUNT, GRBM_GUI_ACTIVE, TD_TD_BUSY_sum, TD_TC_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164312_4170186/input0_results_240321_164312 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_164312' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164312_4170370' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164312_4170370/input0_results_240321_164312' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164312_4170370/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164312_4170370/input0_results_240321_164312 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_164313' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164313_4170555' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164313_4170555/input0_results_240321_164313' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164313_4170555/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164313_4170555/input0_results_240321_164313 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_164313' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164313_4170744' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164313_4170744/input0_results_240321_164313' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164313_4170744/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TD_COALESCABLE_WAVEFRONT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164313_4170744/input0_results_240321_164313 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/ipblocks_TD/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_164314' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/ipblocks_TD/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164314_4170931' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164314_4170931/input0_results_240321_164314' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164314_4170931/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164314_4170931/input0_results_240321_164314 + |-> [rocprof] File 'tests/workloads/ipblocks_TD/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/ipblocks_TD/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/ipblocks_TD/MI200/pmc_dispatch_info.csv b/tests/workloads/ipblocks_TD/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/ipblocks_TD/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/ipblocks_TD/MI200/pmc_perf.csv b/tests/workloads/ipblocks_TD/MI200/pmc_perf.csv index 6e32f3b4ab..0b4ce10000 100644 --- a/tests/workloads/ipblocks_TD/MI200/pmc_perf.csv +++ b/tests/workloads/ipblocks_TD/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,wave_size_1,obj_1,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,wave_size_2,obj_2,TD_COALESCABLE_WAVEFRONT_sum,wave_size_3,obj_3,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f249e60cec0,0.0,16384.0,64,0x7fca27f10ec0,399.0,32768.0,64,0x7f18657b8ec0,0.0,64,0x7f46abdacec0,223128,131708,1668426,16384,11242880,27890,27890,1325799.0,1027102.0,199547059519110,199547059539430 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f249e60cec0,0.0,16384.0,64,0x7fca27f10ec0,210.0,32768.0,64,0x7f18657b8ec0,0.0,64,0x7f46abdacec0,302160,208300,2564434,16384,18120165,37769,37769,2373984.0,2062477.0,199547059627110,199547059643270 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f249e60cec0,0.0,16384.0,64,0x7fca27f10ec0,274.0,32768.0,64,0x7f18657b8ec0,0.0,64,0x7f46abdacec0,333448,224363,2787083,16384,19455944,41680,41680,2452213.0,2146452.0,199547059664230,199547059679750 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,GRBM_COUNT,GRBM_GUI_ACTIVE,TD_TD_BUSY_sum,TD_TC_STALL_sum,wave_size_1,obj_1,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,wave_size_2,obj_2,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,wave_size_3,obj_3,TD_COALESCABLE_WAVEFRONT_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f7a99804ec0,220960,128513,1624827,16384,10795952,27619,27619,1358050.0,1061134.0,64,0x7ff487768ec0,0.0,16384.0,64,0x7f03c84ecec0,447.0,32768.0,64,0x7fe2a2b38ec0,0.0,1413126661364680,1413126661384680 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f7a99804ec0,302304,206953,2591368,16384,17655189,37787,37787,2399017.0,2090333.0,64,0x7ff487768ec0,0.0,16384.0,64,0x7f03c84ecec0,236.0,32768.0,64,0x7fe2a2b38ec0,0.0,1413126661403880,1413126661419400 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f7a99804ec0,328056,219592,2759716,16384,19292387,41006,41006,2467760.0,2161716.0,64,0x7ff487768ec0,0.0,16384.0,64,0x7f03c84ecec0,204.0,32768.0,64,0x7fe2a2b38ec0,0.0,1413126661474120,1413126661490600 diff --git a/tests/workloads/ipblocks_TD/MI200/roofline.csv b/tests/workloads/ipblocks_TD/MI200/roofline.csv index 6b666a5638..7b4ce5cc58 100644 --- a/tests/workloads/ipblocks_TD/MI200/roofline.csv +++ b/tests/workloads/ipblocks_TD/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.9509,1388.3612,1389.5406,5014.793,5011.5312,5018.0547,9223.0742,9222.4434,9223.7051,18049.586,18048.721,18050.451,20931.9,20871.432,20992.369,20261.727,20261.002,20262.451,170399.3,170395.31,170403.28,164852.52,164847.61,164857.42,41417.066,41416.535,41417.598,41477.52,41476.922,41478.117,166330.03,165838.83,166821.23 -1,1389.3237,1388.8047,1389.8428,5026.1694,5024.1035,5028.2354,9231.6592,9230.9326,9232.3857,18088.08,18084.199,18091.961,20970.721,20903.84,21037.602,20289.123,20288.473,20289.773,170790.78,170786.94,170794.62,165046.8,165043.45,165050.14,41469.863,41468.957,41470.77,41529.766,41528.867,41530.664,166845.92,166842.92,166848.92 -2,1388.3853,1387.8412,1388.9293,5035.041,5032.6895,5037.3926,9259.8057,9259.0186,9260.5928,18102.119,18101.258,18102.98,21044.225,21043.779,21044.67,20347.809,20347.166,20348.451,171085.16,171081.53,171088.78,165468.19,165464.12,165472.25,41572.938,41571.941,41573.934,41631.891,41631.031,41632.75,166910.88,166318.69,167503.06 -3,1388.9561,1388.4015,1389.5106,5032.2793,5031.104,5033.4546,9240.8994,9240.209,9241.5898,18024.684,18021.26,18028.107,21037.52,21036.775,21038.264,20313.844,20313.178,20314.51,171021.56,171017.92,171025.2,165226.5,165222.19,165230.81,41441.406,41287.621,41595.191,41583.449,41582.934,41583.965,167031.38,167029.02,167033.73 +0,1388.538,1387.9762,1389.0997,5017.1182,5014.1094,5020.127,9227.043,9226.459,9227.627,17714.195,17711.281,17717.109,20944.381,20884.125,21004.637,20272.227,20271.666,20272.787,170485.48,170481.59,170489.38,164942.66,164939.66,164945.66,41443.621,41443.035,41444.207,41498.727,41497.863,41499.59,166430.06,165938.12,166922 +1,1389.3248,1388.7289,1389.9208,5028.5581,5026.3989,5030.7173,9233.707,9232.8701,9234.5439,18230.932,18229.34,18232.523,20978.568,20911.711,21045.426,20293.357,20292.748,20293.967,170856.8,170852.11,170861.48,165093.83,165088.97,165098.69,41481.453,41480.867,41482.039,41546.023,41545.035,41547.012,166878.31,166875.48,166881.14 +2,1388.7206,1388.1442,1389.297,5035.8169,5033.6934,5037.9404,9258.0723,9257.4561,9258.6885,18216.723,18215.756,18217.689,21047.006,21046.486,21047.525,20348.695,20348.139,20349.252,171100.08,171096.58,171103.58,165489.08,165485.72,165492.44,41575.102,41574.285,41575.918,41638.387,41637.543,41639.23,166958.09,166363.08,167553.11 +3,1388.8367,1388.2158,1389.4575,5033.0796,5031.4673,5034.6919,9240.8555,9240.1973,9241.5137,18333.217,18332.332,18334.102,21034.508,21034.199,21034.816,20309.066,20308.637,20309.496,171040.95,171035.69,171046.22,165180.62,165176.31,165184.94,41431.945,41277.156,41586.734,41568.371,41567.145,41569.598,166979.89,166975.81,166983.97 diff --git a/tests/workloads/ipblocks_TD/MI200/sysinfo.csv b/tests/workloads/ipblocks_TD/MI200/sysinfo.csv index fd7dc35618..01297e11e6 100644 --- a/tests/workloads/ipblocks_TD/MI200/sysinfo.csv +++ b/tests/workloads/ipblocks_TD/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -ipblocks_TD,./sample/vcopy -n 1048576 -b 256 -i 3,td|roofline,Thu 07 Mar 2024 02:36:52 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +ipblocks_TD,./tests/vcopy -n 1048576 -b 256 -i 3,td|roofline,Thu 21 Mar 2024 04:43:11 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/ipblocks_TD/MI200/timestamps.csv b/tests/workloads/ipblocks_TD/MI200/timestamps.csv index 7859d631c0..ac5a8cf723 100644 --- a/tests/workloads/ipblocks_TD/MI200/timestamps.csv +++ b/tests/workloads/ipblocks_TD/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,346607,346607,1048576,256,0,0,8,0,16,64,0x0,0x7fee2b950ec0,199547059494326,199547059519110,199547059539430,199547059552055 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,346607,346607,1048576,256,0,0,8,0,16,64,0x0,0x7fee2b950ec0,199547059550312,199547059627110,199547059643270,199547059644400 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,346607,346607,1048576,256,0,0,8,0,16,64,0x0,0x7fee2b950ec0,199547059654429,199547059664230,199547059679750,199547059680738 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4171091,4171091,1048576,256,0,0,8,0,16,64,0x0,0x7f8fd19e8ec0,1413126661339705,1413126661364680,1413126661384680,1413126661398085 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4171091,4171091,1048576,256,0,0,8,0,16,64,0x0,0x7f8fd19e8ec0,1413126661396051,1413126661403880,1413126661419400,1413126661472496 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4171091,4171091,1048576,256,0,0,8,0,16,64,0x0,0x7f8fd19e8ec0,1413126661429875,1413126661474120,1413126661490600,1413126661491822 diff --git a/tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv index 1dfb1d5aa5..3a5fa19c75 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118192,118192,1048576,256,0,0,8,8,16,64,0x0,0x7fd6acbaae80,48437,48437,16384,65536,14298,1816332,194104431495577,194116676571166,194116676595486,194104439234270 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118192,118192,1048576,256,0,0,8,8,16,64,0x0,0x7fd6acbaae80,42764,42764,16384,65536,8238,1048580,194104439255931,194116676615646,194116676634206,194104439587438 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118192,118192,1048576,256,0,0,8,8,16,64,0x0,0x7fd6acbaae80,42796,42796,16384,65536,8222,1048588,194104439621202,194116676727326,194116676746366,194104439801504 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1213878,1213878,1048576,256,0,0,8,8,16,64,0x0,0x7fc501fd8ec0,48946,48946,16384,65536,13533,1721000,1410032159353249,1410043880547753,1410043880571433,1410032167088017 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1213878,1213878,1048576,256,0,0,8,8,16,64,0x0,0x7fc501fd8ec0,43625,43625,16384,65536,8181,1048580,1410032167112132,1410043880671913,1410043880690633,1410032167425614 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1213878,1213878,1048576,256,0,0,8,8,16,64,0x0,0x7fc501fd8ec0,44283,44283,16384,65536,8388,1048596,1410032167457354,1410043880710953,1410043880730153,1410032167621583 diff --git a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv index 8b7a71eed8..b281b42c29 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118382,118382,1048576,256,0,0,8,8,16,64,0x0,0x7f17127dce80,0,0,0,194104926213446,194116676571166,194116676595486,194104933889590 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118382,118382,1048576,256,0,0,8,8,16,64,0x0,0x7f17127dce80,0,0,0,194104933908085,194116676615646,194116676634206,194104934234704 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118382,118382,1048576,256,0,0,8,8,16,64,0x0,0x7f17127dce80,0,0,0,194104934263328,194116676727326,194116676746366,194104934440583 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1214064,1214064,1048576,256,0,0,8,8,16,64,0x0,0x7ff7e8e1cec0,0,0,0,1410032643063831,1410043880547753,1410043880571433,1410032650697498 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1214064,1214064,1048576,256,0,0,8,8,16,64,0x0,0x7ff7e8e1cec0,0,0,0,1410032650719119,1410043880671913,1410043880690633,1410032651003926 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1214064,1214064,1048576,256,0,0,8,8,16,64,0x0,0x7ff7e8e1cec0,0,0,0,1410032651031889,1410043880710953,1410043880730153,1410032651198643 diff --git a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv index 6a831ec11a..0ada745a3a 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118567,118567,1048576,256,0,0,8,8,16,64,0x0,0x7f7400394e80,65536,197034,25247432,194105416376991,194116676571166,194116676595486,194105424085737 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118567,118567,1048576,256,0,0,8,8,16,64,0x0,0x7f7400394e80,65536,176914,22629536,194105424102449,194116676615646,194116676634206,194105424410733 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118567,118567,1048576,256,0,0,8,8,16,64,0x0,0x7f7400394e80,65536,184956,23691288,194105424438876,194116676727326,194116676746366,194105424602586 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1214265,1214265,1048576,256,0,0,8,8,16,64,0x0,0x7f50e1e68ec0,65536,190682,24383576,1410033122219622,1410043880547753,1410043880571433,1410033129789148 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1214265,1214265,1048576,256,0,0,8,8,16,64,0x0,0x7f50e1e68ec0,65536,193106,24683872,1410033129808855,1410043880671913,1410043880690633,1410033130371877 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1214265,1214265,1048576,256,0,0,8,8,16,64,0x0,0x7f50e1e68ec0,65536,163550,20955824,1410033130400381,1410043880710953,1410043880730153,1410033130545715 diff --git a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv index 1bea4b4a54..a7dfed1685 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118767,118767,1048576,256,0,0,8,8,16,64,0x0,0x7f979e936e80,32768,627003,80249452,194105910406296,194116676571166,194116676595486,194105918239688 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118767,118767,1048576,256,0,0,8,8,16,64,0x0,0x7f979e936e80,32768,682198,87324288,194105918259445,194116676615646,194116676634206,194105918569532 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118767,118767,1048576,256,0,0,8,8,16,64,0x0,0x7f979e936e80,32768,666672,85351124,194105918598307,194116676727326,194116676746366,194105918772246 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1214456,1214456,1048576,256,0,0,8,8,16,64,0x0,0x7f0a1e43cec0,32768,675489,86458540,1410033599911372,1410043880547753,1410043880571433,1410033607560017 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1214456,1214456,1048576,256,0,0,8,8,16,64,0x0,0x7f0a1e43cec0,32768,679151,86928408,1410033607581929,1410043880671913,1410043880690633,1410033607885631 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1214456,1214456,1048576,256,0,0,8,8,16,64,0x0,0x7f0a1e43cec0,32768,664085,85001528,1410033607913574,1410043880710953,1410043880730153,1410033608093323 diff --git a/tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv index 8a5ac79a6a..e00b984b61 100644 --- a/tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,118955,118955,1048576,256,0,0,8,8,16,64,0x0,0x7fa2db79ce80,47707,47707,16762,381664,16384,25174271,233099,0,101191452,194106398813286,194116676571166,194116676595486,194106406589529 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,118955,118955,1048576,256,0,0,8,8,16,64,0x0,0x7fa2db79ce80,43514,43514,14451,348120,16384,24820386,234052,0,99779440,194106406621440,194116676615646,194116676634206,194106406876623 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,118955,118955,1048576,256,0,0,8,8,16,64,0x0,0x7fa2db79ce80,42906,42906,13717,343256,16384,24906156,231361,0,100124212,194106406914885,194116676727326,194116676746366,194106407073626 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1214642,1214642,1048576,256,0,0,8,8,16,64,0x0,0x7f4d3d920ec0,48606,48606,18515,388856,16384,25509493,236741,0,102558484,1410034076804826,1410043880547753,1410043880571433,1410034084557548 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1214642,1214642,1048576,256,0,0,8,8,16,64,0x0,0x7f4d3d920ec0,42237,42237,13786,337904,16384,24173280,227954,0,97229236,1410034084587645,1410043880671913,1410043880690633,1410034084925772 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1214642,1214642,1048576,256,0,0,8,8,16,64,0x0,0x7f4d3d920ec0,42229,42229,12731,337840,16384,24017903,227475,0,96607268,1410034084963954,1410043880710953,1410043880730153,1410034085148072 diff --git a/tests/workloads/join_type_grid/MI100/log.txt b/tests/workloads/join_type_grid/MI100/log.txt new file mode 100644 index 0000000000..9a852afafa --- /dev/null +++ b/tests/workloads/join_type_grid/MI100/log.txt @@ -0,0 +1,679 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/join_type_grid/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155138' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155138_1213718' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155138_1213718/input0_results_240321_155138' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155138_1213718/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155138_1213718/input0_results_240321_155138 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155138' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155138_1213904' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155138_1213904/input0_results_240321_155138' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155138_1213904/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155138_1213904/input0_results_240321_155138 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155139' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155139_1214105' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155139_1214105/input0_results_240321_155139' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155139_1214105/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155139_1214105/input0_results_240321_155139 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155139' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155139_1214296' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155139_1214296/input0_results_240321_155139' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155139_1214296/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155139_1214296/input0_results_240321_155139 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155140' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155140_1214482' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155140_1214482/input0_results_240321_155140' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155140_1214482/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155140_1214482/input0_results_240321_155140 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155140' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155140_1214668' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155140_1214668/input0_results_240321_155140' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155140_1214668/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155140_1214668/input0_results_240321_155140 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155141' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155141_1214855' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155141_1214855/input0_results_240321_155141' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155141_1214855/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155141_1214855/input0_results_240321_155141 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155141' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155141_1215040' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155141_1215040/input0_results_240321_155141' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155141_1215040/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155141_1215040/input0_results_240321_155141 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155142' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155142_1215227' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155142_1215227/input0_results_240321_155142' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155142_1215227/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155142_1215227/input0_results_240321_155142 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155142' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155142_1215428' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155142_1215428/input0_results_240321_155142' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155142_1215428/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155142_1215428/input0_results_240321_155142 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155143' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155143_1215618' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155143_1215618/input0_results_240321_155143' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155143_1215618/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155143_1215618/input0_results_240321_155143 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155144' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155144_1215819' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155144_1215819/input0_results_240321_155144' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155144_1215819/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155144_1215819/input0_results_240321_155144 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155144' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155144_1216004' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155144_1216004/input0_results_240321_155144' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155144_1216004/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155144_1216004/input0_results_240321_155144 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155145' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155145_1216190' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155145_1216190/input0_results_240321_155145' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155145_1216190/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155145_1216190/input0_results_240321_155145 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155146' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155146_1216377' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155146_1216377/input0_results_240321_155146' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155146_1216377/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155146_1216377/input0_results_240321_155146 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155146' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155146_1216578' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155146_1216578/input0_results_240321_155146' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155146_1216578/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155146_1216578/input0_results_240321_155146 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155146' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155146_1216762' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155146_1216762/input0_results_240321_155146' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155146_1216762/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155146_1216762/input0_results_240321_155146 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155147' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155147_1216963' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155147_1216963/input0_results_240321_155147' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155147_1216963/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155147_1216963/input0_results_240321_155147 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155147' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155147_1217148' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155147_1217148/input0_results_240321_155147' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155147_1217148/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155147_1217148/input0_results_240321_155147 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155148' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155148_1217349' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155148_1217349/input0_results_240321_155148' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155148_1217349/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155148_1217349/input0_results_240321_155148 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155148' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155148_1217536' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155148_1217536/input0_results_240321_155148' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155148_1217536/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155148_1217536/input0_results_240321_155148 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155149' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155149_1217720' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155149_1217720/input0_results_240321_155149' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155149_1217720/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155149_1217720/input0_results_240321_155149 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155149' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155149_1217905' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155149_1217905/input0_results_240321_155149' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155149_1217905/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155149_1217905/input0_results_240321_155149 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/join_type_grid/MI100/pmc_dispatch_info.csv b/tests/workloads/join_type_grid/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/join_type_grid/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/join_type_grid/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/join_type_grid/MI100/pmc_perf.csv b/tests/workloads/join_type_grid/MI100/pmc_perf.csv index 412205a8d0..3d85c34a08 100644 --- a/tests/workloads/join_type_grid/MI100/pmc_perf.csv +++ b/tests/workloads/join_type_grid/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_4,obj_4,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_5,obj_5,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,TCC_EA_ATOMIC_LEVEL_sum,wave_size_10,obj_10,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_11,obj_11,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_12,obj_12,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_15,obj_15,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f69d2202e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131355.0,0.0,558.0,131354.0,64,0x7f80b7dcae80,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,0,48260,0,0,64,0x7f09074bce80,0,0,192,0,65536,64477,48,1361,30817,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,46993,1710,0,48.0,223.0,0.0,262288.0,64,0x7f1fbcc16e80,131072.0,131072.0,0.0,2401475.0,0.0,0.0,124242912.0,59220180.0,64,0x7f2339a40e80,211138,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13048,29432,9842,550,0,46317,262608.0,0.0,188.0,262420.0,64,0x7fde3c94ce80,1878775,360448,163840,0,0,180224,114688,0,69894909.0,180908813.0,65456755.0,131072.0,0.0,648298.0,0,0,25969,81303.0,0.0,0.0,81303.0,64,0x7f075536ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47188,0,131540.0,131072.0,0.0,131104.0,64,0x7f688fdc2e80,32768,0,0,0,16384,16384,393216,23122952,960.0,513926.0,0.0,524288.0,953338.0,32768.0,0,0,0,16936,131072.0,131072.0,0.0,131072.0,64,0x7f470fe8ae80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f958f3cce80,0.0,64,0x7f761c6b0e80,4096,0,1128,0,4096,0,2253,0,4099,0,846,0,4096,0,1305,0,4096,0,1406,0,4096,0,0,0,4096,0,1364,0,4096,0,0,0,4096,0,2488,0,4096,0,2211,0,4144,0,486,0,4096,0,2499,0,4096,0,946,0,4096,0,7089,0,4096,0,1682,0,4096,0,0,0,4096,0,4589,0,4096,0,3591,0,4097,0,1732,0,4096,0,399,0,4096,0,775,0,4096,0,829,0,4096,0,3663,0,4216,0,664,0,4096,0,5833,0,4096,0,4597,0,4096,0,461,0,4096,0,0,0,4096,0,4137,0,4096,0,90,0,4096,0,267,0,4144,0,0,0,64,0x7efdecf5ce80,0,4882666,4096,4096,0,4315012,4096,4096,0,4476841,4096,4096,0,3912802,4096,4096,0,3390103,4096,4096,0,4277346,4096,4096,0,3258684,4096,4096,0,4092835,4096,4096,0,4790502,4096,4096,0,3490827,4096,4096,0,3457748,4096,4096,0,3128836,4096,4096,0,4988102,4096,4096,0,3379177,4096,4096,0,3755354,4096,4096,0,2659601,4096,4096,0,3647878,4096,4096,0,5216862,4096,4096,0,5485276,4096,4096,0,2689073,4096,4096,0,4594790,4096,4096,0,4774406,4096,4096,0,3905553,4096,4096,0,2957427,4096,4096,0,3385873,4096,4096,0,3163970,4096,4096,0,3686859,4096,4096,0,3458076,4096,4096,0,4241359,4096,4096,0,4170003,4096,4096,0,3269196,4096,4096,0,4551421,4096,4096,64,0x7fa00b4cae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87115.0,43957.0,131111.0,0.0,64,0x7f472dd2ae80,387016,233630,3414217,16384,25158558,144,48,0,48376,48376,3857066.0,3030825.0,6946.0,1037678.0,2051107.0,0.0,3021647.0,2710059.0,385303,243554,48376,0,48376,0,1548032.0,967341.0,0.0,0.0,64,0x7fdea5c62e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,53693.0,119588.0,64,0x7f3cbdc46e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb120050e80,2027,0,0,1825912,3947,0,0,2070916,2144,0,0,1838162,3535,0,0,1974164,1942,0,0,1849379,1640,0,0,1769866,3008,0,0,1957094,2397,0,0,1977340,1128,0,0,1713467,1469,0,0,1836888,3938,0,0,2051117,2591,0,0,1896217,2505,0,0,1932320,1729,0,0,1820007,2338,0,0,1822817,1503,0,0,1773016,1467,0,0,1761135,1114,0,0,1722059,4956,0,0,2049123,2378,0,0,1895404,2957,0,0,1865355,2221,0,0,1865019,3188,0,0,1984519,3249,0,0,2007555,2504,0,0,1876894,950,0,0,1660382,6177,0,0,2201001,4101,0,0,2077845,2807,0,0,1934125,1518,0,0,1725891,3219,0,0,1961188,4664,0,0,2095589,194116676571166,194116676595486 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f69d2202e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131734.0,0.0,1322.0,131733.0,64,0x7f80b7dcae80,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,0,43420,0,0,64,0x7f09074bce80,0,0,48,0,65536,65536,0,0,30004,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41483,1756,0,48.0,203.0,0.0,262144.0,64,0x7f1fbcc16e80,131072.0,131072.0,0.0,2491310.0,0.0,0.0,109960527.0,37960389.0,64,0x7f2339a40e80,149423,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12371,28755,8597,2428,0,41184,262433.0,0.0,47.0,262386.0,64,0x7fde3c94ce80,1325503,360448,163840,0,0,180224,114688,0,69020920.0,179384934.0,67818306.0,131072.0,0.0,710902.0,0,0,25828,57573.0,0.0,0.0,57573.0,64,0x7f075536ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5588,44149,1078,131909.0,131072.0,0.0,93433.0,64,0x7f688fdc2e80,32768,0,0,0,16384,16384,393216,23551080,960.0,513993.0,0.0,524288.0,909914.0,32768.0,0,0,0,14511,86716.0,86716.0,0.0,86716.0,64,0x7f470fe8ae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f958f3cce80,0.0,64,0x7f761c6b0e80,4096,0,0,0,4096,0,322,0,4096,0,830,0,4096,0,197,0,4096,0,215,0,4096,0,754,0,4096,0,438,0,4098,0,280,0,4096,0,0,0,4096,0,800,0,4144,0,396,0,4097,0,8179,0,4096,0,444,0,4096,0,0,0,4096,0,995,0,4096,0,0,0,4096,0,689,0,4096,0,3183,0,4097,0,511,0,4096,0,991,0,4096,0,0,0,4096,0,91,0,4096,0,591,0,4216,0,433,0,4096,0,0,0,4097,0,484,0,4096,0,719,0,4096,0,0,0,4096,0,0,0,4096,0,433,0,4096,0,639,0,4144,0,363,0,64,0x7efdecf5ce80,0,4455261,2724,2724,0,2831778,2740,2740,0,3672359,2672,2672,0,3119734,2680,2680,0,4081614,2676,2676,0,2765774,2748,2748,0,3090099,2682,2682,0,4186396,2690,2690,0,4053287,2702,2702,0,3171033,2719,2719,0,2838616,2705,2705,0,4110556,2716,2716,0,4200362,2706,2706,0,3786327,2712,2712,0,3494750,2681,2681,0,3993452,2680,2680,0,4126363,2690,2690,0,3851237,2705,2705,0,3789524,2692,2692,0,3704780,2696,2696,0,4088835,2712,2712,0,4293048,2731,2731,0,3377943,2688,2688,0,3095349,2675,2675,0,4205647,2690,2690,0,5094923,2708,2708,0,3002549,2704,2704,0,3469424,2684,2684,0,3564544,2724,2724,0,3540920,2729,2729,0,4042738,2706,2706,0,3469019,2680,2680,64,0x7fa00b4cae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87290.0,0.0,131112.0,0.0,64,0x7f472dd2ae80,380584,231131,3348462,16384,23567267,0,48,0,47572,47572,3756915.0,3067444.0,6559.0,1220484.0,2078956.0,0.0,3057436.0,2746209.0,380576,240825,47572,0,47572,977,1522304.0,845079.0,0.0,0.0,64,0x7fdea5c62e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,76859.0,140552.0,64,0x7f3cbdc46e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8362,4266,8362,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb120050e80,3570,0,0,1696906,1757,0,0,1410916,3193,0,0,1609150,4152,0,0,1721417,5259,0,0,1830601,817,0,0,1283728,1483,0,0,1424629,725,0,0,1346660,1728,0,0,1370028,1952,0,0,1516038,838,0,0,1289218,1632,0,0,1458473,831,0,0,1221025,3727,0,0,1687681,893,0,0,1283193,2558,0,0,1587276,952,0,0,1324301,2099,0,0,1576361,2055,0,0,1518370,1295,0,0,1414906,1647,0,0,1344793,1541,0,0,1440963,4439,0,0,1730681,6584,0,0,1897334,1675,0,0,1452641,1550,0,0,1485876,2872,0,0,1651929,3836,0,0,1698706,1157,0,0,1349765,1936,0,0,1490784,2431,0,0,1558439,3806,0,0,1672864,194116676615646,194116676634206 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f69d2202e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131320.0,0.0,494.0,131319.0,64,0x7f80b7dcae80,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,0,43796,0,0,64,0x7f09074bce80,0,0,48,0,65536,65536,0,0,31039,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42457,1743,0,48.0,224.0,0.0,262144.0,64,0x7f1fbcc16e80,131072.0,131072.0,0.0,2347788.0,0.0,0.0,127170115.0,48008462.0,64,0x7f2339a40e80,185700,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,10428,26812,8524,2539,0,41029,262467.0,0.0,47.0,262420.0,64,0x7fde3c94ce80,1576509,360448,163840,0,0,180224,114688,0,71542653.0,190382994.0,68240330.0,131072.0,0.0,743773.0,0,0,25858,93202.0,0.0,0.0,93202.0,64,0x7f075536ce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2790,40033,0,131395.0,131072.0,0.0,86956.0,64,0x7f688fdc2e80,32768,0,0,0,16384,16384,393216,23274918,960.0,513912.0,0.0,524288.0,1037782.0,32768.0,0,0,0,13449,86514.0,86514.0,0.0,86514.0,64,0x7f470fe8ae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f958f3cce80,0.0,64,0x7f761c6b0e80,4096,0,1191,0,4096,0,699,0,4096,0,236,0,4096,0,0,0,4096,0,658,0,4096,0,206,0,4096,0,0,0,4098,0,1273,0,4096,0,1663,0,4096,0,13,0,4144,0,372,0,4097,0,1699,0,4096,0,756,0,4096,0,143,0,4096,0,1123,0,4096,0,0,0,4096,0,1637,0,4096,0,1970,0,4097,0,268,0,4096,0,145,0,4096,0,244,0,4096,0,7021,0,4096,0,0,0,4216,0,0,0,4096,0,1085,0,4097,0,162,0,4096,0,590,0,4096,0,117,0,4096,0,1504,0,4096,0,214,0,4096,0,18,0,4144,0,203,0,64,0x7efdecf5ce80,0,3789727,2708,2708,0,4145600,2707,2707,0,3932662,2656,2656,0,4125888,2696,2696,0,3594798,2698,2698,0,3494827,2740,2740,0,3307567,2714,2714,0,4032329,2708,2708,0,4479334,2704,2704,0,3967079,2704,2704,0,3573241,2688,2688,0,4158832,2736,2736,0,3510227,2706,2706,0,4272727,2708,2708,0,3662961,2674,2674,0,4262311,2674,2674,0,4833370,2697,2697,0,3906428,2713,2713,0,3977740,2696,2696,0,4376696,2708,2708,0,4824920,2712,2712,0,4923431,2748,2748,0,3385540,2696,2696,0,4625894,2692,2692,0,3513986,2704,2704,0,4125405,2689,2689,0,3506967,2742,2742,0,3174388,2678,2678,0,3730756,2734,2734,0,4871593,2685,2685,0,3710968,2724,2724,0,3475452,2696,2696,64,0x7fa00b4cae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86695.0,0.0,131112.0,0.0,64,0x7f472dd2ae80,334496,224843,3296742,16384,24356490,0,48,0,41811,41811,3662176.0,3009269.0,5876.0,991004.0,2061252.0,0.0,3000693.0,2689802.0,334488,234109,41811,0,41811,0,1337952.0,790729.0,0.0,0.0,64,0x7fdea5c62e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,59427.0,126090.0,64,0x7f3cbdc46e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8372,4276,8372,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb120050e80,4247,0,0,1679600,3503,0,0,1582477,3308,0,0,1631995,4362,0,0,1696865,4815,0,0,1710487,1461,0,0,1432848,2807,0,0,1607771,2642,0,0,1570268,885,0,0,1218049,1403,0,0,1400418,5220,0,0,1805574,2701,0,0,1662686,2361,0,0,1529643,1249,0,0,1404184,1528,0,0,1525621,717,0,0,1342620,2102,0,0,1455186,561,0,0,1217845,3764,0,0,1638630,1359,0,0,1404365,1478,0,0,1415279,2509,0,0,1507952,6369,0,0,1756437,7466,0,0,1902456,2341,0,0,1428084,1435,0,0,1340307,4209,0,0,1708167,5138,0,0,1712099,2524,0,0,1507465,1449,0,0,1389305,2328,0,0,1522256,297,0,0,1275174,194116676727326,194116676746366 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_2,obj_2,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_3,obj_3,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_6,obj_6,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_7,obj_7,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_8,obj_8,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_9,obj_9,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_10,obj_10,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_11,obj_11,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_12,obj_12,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_13,obj_13,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_15,obj_15,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_16,obj_16,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fa2f020cec0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,0,48628,0,0,64,0x7f0b1d5c0ec0,387856,233906,3374490,16384,24370130,144,48,0,48481,48481,3860694.0,2975183.0,6165.0,1091112.0,2241183.0,0.0,2965665.0,2655767.0,386207,243832,48481,0,48481,0,1551392.0,976350.0,0.0,0.0,64,0x7f10e0890ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,37722.0,141066.0,64,0x7f4fe7e54ec0,2596,0,0,1920666,3998,0,0,1993819,1505,0,0,1744505,3710,0,0,1988644,1571,0,0,1785186,1008,0,0,1670834,5327,0,0,2099529,3835,0,0,2041258,1824,0,0,1782524,3897,0,0,2075271,2314,0,0,1907781,2831,0,0,1962240,3586,0,0,2091443,904,0,0,1673288,2052,0,0,1828199,5438,0,0,2107787,3108,0,0,2002182,653,0,0,1626525,5393,0,0,2235969,3468,0,0,2024579,2241,0,0,1945184,1682,0,0,1877801,2865,0,0,2002588,5039,0,0,2071946,4047,0,0,1997989,777,0,0,1569504,1962,0,0,1897381,4628,0,0,2085344,5299,0,0,2239190,1810,0,0,1803965,2238,0,0,1886480,2173,0,0,1752483,64,0x7f8dda0dcec0,0,4553748,4096,4096,0,3935210,4096,4096,0,4123427,4096,4096,0,3308748,4096,4096,0,3637521,4096,4096,0,3837877,4096,4096,0,3436914,4096,4096,0,3005704,4096,4096,0,3357678,4096,4096,0,4814190,4096,4096,0,3955686,4096,4096,0,4328718,4096,4096,0,5000747,4096,4096,0,3160727,4096,4096,0,3702502,4096,4096,0,3525628,4096,4096,0,3633130,4096,4096,0,5066339,4096,4096,0,3431858,4096,4096,0,2858686,4096,4096,0,3816638,4096,4096,0,3590146,4096,4096,0,4842859,4096,4096,0,3777629,4096,4096,0,4275761,4096,4096,0,4615836,4096,4096,0,3218819,4096,4096,0,3630281,4096,4096,0,3477226,4096,4096,0,2796788,4096,4096,0,3171007,4096,4096,0,4105809,4096,4096,64,0x7faea3078ec0,32768,0,0,0,16384,16384,393216,23076277,960.0,513832.0,0.0,524288.0,1052632.0,32768.0,0,0,0,17076,131072.0,131072.0,0.0,131072.0,64,0x7f8e08378ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86332.0,44740.0,131111.0,0.0,64,0x7f9272670ec0,0,0,192,0,65536,64446,48,1329,32479,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48693,2071,0,48.0,221.0,0.0,262288.0,64,0x7f2275a94ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46542,0,131437.0,131072.0,0.0,131104.0,64,0x7fc2a9978ec0,186293,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13226,29610,10015,588,0,45618,262726.0,0.0,188.0,262538.0,64,0x7f20c2a0cec0,131072.0,131072.0,0.0,2617060.0,0.0,0.0,104089552.0,56680554.0,64,0x7f717de90ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f88b7f60ec0,4096,0,4412,0,4096,0,0,0,4096,0,6915,0,4099,0,26,0,4096,0,65,0,4096,0,2533,0,4096,0,1240,0,4096,0,919,0,4096,0,450,0,4096,0,4006,0,4096,0,765,0,4144,0,4517,0,4096,0,861,0,4096,0,1153,0,4096,0,1406,0,4096,0,817,0,4290,0,84,0,4096,0,2309,0,4096,0,2675,0,4096,0,935,0,4096,0,1841,0,4096,0,604,0,4096,0,71,0,4096,0,491,0,4096,0,1952,0,4096,0,5970,0,4096,0,1048,0,4097,0,242,0,4096,0,0,0,4096,0,1179,0,4216,0,1170,0,4096,0,1038,0,64,0x7f7126cd8ec0,0.0,64,0x7f25802f4ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131354.0,0.0,556.0,131353.0,64,0x7fedf7bb8ec0,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8557,4461,8557,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f32fa48cec0,2800390,360448,163840,0,0,180224,114688,0,64963625.0,172781180.0,71964449.0,131072.0,0.0,694332.0,0,0,26632,96652.0,0.0,0.0,96652.0,1410043880547753,1410043880571433 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fa2f020cec0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,0,42735,0,0,64,0x7f0b1d5c0ec0,340440,231228,3344763,16384,23662160,0,48,0,42554,42554,3757552.0,3044857.0,5838.0,1048114.0,2275913.0,0.0,3035638.0,2725764.0,340432,240559,42554,0,42554,0,1361728.0,833756.0,0.0,0.0,64,0x7f10e0890ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,12411.0,76865.0,64,0x7f4fe7e54ec0,1589,0,0,1466077,391,0,0,1297503,2912,0,0,1518078,1696,0,0,1431032,1220,0,0,1333642,162,0,0,1198131,5591,0,0,1758462,1852,0,0,1449298,300,0,0,1202230,1041,0,0,1362443,1900,0,0,1518765,1445,0,0,1479992,1279,0,0,1410440,2705,0,0,1640073,354,0,0,1206858,1276,0,0,1415523,4408,0,0,1732039,860,0,0,1377041,2861,0,0,1569919,2267,0,0,1545719,1225,0,0,1376659,1828,0,0,1487711,1371,0,0,1343322,453,0,0,1238913,1456,0,0,1416508,179,0,0,1158028,3410,0,0,1623538,2556,0,0,1578735,1172,0,0,1385559,2861,0,0,1593236,3575,0,0,1608803,2198,0,0,1501322,64,0x7f8dda0dcec0,0,2631526,2708,2708,0,3043522,2691,2691,0,4948046,2684,2684,0,2984528,2735,2735,0,2431253,2692,2692,0,2987057,2716,2716,0,4306489,2764,2764,0,3345013,2730,2730,0,3353066,2730,2730,0,3212291,2680,2680,0,2976986,2724,2724,0,3764986,2740,2740,0,2632221,2704,2704,0,3195176,2709,2709,0,3427224,2704,2704,0,2744365,2742,2742,0,2901920,2724,2724,0,4286291,2680,2680,0,3071791,2702,2702,0,4571270,2736,2736,0,3407221,2736,2736,0,3473385,2746,2746,0,4871415,2731,2731,0,2703699,2692,2692,0,2746395,2696,2696,0,2605233,2694,2694,0,3537128,2760,2760,0,2847686,2736,2736,0,2578636,2724,2724,0,2459025,2685,2685,0,5242075,2730,2730,0,3767934,2740,2740,64,0x7faea3078ec0,32768,0,0,0,16384,16384,393216,22807856,960.0,514036.0,0.0,524288.0,933501.0,32768.0,0,0,0,13963,86519.0,86519.0,0.0,86519.0,64,0x7f8e08378ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86564.0,44508.0,131111.0,0.0,64,0x7f9272670ec0,0,0,48,0,65536,65536,0,0,30529,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41986,1790,0,48.0,281.0,0.0,262144.0,64,0x7f2275a94ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5763,43220,1037,131772.0,131072.0,0.0,89861.0,64,0x7fc2a9978ec0,185949,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14213,30597,8562,2350,0,40991,262652.0,0.0,47.0,262605.0,64,0x7f20c2a0cec0,131072.0,131072.0,0.0,2606492.0,0.0,0.0,127434728.0,45650813.0,64,0x7f717de90ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f88b7f60ec0,4096,0,2113,0,4096,0,3187,0,4096,0,140,0,4096,0,559,0,4096,0,1804,0,4098,0,1233,0,4096,0,1155,0,4096,0,3902,0,4096,0,431,0,4096,0,1958,0,4096,0,7176,0,4145,0,4881,0,4096,0,222,0,4096,0,2198,0,4096,0,1519,0,4096,0,488,0,4280,0,3569,0,4096,0,2424,0,4096,0,0,0,4096,0,1136,0,4096,0,0,0,4097,0,2229,0,4096,0,485,0,4096,0,5740,0,4096,0,1815,0,4096,0,1070,0,4096,0,2058,0,4097,0,52,0,4096,0,16,0,4096,0,3585,0,4216,0,357,0,4096,0,1277,0,64,0x7f7126cd8ec0,0.0,64,0x7f25802f4ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131339.0,0.0,532.0,131338.0,64,0x7fedf7bb8ec0,0,8193,4097,8193,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8531,4435,8531,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f32fa48cec0,1780143,360448,163840,0,0,180224,114688,0,67063887.0,198896890.0,80345984.0,131072.0,0.0,766513.0,0,0,25952,101088.0,0.0,0.0,101088.0,1410043880671913,1410043880690633 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fa2f020cec0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,0,42879,0,0,64,0x7f0b1d5c0ec0,338792,228551,3266420,16384,23422148,0,48,0,42348,42348,3717386.0,2970053.0,5306.0,1029527.0,2277272.0,0.0,2960729.0,2651645.0,338784,237941,42348,0,42348,0,1355136.0,831919.0,0.0,0.0,64,0x7f10e0890ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,44883.0,130999.0,64,0x7f4fe7e54ec0,1328,0,0,1430248,3138,0,0,1554519,1742,0,0,1440438,5395,0,0,1723120,952,0,0,1311348,406,0,0,1229473,4211,0,0,1699956,3423,0,0,1603151,800,0,0,1315234,1967,0,0,1502283,334,0,0,1257267,4687,0,0,1761098,2344,0,0,1521343,1192,0,0,1424958,973,0,0,1313990,3449,0,0,1601322,768,0,0,1351911,3500,0,0,1697077,919,0,0,1332810,6708,0,0,1886682,1221,0,0,1397425,1474,0,0,1402669,1555,0,0,1458858,872,0,0,1256811,3817,0,0,1580278,2427,0,0,1507681,919,0,0,1340066,4532,0,0,1681841,1369,0,0,1295302,2727,0,0,1520456,1466,0,0,1297059,5319,0,0,1769343,64,0x7f8dda0dcec0,0,3568188,2717,2717,0,3079688,2698,2698,0,3728704,2663,2663,0,3916770,2704,2704,0,3756727,2698,2698,0,3133000,2712,2712,0,2582699,2680,2680,0,3238757,2726,2726,0,3921116,2708,2708,0,5074509,2694,2694,0,3134748,2688,2688,0,2865464,2736,2736,0,3855562,2708,2708,0,3048564,2692,2692,0,3532746,2664,2664,0,2793430,2702,2702,0,3153737,2712,2712,0,4910109,2698,2698,0,3888085,2670,2670,0,2821427,2736,2736,0,4557082,2714,2714,0,4086209,2750,2750,0,2607415,2655,2655,0,2775255,2708,2708,0,3197716,2712,2712,0,3541884,2680,2680,0,3560715,2704,2704,0,3552495,2692,2692,0,3071250,2714,2714,0,3438107,2698,2698,0,3897589,2713,2713,0,2953056,2724,2724,64,0x7faea3078ec0,32768,0,0,0,16384,16384,393216,23044759,960.0,513971.0,0.0,524288.0,936848.0,32768.0,0,0,0,15071,86622.0,86622.0,0.0,86622.0,64,0x7f8e08378ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86449.0,0.0,131112.0,0.0,64,0x7f9272670ec0,0,0,48,0,65536,65536,0,0,30017,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41882,1806,0,48.0,226.0,0.0,262144.0,64,0x7f2275a94ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2783,39456,0,131303.0,131072.0,0.0,87039.0,64,0x7fc2a9978ec0,170265,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,15912,32296,8592,2437,0,41867,262656.0,0.0,47.0,262609.0,64,0x7f20c2a0cec0,131072.0,131072.0,0.0,2563820.0,0.0,0.0,128549786.0,47675231.0,64,0x7f717de90ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f88b7f60ec0,4096,0,1806,0,4096,0,336,0,4096,0,3688,0,4096,0,129,0,4096,0,280,0,4098,0,881,0,4096,0,406,0,4096,0,1788,0,4096,0,1430,0,4096,0,1469,0,4096,0,2350,0,4145,0,7051,0,4096,0,1792,0,4096,0,1968,0,4096,0,377,0,4096,0,654,0,4298,0,5743,0,4096,0,1528,0,4096,0,719,0,4096,0,919,0,4096,0,412,0,4097,0,3561,0,4096,0,476,0,4096,0,0,0,4096,0,470,0,4096,0,4717,0,4096,0,1025,0,4097,0,1142,0,4096,0,727,0,4096,0,591,0,4216,0,3790,0,4096,0,598,0,64,0x7f7126cd8ec0,0.0,64,0x7f25802f4ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131365.0,0.0,584.0,131364.0,64,0x7fedf7bb8ec0,0,8193,4097,8193,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8485,4389,8485,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f32fa48cec0,3483635,360448,163840,0,0,180224,114688,0,56278793.0,150993659.0,58733657.0,131072.0,0.0,824610.0,0,0,26238,74319.0,0.0,0.0,74319.0,1410043880710953,1410043880730153 diff --git a/tests/workloads/join_type_grid/MI100/sysinfo.csv b/tests/workloads/join_type_grid/MI100/sysinfo.csv index 2d0391f20a..01041b7128 100644 --- a/tests/workloads/join_type_grid/MI100/sysinfo.csv +++ b/tests/workloads/join_type_grid/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -join_type_grid,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:06:09 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +join_type_grid,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:51:37 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/join_type_grid/MI100/timestamps.csv b/tests/workloads/join_type_grid/MI100/timestamps.csv index 82c5599f3f..98141b8b3e 100644 --- a/tests/workloads/join_type_grid/MI100/timestamps.csv +++ b/tests/workloads/join_type_grid/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,122400,122400,1048576,256,0,0,8,8,16,64,0x0,0x7f4349e02e80,194116676544295,194116676571166,194116676595486,194116676616381 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,122400,122400,1048576,256,0,0,8,8,16,64,0x0,0x7f4349e02e80,194116676607995,194116676615646,194116676634206,194116676725127 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,122400,122400,1048576,256,0,0,8,8,16,64,0x0,0x7f4349e02e80,194116676645276,194116676727326,194116676746366,194116676747299 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1218065,1218065,1048576,256,0,0,8,8,16,64,0x0,0x7f22c1320ec0,1410043880523173,1410043880547753,1410043880571433,1410043880583947 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1218065,1218065,1048576,256,0,0,8,8,16,64,0x0,0x7f22c1320ec0,1410043880584238,1410043880671913,1410043880690633,1410043880692542 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1218065,1218065,1048576,256,0,0,8,8,16,64,0x0,0x7f22c1320ec0,1410043880702922,1410043880710953,1410043880730153,1410043880731556 diff --git a/tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv index ab02c81f08..5e60808d4a 100644 --- a/tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,268795,268795,1048576,256,0,0,8,0,16,64,0x0,0x7f3875f94ec0,27374,27374,16384,65536,13435,1482776,197831630573234,197844341953097,197844341974057,197831646365049 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,268795,268795,1048576,256,0,0,8,0,16,64,0x0,0x7f3875f94ec0,41961,41961,16384,65536,9034,1048676,197831646388163,197844342059817,197844342076617,197831646690244 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,268795,268795,1048576,256,0,0,8,0,16,64,0x0,0x7f3875f94ec0,40396,40396,16384,65536,9362,1048708,197831646720141,197844342096937,197844342112777,197831646881486 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4092205,4092205,1048576,256,0,0,8,0,16,64,0x0,0x7fe75c9d8ec0,27928,27928,16384,65536,18635,2082112,1411316888050703,1411329731616837,1411329731637157,1411316904365136 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4092205,4092205,1048576,256,0,0,8,0,16,64,0x0,0x7fe75c9d8ec0,41424,41424,16384,65536,9552,1048796,1411316904386446,1411329731745477,1411329731761797,1411316904686303 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4092205,4092205,1048576,256,0,0,8,0,16,64,0x0,0x7fe75c9d8ec0,42048,42048,16384,65536,9388,1048624,1411316904715488,1411329731781797,1411329731797477,1411316904873577 diff --git a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv index 320769e4f3..ded7bb5122 100644 --- a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,268979,268979,1048576,256,0,0,8,0,16,64,0x0,0x7f6a88b28ec0,0,0,0,197832117662258,197844341953097,197844341974057,197832133615228 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,268979,268979,1048576,256,0,0,8,0,16,64,0x0,0x7f6a88b28ec0,0,0,0,197832133634524,197844342059817,197844342076617,197832133945623 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,268979,268979,1048576,256,0,0,8,0,16,64,0x0,0x7f6a88b28ec0,0,0,0,197832133972123,197844342096937,197844342112777,197832134122668 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4092406,4092406,1048576,256,0,0,8,0,16,64,0x0,0x7f98d4500ec0,0,0,0,1411317380912498,1411329731616837,1411329731637157,1411317397019218 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4092406,4092406,1048576,256,0,0,8,0,16,64,0x0,0x7f98d4500ec0,0,0,0,1411317397036691,1411329731745477,1411329731761797,1411317397351677 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4092406,4092406,1048576,256,0,0,8,0,16,64,0x0,0x7f98d4500ec0,0,0,0,1411317397377886,1411329731781797,1411329731797477,1411317397538921 diff --git a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv index cd375daec3..a687a5c944 100644 --- a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,269164,269164,1048576,256,0,0,8,0,16,64,0x0,0x7f70c5ab0ec0,65536,172876,19306104,197832602591055,197844341953097,197844341974057,197832618916540 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,269164,269164,1048576,256,0,0,8,0,16,64,0x0,0x7f70c5ab0ec0,65536,225082,25263696,197832618933692,197844342059817,197844342076617,197832619241725 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,269164,269164,1048576,256,0,0,8,0,16,64,0x0,0x7f70c5ab0ec0,65536,223104,25083768,197832619268415,197844342096937,197844342112777,197832619429540 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4092589,4092589,1048576,256,0,0,8,0,16,64,0x0,0x7fc1e3628ec0,65536,176480,19776656,1411317862649815,1411329731616837,1411329731637157,1411317878651136 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4092589,4092589,1048576,256,0,0,8,0,16,64,0x0,0x7fc1e3628ec0,65536,233008,25843376,1411317878669250,1411329731745477,1411329731761797,1411317878963086 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4092589,4092589,1048576,256,0,0,8,0,16,64,0x0,0x7fc1e3628ec0,65536,234036,26272640,1411317878989245,1411329731781797,1411329731797477,1411317879144699 diff --git a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv index dc5d376a15..6a731e549b 100644 --- a/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,269364,269364,1048576,256,0,0,8,0,16,64,0x0,0x7f8ebb654ec0,32768,293577,32894296,197833079703706,197844341953097,197844341974057,197833095734944 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,269364,269364,1048576,256,0,0,8,0,16,64,0x0,0x7f8ebb654ec0,32768,595549,66696720,197833095754490,197844342059817,197844342076617,197833096028789 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,269364,269364,1048576,256,0,0,8,0,16,64,0x0,0x7f8ebb654ec0,32768,591031,66199820,197833096054588,197844342096937,197844342112777,197833096222225 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4092781,4092781,1048576,256,0,0,8,0,16,64,0x0,0x7fb2ce1c8ec0,32768,300825,33684916,1411318342773120,1411329731616837,1411329731637157,1411318358895730 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4092781,4092781,1048576,256,0,0,8,0,16,64,0x0,0x7fb2ce1c8ec0,32768,581847,65163140,1411318358913414,1411329731745477,1411329731761797,1411318359233669 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4092781,4092781,1048576,256,0,0,8,0,16,64,0x0,0x7fb2ce1c8ec0,32768,586252,65640768,1411318359260229,1411329731781797,1411329731797477,1411318359423198 diff --git a/tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv index 154bd95d72..1ba03d9017 100644 --- a/tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,269547,269547,1048576,256,0,0,8,0,16,64,0x0,0x7f01b4c28ec0,27994,27994,11084,223960,16384,11107366,131595,0,44938912,197833559590174,197844341953097,197844341974057,197833575321725 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,269547,269547,1048576,256,0,0,8,0,16,64,0x0,0x7f01b4c28ec0,41763,41763,13589,334112,16384,19618427,225469,0,78963024,197833575346992,197844342059817,197844342076617,197833575660425 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,269547,269547,1048576,256,0,0,8,0,16,64,0x0,0x7f01b4c28ec0,41696,41696,13755,333576,16384,19502404,225614,0,78488224,197833575695722,197844342096937,197844342112777,197833575860744 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4092974,4092974,1048576,256,0,0,8,0,16,64,0x0,0x7f326b010ec0,28409,28409,11350,227280,16384,11148766,132571,0,45089732,1411318827739634,1411329731616837,1411329731637157,1411318843920965 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4092974,4092974,1048576,256,0,0,8,0,16,64,0x0,0x7f326b010ec0,40502,40502,12672,324024,16384,19573406,223593,0,78781376,1411318843948948,1411329731745477,1411329731761797,1411318844259285 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4092974,4092974,1048576,256,0,0,8,0,16,64,0x0,0x7f326b010ec0,40806,40806,12733,326456,16384,19791162,227017,0,79638076,1411318844294592,1411329731781797,1411329731797477,1411318844465124 diff --git a/tests/workloads/join_type_grid/MI200/log.txt b/tests/workloads/join_type_grid/MI200/log.txt new file mode 100644 index 0000000000..9482eb105a --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/log.txt @@ -0,0 +1,739 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/join_type_grid/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_161304' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161304_4092045' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161304_4092045/input0_results_240321_161304' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161304_4092045/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161304_4092045/input0_results_240321_161304 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_161305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161305_4092246' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161305_4092246/input0_results_240321_161305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161305_4092246/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161305_4092246/input0_results_240321_161305 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_161305' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161305_4092429' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161305_4092429/input0_results_240321_161305' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161305_4092429/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161305_4092429/input0_results_240321_161305 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_161306' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161306_4092621' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161306_4092621/input0_results_240321_161306' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161306_4092621/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161306_4092621/input0_results_240321_161306 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_161306' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161306_4092814' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161306_4092814/input0_results_240321_161306' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161306_4092814/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161306_4092814/input0_results_240321_161306 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_161307' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161307_4093002' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161307_4093002/input0_results_240321_161307' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161307_4093002/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161307_4093002/input0_results_240321_161307 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_161307' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161307_4093186' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161307_4093186/input0_results_240321_161307' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161307_4093186/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161307_4093186/input0_results_240321_161307 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_161308' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161308_4093378' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161308_4093378/input0_results_240321_161308' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161308_4093378/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161308_4093378/input0_results_240321_161308 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_161308' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161308_4093585' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161308_4093585/input0_results_240321_161308' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161308_4093585/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161308_4093585/input0_results_240321_161308 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_161309' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161309_4093792' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161309_4093792/input0_results_240321_161309' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161309_4093792/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161309_4093792/input0_results_240321_161309 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_161309' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161309_4093985' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161309_4093985/input0_results_240321_161309' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161309_4093985/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161309_4093985/input0_results_240321_161309 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_161310' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161310_4094173' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161310_4094173/input0_results_240321_161310' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161310_4094173/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161310_4094173/input0_results_240321_161310 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_161310' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161310_4094366' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161310_4094366/input0_results_240321_161310' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161310_4094366/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161310_4094366/input0_results_240321_161310 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_161311' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161311_4094568' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161311_4094568/input0_results_240321_161311' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161311_4094568/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161311_4094568/input0_results_240321_161311 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_161312' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161312_4094752' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161312_4094752/input0_results_240321_161312' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161312_4094752/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161312_4094752/input0_results_240321_161312 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_161313' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161313_4094953' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161313_4094953/input0_results_240321_161313' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161313_4094953/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161313_4094953/input0_results_240321_161313 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_161313' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161313_4095154' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161313_4095154/input0_results_240321_161313' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161313_4095154/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161313_4095154/input0_results_240321_161313 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_161314' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161314_4095358' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161314_4095358/input0_results_240321_161314' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161314_4095358/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161314_4095358/input0_results_240321_161314 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_161314' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161314_4095556' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161314_4095556/input0_results_240321_161314' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161314_4095556/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161314_4095556/input0_results_240321_161314 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_161315' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161315_4095740' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161315_4095740/input0_results_240321_161315' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161315_4095740/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161315_4095740/input0_results_240321_161315 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_161315' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161315_4095925' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161315_4095925/input0_results_240321_161315' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161315_4095925/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161315_4095925/input0_results_240321_161315 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_161316' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161316_4096109' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161316_4096109/input0_results_240321_161316' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161316_4096109/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161316_4096109/input0_results_240321_161316 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_161316' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161316_4096292' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161316_4096292/input0_results_240321_161316' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161316_4096292/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161316_4096292/input0_results_240321_161316 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_161317' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161317_4096493' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161317_4096493/input0_results_240321_161317' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161317_4096493/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161317_4096493/input0_results_240321_161317 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_grid/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_161317' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_grid/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161317_4096679' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161317_4096679/input0_results_240321_161317' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161317_4096679/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161317_4096679/input0_results_240321_161317 + |-> [rocprof] File 'tests/workloads/join_type_grid/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/join_type_grid/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/join_type_grid/MI200/pmc_dispatch_info.csv b/tests/workloads/join_type_grid/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/join_type_grid/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/join_type_grid/MI200/pmc_perf.csv b/tests/workloads/join_type_grid/MI200/pmc_perf.csv index 4aad1beca8..8643ddb8b7 100644 --- a/tests/workloads/join_type_grid/MI200/pmc_perf.csv +++ b/tests/workloads/join_type_grid/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_1,obj_1,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_5,obj_5,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_6,obj_6,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_12,obj_12,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_13,obj_13,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_16,obj_16,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_17,obj_17,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_18,obj_18,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8219bd4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,33301.0,46111.0,19425.0,64,0x7fb8b6fd4ec0,2229,4096,2229,6325,2294,4096,2294,6390,2285,4101,2290,6386,2290,4096,2290,6386,2237,4096,2237,6333,2293,4096,2293,6389,2277,4096,2277,6373,2296,4096,2296,6392,2298,4096,2298,6394,2232,4096,2232,6328,2293,4096,2293,6389,2287,4096,2287,6383,2288,4096,2288,6384,2240,4096,2240,6336,2298,4097,2299,6395,2276,4096,2276,6372,2282,4096,2282,6378,2316,4097,2317,6413,2269,4097,2270,6366,2271,4096,2271,6367,2275,4096,2275,6371,2287,4096,2287,6383,2279,4096,2279,6375,2452,4098,2454,6550,2285,4096,2285,6381,2283,4096,2283,6379,2267,4096,2267,6363,2271,4096,2271,6367,2270,4096,2270,6366,2277,4096,2277,6373,2291,4096,2291,6387,2277,4096,2277,6373,64,0x7f28659a0ec0,32768,32768,0,64,0x7f67610acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13364,18796,8402,545,0,27442,203985.0,0.0,72905.0,131080.0,64,0x7f7390f20ec0,114688,0,32768,32768,16384,16384,65536,49152,27600530.0,88074395.0,39774833.0,131072.0,0.0,226745.0,0,0,15332,2099.0,131084.0,0.0,16.0,64,0x7ffa3c3e8ec0,10662847,9620852,697931,344064,1605485,0,0,163840,832.0,515136.0,0.0,524288.0,270332.0,32768.0,465143,0,0,11101,131072.0,131072.0,0.0,131072.0,64,0x7fa841cb8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10188,0,818,28498,0,73091.0,131072.0,0.0,65571.0,64,0x7feaf8264ec0,0,0,0,1010297,0,0,0,1205994,0,0,0,965878,0,0,0,1072759,123,0,0,1161639,0,0,0,1124670,0,0,0,993668,0,0,0,1119435,0,0,0,993244,0,0,0,992961,0,0,0,1137637,0,0,0,1078361,0,0,0,996449,0,0,0,1108712,306,0,0,1309156,0,0,0,1092686,0,0,0,1161945,0,0,0,1146745,0,0,0,1091460,0,0,0,1150877,0,0,0,1016505,0,0,0,1134661,0,0,0,1099405,0,0,0,1193689,0,0,0,1128075,0,0,0,1015156,0,0,0,1076809,0,0,0,1209301,0,0,0,1111766,0,0,0,1117718,0,0,0,1045141,0,0,0,1104540,64,0x7f4c38760ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41282079.0,35751621.0,0.0,64,0x7f34e1488ec0,4096,0,0,0,4096,0,0,0,4096,0,298,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,12,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,116,0,64,0x7fd4443e8ec0,231088,129063,16384,0,16384,16384,32768,49152,28885,28885,1955608.0,1373203.0,3754.0,165838.0,1069114.0,0.0,1364828.0,1065832.0,229377,137184,28885,0,28885,0,924320.0,493058.0,0.0,0.0,64,0x7f596a470ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,924928.0,64,0x7f12afa38ec0,1284,115449,0,0,65536,63800,56,1680,64,0x7efd09584ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f499dd68ec0,6382,0,4096,6404,0,4096,6357,0,4096,6364,0,4096,6368,0,4096,6355,0,4096,6325,0,4096,6376,0,4096,6376,0,4096,6384,0,4096,6405,0,4096,6362,0,4096,6364,0,4096,6373,0,4096,6361,0,4096,6326,0,4096,6397,0,4096,6361,0,4096,6354,0,4096,6377,0,4096,6372,0,4096,6423,0,4096,6348,0,4096,6572,0,4096,6410,0,4096,6398,0,4096,6364,0,4096,6354,0,4096,6373,0,4096,6374,0,4096,6419,0,4096,6352,0,4096,64,0x7f0e35368ec0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,0,27304,0,0,64,0x7f7222850ec0,0,0,0,224,0,65536,64210,56,64,0x7fc809a60ec0,0,1222409,4096,4096,0,1302727,4096,4096,0,1356041,4096,4096,0,1334083,4096,4096,0,1271855,4096,4096,0,1504049,4096,4096,0,1130210,4096,4096,0,1307177,4096,4096,0,1220555,4096,4096,0,1114533,4096,4096,0,1208079,4096,4096,0,1233047,4096,4096,0,1374161,4096,4096,0,1335796,4096,4096,0,1197253,4096,4096,0,1352839,4096,4096,0,1255753,4096,4096,0,1316838,4096,4096,0,1091375,4096,4096,0,1539189,4096,4096,0,1300862,4096,4096,0,1247546,4096,4096,0,1316370,4096,4096,0,1182013,4096,4096,0,1396198,4096,4096,0,1207880,4096,4096,0,1211839,4096,4096,0,1179703,4096,4096,0,1160592,4096,4096,0,1261145,4096,4096,0,1121675,4096,4096,0,1384759,4096,4096,64,0x7f33184f8ec0,0,393216,163840,0,0,0,0,0,17516,0.0,0.0,0.0,32768.0,0.0,0.0,399.0,32768.0,4096,16384,352,28026,2157,0,56.0,5.0,0.0,204159.0,197844341953097,197844341974057 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8219bd4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,99055.0,45546.0,0.0,64,0x7fb8b6fd4ec0,2156,4096,2156,6252,2142,4096,2142,6238,2135,4101,2140,6236,2142,4096,2142,6238,2145,4096,2145,6241,2159,4096,2159,6255,2149,4096,2149,6245,2158,4096,2158,6254,2164,4096,2164,6260,2153,4096,2153,6249,2141,4096,2141,6237,2139,4096,2139,6235,2142,4096,2142,6238,2145,4096,2145,6241,2156,4097,2157,6253,2149,4096,2149,6245,2154,4097,2155,6251,2230,4097,2231,6327,2141,4097,2142,6238,2148,4096,2148,6244,2148,4096,2148,6244,2154,4098,2156,6252,2167,4096,2167,6263,2165,4096,2165,6261,2165,4096,2165,6261,2155,4096,2155,6251,2174,4096,2174,6270,2144,4096,2144,6240,2147,4096,2147,6243,2150,4096,2150,6246,2153,4096,2153,6249,2174,4096,2174,6270,64,0x7f28659a0ec0,32768,32768,0,64,0x7f67610acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27332,27234,8880,550,0,35961,200365.0,0.0,69290.0,131075.0,64,0x7f7390f20ec0,114688,0,32768,32768,16384,16384,65536,49152,58908740.0,201592118.0,44567153.0,131072.0,0.0,568390.0,0,0,25658,5211.0,131085.0,0.0,24.0,64,0x7ffa3c3e8ec0,19391063,17952502,1094497,344064,2791220,0,0,163840,832.0,515136.0,0.0,524288.0,640095.0,32768.0,1022544,0,0,14126,91208.0,91208.0,0.0,91208.0,64,0x7fa841cb8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,23172,0,3579,39602,0,69614.0,131072.0,0.0,45643.0,64,0x7feaf8264ec0,252,0,0,1996095,364,0,0,2121606,0,0,0,1756899,257,0,0,2138562,0,0,0,1966917,2087,0,0,2926074,145,0,0,1741464,0,0,0,2037348,0,0,0,1937336,0,0,0,1703304,290,0,0,1907139,31,0,0,1905018,3,0,0,2142949,445,0,0,2148298,0,0,0,2066979,507,0,0,1904322,292,0,0,2090429,0,0,0,1662207,0,0,0,1502967,472,0,0,2290706,118,0,0,2052461,413,0,0,2335740,0,0,0,1644030,0,0,0,1913009,0,0,0,1943825,559,0,0,2132393,0,0,0,1845826,116,0,0,1880531,17,0,0,1885777,0,0,0,1799122,133,0,0,2017165,211,0,0,2134717,64,0x7f4c38760ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119970001.0,56535132.0,0.0,64,0x7f34e1488ec0,4096,0,0,0,4096,0,128,0,4096,0,376,0,4096,0,369,0,4096,0,194,0,4096,0,1740,0,4096,0,0,0,4096,0,1251,0,4097,0,631,0,4096,0,0,0,4096,0,269,0,4096,0,0,0,4097,0,2,0,4096,0,1,0,4097,0,542,0,4096,0,0,0,4096,0,1066,0,4096,0,2088,0,4097,0,733,0,4096,0,306,0,4096,0,383,0,4096,0,19,0,4096,0,2121,0,4096,0,2007,0,4099,0,541,0,4096,0,151,0,4096,0,1809,0,4096,0,48,0,4097,0,651,0,4098,0,3,0,4096,0,0,0,4096,0,542,0,64,0x7fd4443e8ec0,328880,220244,16384,0,16384,16384,32768,49152,41109,41109,3138900.0,2456048.0,3847.0,343411.0,1792770.0,0.0,2442986.0,2134347.0,328872,229229,41109,0,41109,0,1315488.0,779252.0,0.0,0.0,64,0x7f596a470ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2041505.0,64,0x7f12afa38ec0,0,190653,0,0,65536,63800,56,1680,64,0x7efd09584ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f499dd68ec0,6286,0,4096,6274,0,4096,6274,0,4096,6261,0,4096,6243,0,4096,6244,0,4096,6244,0,4096,6258,0,4096,6255,0,4096,6292,0,4096,6279,0,4096,6277,0,4096,6264,0,4096,6248,0,4096,6247,0,4096,6244,0,4096,6267,0,4096,6249,0,4096,6270,0,4096,6248,0,4096,6249,0,4096,6259,0,4096,6244,0,4096,6247,0,4096,6250,0,4096,6266,0,4096,6245,0,4096,6271,0,4096,6253,0,4096,6242,0,4096,6257,0,4096,6250,0,4096,64,0x7f0e35368ec0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,0,40414,0,0,64,0x7f7222850ec0,0,0,0,56,0,65536,65536,0,64,0x7fc809a60ec0,0,2744594,2836,2836,0,5416069,2872,2872,0,3378193,2848,2848,0,3202107,2820,2820,0,3626216,2884,2884,0,4579554,2856,2856,0,2579320,2892,2892,0,4268680,2852,2852,0,3182503,2848,2848,0,3100945,2832,2832,0,2961554,2880,2880,0,2927444,2848,2848,0,3122292,2820,2820,0,4400137,2884,2884,0,3741985,2856,2856,0,3228068,2892,2892,0,3329799,2848,2848,0,2993407,2878,2878,0,3398330,2860,2860,0,3685781,2860,2860,0,2626384,2812,2812,0,3286665,2860,2860,0,3143182,2844,2844,0,3705295,2850,2850,0,3730003,2848,2848,0,2932908,2852,2852,0,2948310,2880,2880,0,3430493,2860,2860,0,2804760,2856,2856,0,2883802,2812,2812,0,2641071,2856,2856,0,2825556,2844,2844,64,0x7f33184f8ec0,0,393216,163840,0,0,0,0,0,29393,0.0,0.0,0.0,32768.0,0.0,0.0,237.0,32768.0,4096,16384,302,40429,1936,0,56.0,9.0,0.0,201064.0,197844342059817,197844342076617 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8219bd4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,85898.0,45692.0,0.0,64,0x7fb8b6fd4ec0,2185,4096,2185,6281,2179,4096,2179,6275,2172,4101,2177,6273,2173,4096,2173,6269,2179,4096,2179,6275,2199,4096,2199,6295,2186,4096,2186,6282,2201,4096,2201,6297,2201,4096,2201,6297,2182,4096,2182,6278,2184,4096,2184,6280,2172,4096,2172,6268,2172,4096,2172,6268,2180,4096,2180,6276,2200,4097,2201,6297,2189,4096,2189,6285,2213,4097,2214,6310,2265,4097,2266,6362,2166,4097,2167,6263,2166,4096,2166,6262,2185,4096,2185,6281,2190,4098,2192,6288,2208,4096,2208,6304,2186,4096,2186,6282,2186,4096,2186,6282,2218,4096,2218,6314,2211,4096,2211,6307,2169,4096,2169,6265,2166,4096,2166,6262,2187,4096,2187,6283,2184,4096,2184,6280,2208,4096,2208,6304,64,0x7f28659a0ec0,32768,32768,0,64,0x7f67610acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29872,27145,9771,3011,0,39089,200551.0,0.0,69468.0,131083.0,64,0x7f7390f20ec0,114688,0,32768,32768,16384,16384,65536,49152,56545889.0,196016443.0,47805110.0,131072.0,0.0,506043.0,0,0,25452,9004.0,131088.0,0.0,30.0,64,0x7ffa3c3e8ec0,19281669,17915533,1022072,344064,2794785,0,0,163840,832.0,515156.0,0.0,524288.0,543776.0,32768.0,1008504,0,0,13428,91062.0,91062.0,0.0,91062.0,64,0x7fa841cb8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21299,0,3201,38468,0,69727.0,131072.0,0.0,45609.0,64,0x7feaf8264ec0,0,0,0,1636856,91,0,0,1759257,0,0,0,1500771,0,0,0,2179376,0,0,0,1865353,0,0,0,1955465,254,0,0,1608139,84,0,0,2248820,334,0,0,1931047,152,0,0,1606182,672,0,0,2470605,0,0,0,1704716,213,0,0,1856647,14,0,0,1756608,21,0,0,1821685,350,0,0,1851164,0,0,0,1783520,0,0,0,1975559,0,0,0,1420386,231,0,0,2130494,196,0,0,1889017,0,0,0,1935297,185,0,0,1712951,0,0,0,2069704,0,0,0,1564384,0,0,0,1692698,0,0,0,1565693,293,0,0,2083546,417,0,0,1948398,0,0,0,1844399,0,0,0,1598763,369,0,0,1762484,64,0x7f4c38760ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120877902.0,60992876.0,0.0,64,0x7f34e1488ec0,4096,0,0,0,4096,0,320,0,4096,0,880,0,4096,0,324,0,4096,0,280,0,4096,0,1200,0,4096,0,96,0,4096,0,508,0,4097,0,112,0,4096,0,1,0,4096,0,11,0,4096,0,2433,0,4097,0,248,0,4096,0,0,0,4097,0,282,0,4096,0,128,0,4096,0,970,0,4096,0,563,0,4097,0,0,0,4096,0,281,0,4096,0,384,0,4096,0,394,0,4096,0,0,0,4096,0,210,0,4098,0,660,0,4096,0,2,0,4096,0,226,0,4096,0,377,0,4097,0,0,0,4098,0,399,0,4096,0,363,0,4096,0,0,0,64,0x7fd4443e8ec0,324072,217506,16384,0,16384,16384,32768,49152,40508,40508,3104469.0,2410672.0,4728.0,354900.0,1708183.0,0.0,2399106.0,2090110.0,324064,226637,40508,0,40508,0,1296256.0,771834.0,0.0,0.0,64,0x7f596a470ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2029773.0,64,0x7f12afa38ec0,0,183665,0,0,65536,63800,56,1680,64,0x7efd09584ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7f499dd68ec0,6253,0,4096,6257,0,4096,6269,0,4096,6282,0,4096,6286,0,4096,6293,0,4096,6263,0,4096,6249,0,4096,6246,0,4096,6252,0,4096,6264,0,4096,6272,0,4096,6289,0,4096,6292,0,4096,6292,0,4096,6266,0,4096,6294,0,4096,6279,0,4096,6241,0,4096,6252,0,4096,6252,0,4096,6274,0,4096,6299,0,4096,6265,0,4096,6266,0,4096,6296,0,4096,6279,0,4096,6244,0,4096,6254,0,4096,6255,0,4096,6277,0,4096,6297,0,4096,64,0x7f0e35368ec0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,0,41484,0,0,64,0x7f7222850ec0,0,0,0,56,0,65536,65536,0,64,0x7fc809a60ec0,0,3756839,2828,2828,0,4265889,2856,2856,0,4035033,2848,2848,0,4488624,2840,2840,0,2872436,2888,2888,0,3289530,2856,2856,0,2955224,2852,2852,0,4395018,2804,2804,0,3142593,2804,2804,0,2783675,2828,2828,0,3214670,2856,2856,0,3308008,2848,2848,0,4744349,2832,2832,0,2815373,2888,2888,0,5380790,2856,2856,0,3508411,2856,2856,0,3018342,2804,2804,0,3753540,2828,2828,0,3567803,2840,2840,0,3536128,2860,2860,0,5112421,2824,2824,0,3337315,2856,2856,0,3196234,2836,2836,0,3495189,2838,2838,0,3175295,2840,2840,0,2689358,2804,2804,0,3138631,2828,2828,0,3978952,2844,2844,0,2965545,2858,2858,0,4732657,2826,2826,0,3317425,2862,2862,0,3437194,2836,2836,64,0x7f33184f8ec0,0,393216,163840,0,0,0,0,0,29277,0.0,0.0,0.0,32768.0,0.0,0.0,206.0,32768.0,4096,16384,302,40412,2004,0,56.0,10.0,0.0,200839.0,197844342096937,197844342112777 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_6,obj_6,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_7,obj_7,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_9,obj_9,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_10,obj_10,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_11,obj_11,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_12,obj_12,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_13,obj_13,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_14,obj_14,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_15,obj_15,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_16,obj_16,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_17,obj_17,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_18,obj_18,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fdb11004ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f12448e8ec0,0,0,0,1162544,0,0,0,1086617,0,0,0,982488,0,0,0,1159056,0,0,0,987314,0,0,0,1100571,0,0,0,1160780,0,0,0,1169378,0,0,0,1075262,0,0,0,1025675,0,0,0,1009639,0,0,0,1053484,0,0,0,1098544,0,0,0,1023053,7,0,0,1128622,103,0,0,1356879,0,0,0,1040128,0,0,0,1049602,0,0,0,991901,42,0,0,1285371,0,0,0,1084391,0,0,0,1079466,0,0,0,1120367,0,0,0,1066036,0,0,0,963517,23,0,0,1096082,0,0,0,1032217,0,0,0,1167473,0,0,0,1128363,0,0,0,1085624,0,0,0,1094465,115,0,0,1295178,64,0x7fac048b0ec0,10856504,9857535,654905,344064,1651664,0,0,163840,832.0,515158.0,0.0,524288.0,269866.0,32768.0,480365,0,0,11304,131072.0,131072.0,0.0,131072.0,64,0x7ff5c2940ec0,32768,32768,0,64,0x7f4cfcdb4ec0,2281,4096,2281,6377,2289,4096,2289,6385,2285,4099,2288,6384,2299,4096,2299,6395,2284,4096,2284,6380,2295,4096,2295,6391,2321,4096,2321,6417,2305,4096,2305,6401,2306,4096,2306,6402,2282,4096,2282,6378,2295,4096,2295,6391,2284,4096,2284,6380,2299,4096,2299,6395,2287,4096,2287,6383,2295,4096,2295,6391,2328,4096,2328,6424,2314,4096,2314,6410,2332,4096,2332,6428,2295,4097,2296,6392,2295,4096,2295,6391,2314,4097,2315,6411,2292,4097,2293,6389,2308,4096,2308,6404,2447,4098,2449,6545,2284,4096,2284,6380,2319,4096,2319,6415,2388,4097,2389,6485,2295,4096,2295,6391,2297,4096,2297,6393,2315,4096,2315,6411,2294,4096,2294,6390,2314,4096,2314,6410,64,0x7fee3ff4cec0,0,1108860,4096,4096,0,1302621,4096,4096,0,1414404,4096,4096,0,1251033,4096,4096,0,1184628,4096,4096,0,1642375,4096,4096,0,1283467,4096,4096,0,1340102,4096,4096,0,1151518,4096,4096,0,1091597,4096,4096,0,1171473,4096,4096,0,1204619,4096,4096,0,1197903,4096,4096,0,1131912,4096,4096,0,1311372,4096,4096,0,1271787,4096,4096,0,1140909,4096,4096,0,1161910,4096,4096,0,1300283,4096,4096,0,1300040,4096,4096,0,1202593,4096,4096,0,1104401,4096,4096,0,1169466,4096,4096,0,1270189,4096,4096,0,1265029,4096,4096,0,1056923,4096,4096,0,1024211,4096,4096,0,1224533,4096,4096,0,1119710,4096,4096,0,1100949,4096,4096,0,1005231,4096,4096,0,1378678,4096,4096,64,0x7f259aeb8ec0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,0,28374,0,0,64,0x7f05193f8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,8721,0,814,26337,0,73487.0,131072.0,0.0,65568.0,64,0x7fb355d14ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,992391.0,64,0x7fa2b0514ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40302919.0,35512453.0,0.0,64,0x7f0db9d58ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,33761.0,46011.0,19525.0,64,0x7f54ce004ec0,114688,0,32768,32768,16384,16384,65536,49152,27684512.0,87338341.0,39183012.0,131072.0,0.0,248831.0,0,0,14796,917.0,131083.0,0.0,14.0,64,0x7fad65ba4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12383,18776,8416,546,0,26765,204256.0,0.0,73176.0,131080.0,64,0x7f85cbe84ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,353,0,4096,0,0,0,4096,0,30,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,9,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4097,0,241,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4098,0,0,0,64,0x7fe5680c4ec0,1234,116931,0,0,65536,63800,56,1680,64,0x7f6530700ec0,229648,129159,16384,0,16384,16384,32768,49152,28705,28705,1956518.0,1382906.0,3980.0,190474.0,1072505.0,0.0,1374907.0,1076117.0,227937,137276,28705,0,28705,0,918560.0,498366.0,0.0,0.0,64,0x7f9460550ec0,0,0,0,224,0,65536,64158,56,64,0x7f1ba14a0ec0,0,393216,163840,0,0,0,0,0,17859,0.0,0.0,0.0,32768.0,0.0,0.0,377.0,32768.0,4096,16384,352,28275,1998,0,56.0,6.0,0.0,203834.0,64,0x7fa0acd58ec0,6332,0,4096,6352,0,4096,6425,0,4096,6425,0,4096,6353,0,4096,6349,0,4096,6389,0,4096,6414,0,4096,6416,0,4096,6334,0,4096,6354,0,4096,6430,0,4096,6424,0,4096,6355,0,4096,6354,0,4096,6390,0,4096,6413,0,4096,6441,0,4096,6371,0,4096,6342,0,4096,6428,0,4096,6437,0,4096,6347,0,4096,6557,0,4096,6390,0,4096,6416,0,4096,6446,0,4096,6371,0,4096,6345,0,4096,6428,0,4096,6442,0,4096,6349,0,4096,1411329731616837,1411329731637157 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fdb11004ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f12448e8ec0,257,0,0,1907851,0,0,0,1713635,0,0,0,1761265,137,0,0,1808024,308,0,0,1884425,508,0,0,2425124,240,0,0,1691044,0,0,0,1654233,11,0,0,1677304,165,0,0,2049277,0,0,0,1581934,0,0,0,1613883,0,0,0,1656173,0,0,0,1734579,715,0,0,2166582,4,0,0,2134354,0,0,0,1677843,0,0,0,1816879,0,0,0,1460144,0,0,0,1614583,0,0,0,2038844,0,0,0,2021847,38,0,0,2035590,131,0,0,1756724,0,0,0,1777646,0,0,0,1488286,0,0,0,1867507,91,0,0,2016494,0,0,0,1953373,0,0,0,1768402,144,0,0,1775000,0,0,0,1796232,64,0x7fac048b0ec0,17894104,17300614,249426,344064,2651807,0,0,163840,0.0,524288.0,0.0,524288.0,469199.0,32768.0,795941,0,0,12092,91371.0,91371.0,0.0,91371.0,64,0x7ff5c2940ec0,32768,32768,0,64,0x7f4cfcdb4ec0,2176,4096,2176,6272,2140,4096,2140,6236,2151,4099,2154,6250,2163,4099,2166,6262,2171,4096,2171,6267,2151,4096,2151,6247,2172,4096,2172,6268,2166,4096,2166,6262,2174,4096,2174,6270,2176,4096,2176,6272,2142,4096,2142,6238,2153,4096,2153,6249,2161,4096,2161,6257,2170,4096,2170,6266,2152,4096,2152,6248,2178,4096,2178,6274,2204,4096,2204,6300,2189,4097,2190,6286,2156,4097,2157,6253,2147,4096,2147,6243,2177,4097,2178,6274,2192,4097,2193,6289,2185,4096,2185,6281,2174,4096,2174,6270,2177,4096,2177,6273,2204,4097,2205,6301,2242,4097,2243,6339,2153,4096,2153,6249,2147,4096,2147,6243,2175,4096,2175,6271,2193,4096,2193,6289,2190,4096,2190,6286,64,0x7fee3ff4cec0,0,3065952,2864,2864,0,3378836,2884,2884,0,2878631,2864,2864,0,3580079,2884,2884,0,3620668,2824,2824,0,2585695,2808,2808,0,3601965,2868,2868,0,5834188,2858,2858,0,5670643,2846,2846,0,2605844,2854,2854,0,3256515,2884,2884,0,2659365,2864,2864,0,3160118,2884,2884,0,2817221,2824,2824,0,2723206,2808,2808,0,3533563,2866,2866,0,4023226,2832,2832,0,3818261,2856,2856,0,3328429,2872,2872,0,3882533,2884,2884,0,3307939,2832,2832,0,3689515,2884,2884,0,2948337,2792,2792,0,2787071,2788,2788,0,2753025,2788,2788,0,3212427,2832,2832,0,4002145,2860,2860,0,2920965,2872,2872,0,3305293,2884,2884,0,3166630,2836,2836,0,3208801,2888,2888,0,3299911,2796,2796,64,0x7f259aeb8ec0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,0,42325,0,0,64,0x7f05193f8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,15832,0,819,36889,0,69416.0,131072.0,0.0,45604.0,64,0x7fb355d14ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2106039.0,64,0x7fa2b0514ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119641138.0,59545553.0,0.0,64,0x7f0db9d58ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,97485.0,45548.0,0.0,64,0x7f54ce004ec0,114688,0,32768,32768,16384,16384,65536,49152,54060611.0,197094283.0,43579602.0,131072.0,0.0,577622.0,0,0,23891,28888.0,131083.0,0.0,20.0,64,0x7fad65ba4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30338,26521,9597,2995,0,39622,200841.0,0.0,69758.0,131083.0,64,0x7f85cbe84ec0,4096,0,3,0,4096,0,31,0,4096,0,0,0,4096,0,0,0,4096,0,97,0,4096,0,2337,0,4096,0,0,0,4096,0,394,0,4096,0,0,0,4098,0,177,0,4096,0,726,0,4096,0,0,0,4097,0,126,0,4096,0,0,0,4096,0,0,0,4096,0,5,0,4096,0,1321,0,4096,0,325,0,4097,0,166,0,4096,0,265,0,4096,0,750,0,4096,0,165,0,4096,0,154,0,4096,0,1,0,4097,0,0,0,4096,0,510,0,4096,0,193,0,4096,0,98,0,4097,0,299,0,4096,0,300,0,4096,0,0,0,4098,0,116,0,64,0x7fe5680c4ec0,0,184512,0,0,65536,63800,56,1680,64,0x7f6530700ec0,335808,229170,16384,0,16384,16384,32768,49152,41975,41975,3255875.0,2482097.0,5577.0,388546.0,1699523.0,0.0,2470491.0,2162600.0,335800,238299,41975,0,41975,0,1343200.0,796988.0,0.0,0.0,64,0x7f9460550ec0,0,0,0,56,0,65536,65536,0,64,0x7f1ba14a0ec0,0,393216,163840,0,0,0,0,0,28046,0.0,0.0,0.0,32768.0,0.0,0.0,258.0,32768.0,4096,16384,302,37309,2030,0,56.0,0.0,0.0,200348.0,64,0x7fa0acd58ec0,6286,0,4096,6323,0,4096,6296,0,4096,6308,0,4096,6271,0,4096,6282,0,4096,6252,0,4096,6281,0,4096,6281,0,4096,6282,0,4096,6322,0,4096,6297,0,4096,6307,0,4096,6273,0,4096,6287,0,4096,6253,0,4096,6266,0,4096,6267,0,4096,6257,0,4096,6286,0,4096,6288,0,4096,6300,0,4096,6271,0,4096,6247,0,4096,6250,0,4096,6271,0,4096,6268,0,4096,6257,0,4096,6290,0,4096,6289,0,4096,6299,0,4096,6274,0,4096,1411329731745477,1411329731761797 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fdb11004ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f12448e8ec0,387,0,0,2051053,839,0,0,1926673,0,0,0,1750260,286,0,0,2002102,0,0,0,1771212,811,0,0,2083269,283,0,0,1727174,0,0,0,1508157,0,0,0,1445566,0,0,0,2022261,73,0,0,1774868,0,0,0,1515015,165,0,0,1583710,194,0,0,1952099,317,0,0,1911466,51,0,0,1886170,0,0,0,1504705,21,0,0,1962763,0,0,0,1343699,262,0,0,2060099,0,0,0,1757679,0,0,0,1821110,37,0,0,1802735,0,0,0,1967446,47,0,0,1698049,0,0,0,1477138,0,0,0,1591452,0,0,0,1581883,300,0,0,1906306,0,0,0,1442332,59,0,0,1697430,0,0,0,1835539,64,0x7fac048b0ec0,18708026,17589824,774138,344064,2760990,0,0,163840,832.0,515146.0,0.0,524288.0,586239.0,32768.0,907797,0,0,13963,91540.0,91540.0,0.0,91540.0,64,0x7ff5c2940ec0,32768,32768,0,64,0x7f4cfcdb4ec0,2157,4096,2157,6253,2206,4096,2206,6302,2181,4100,2185,6281,2175,4099,2178,6274,2182,4096,2182,6278,2153,4096,2153,6249,2167,4096,2167,6263,2190,4096,2190,6286,2197,4096,2197,6293,2158,4096,2158,6254,2212,4096,2212,6308,2181,4096,2181,6277,2181,4096,2181,6277,2181,4096,2181,6277,2153,4096,2153,6249,2168,4096,2168,6264,2160,4096,2160,6256,2193,4097,2194,6290,2179,4097,2180,6276,2163,4096,2163,6259,2160,4097,2161,6257,2188,4097,2189,6285,2171,4096,2171,6267,2191,4096,2191,6287,2188,4096,2188,6284,2160,4097,2161,6257,2247,4097,2248,6344,2185,4096,2185,6281,2163,4096,2163,6259,2159,4096,2159,6255,2195,4096,2195,6291,2171,4096,2171,6267,64,0x7fee3ff4cec0,0,3438674,2832,2832,0,4710440,2860,2860,0,3601408,2864,2864,0,4211008,2860,2860,0,3595594,2836,2836,0,4438138,2828,2828,0,3852032,2888,2888,0,4947840,2816,2816,0,3512236,2820,2820,0,3623550,2832,2832,0,3557437,2852,2852,0,3228927,2864,2864,0,3482273,2860,2860,0,3927790,2830,2830,0,4186346,2828,2828,0,5230175,2890,2890,0,4296159,2832,2832,0,4153520,2850,2850,0,3317486,2860,2860,0,3644069,2834,2834,0,3585030,2844,2844,0,3376569,2878,2878,0,3062726,2800,2800,0,4249537,2808,2808,0,3629481,2808,2808,0,3381166,2832,2832,0,4154902,2852,2852,0,3468581,2868,2868,0,3434180,2836,2836,0,3414980,2840,2840,0,3436759,2884,2884,0,3461409,2800,2800,64,0x7f259aeb8ec0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,0,42683,0,0,64,0x7f05193f8ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,18709,0,2603,37538,0,70031.0,131072.0,0.0,45756.0,64,0x7fb355d14ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2038795.0,64,0x7fa2b0514ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118770690.0,60981016.0,0.0,64,0x7f0db9d58ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,82350.0,45622.0,0.0,64,0x7f54ce004ec0,114688,0,32768,32768,16384,16384,65536,49152,56529541.0,196696674.0,44493778.0,131072.0,0.0,539897.0,0,0,24294,16396.0,131085.0,0.0,24.0,64,0x7fad65ba4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31836,27421,9660,3347,0,39525,201124.0,0.0,70041.0,131083.0,64,0x7f85cbe84ec0,4096,0,2110,0,4096,0,586,0,4096,0,1025,0,4096,0,1094,0,4096,0,1551,0,4096,0,1233,0,4096,0,583,0,4096,0,864,0,4096,0,964,0,4098,0,1510,0,4096,0,1364,0,4096,0,193,0,4097,0,583,0,4096,0,1080,0,4096,0,1527,0,4096,0,1010,0,4096,0,1441,0,4096,0,706,0,4097,0,897,0,4096,0,1209,0,4096,0,1241,0,4096,0,1868,0,4096,0,314,0,4096,0,1778,0,4097,0,99,0,4096,0,1282,0,4096,0,135,0,4096,0,2039,0,4097,0,792,0,4096,0,75,0,4096,0,189,0,4098,0,612,0,64,0x7fe5680c4ec0,0,184497,0,0,65536,63800,56,1680,64,0x7f6530700ec0,335080,227096,16384,0,16384,16384,32768,49152,41884,41884,3226779.0,2505495.0,4809.0,415871.0,1701805.0,0.0,2494286.0,2186898.0,335072,235967,41884,0,41884,0,1340288.0,788845.0,0.0,0.0,64,0x7f9460550ec0,0,0,0,56,0,65536,65536,0,64,0x7f1ba14a0ec0,0,393216,163840,0,0,0,0,0,30961,0.0,0.0,0.0,32768.0,0.0,0.0,246.0,32768.0,4096,16384,302,42183,1986,0,56.0,10.0,0.0,200937.0,64,0x7fa0acd58ec0,6272,0,4096,6300,0,4096,6282,0,4096,6258,0,4096,6309,0,4096,6326,0,4096,6272,0,4096,6266,0,4096,6266,0,4096,6277,0,4096,6306,0,4096,6286,0,4096,6262,0,4096,6310,0,4096,6327,0,4096,6274,0,4096,6251,0,4096,6251,0,4096,6269,0,4096,6303,0,4096,6252,0,4096,6268,0,4096,6279,0,4096,6277,0,4096,6279,0,4096,6252,0,4096,6254,0,4096,6272,0,4096,6306,0,4096,6257,0,4096,6269,0,4096,6279,0,4096,1411329731781797,1411329731797477 diff --git a/tests/workloads/join_type_grid/MI200/roofline.csv b/tests/workloads/join_type_grid/MI200/roofline.csv index 8f9e7cf7a2..85e5d140e9 100644 --- a/tests/workloads/join_type_grid/MI200/roofline.csv +++ b/tests/workloads/join_type_grid/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.0038,1388.3987,1389.6089,5015.1157,5012.2314,5018,9223.8711,9223.167,9224.5752,18053.973,18052.926,18055.02,20936.111,20875.215,20997.008,20262.564,20261.719,20263.41,170386.69,170382.23,170391.14,164843.95,164841.16,164846.75,41416.551,41416.031,41417.07,41475.82,41474.93,41476.711,166322.44,165832.12,166812.75 -1,1389.3538,1388.8239,1389.8837,5027.9702,5025.9165,5030.0239,9236.3096,9235.7012,9236.918,18098.809,18094.221,18103.396,20977.502,20910.598,21044.406,20295.943,20295.197,20296.689,170841.7,170837.19,170846.22,165119.48,165116.42,165122.55,41489.344,41488.586,41490.102,41547.473,41546.598,41548.348,166895.52,166891.62,166899.41 -2,1388.7098,1388.161,1389.2587,5033.98,5031.833,5036.127,9261.2559,9260.3711,9262.1406,18105.875,18104.926,18106.824,21048.035,21047.703,21048.367,20349.461,20348.93,20349.992,171090.62,171086.73,171094.52,165487.03,165483.39,165490.67,41579.785,41578.727,41580.844,41633.246,41632.113,41634.379,166922.98,166326.97,167519 -3,1388.9546,1388.3644,1389.5448,5032.0625,5030.7207,5033.4043,9241.0859,9240.6084,9241.5635,18022.875,18019.514,18026.236,21029.26,21028.918,21029.602,20310.809,20310.252,20311.365,171002.44,170997.73,171007.14,165216.23,165212.27,165220.2,41438.988,41283.625,41594.352,41579.773,41579.082,41580.465,167024.95,167023.23,167026.67 +0,1388.486,1387.8898,1389.0822,5016.1445,5013.0195,5019.2695,9227.0137,9226.4434,9227.584,17718.193,17715.303,17721.084,20944.297,20883.361,21005.232,20273.82,20273.236,20274.404,170481.22,170477.59,170484.84,164930.3,164926.34,164934.25,41437.273,41436.762,41437.785,41496.434,41495.852,41497.016,166391.69,165889.56,166893.81 +1,1388.6577,1388.0673,1389.2482,5027.5322,5025.4722,5029.5923,9234.4561,9233.7021,9235.21,18232.967,18230.99,18234.943,20979.215,20911.27,21047.16,20296.037,20295.385,20296.689,170858.34,170854.53,170862.16,165103.42,165098.36,165108.48,41483.328,41482.406,41484.25,41544.719,41543.91,41545.527,166863.31,166860.45,166866.17 +2,1389.0323,1388.4905,1389.5742,5035.7515,5033.4453,5038.0576,9260.7305,9260.1426,9261.3184,18216.838,18216.055,18217.621,21051.447,21051.006,21051.889,20355.74,20355.092,20356.389,171172.27,171167.73,171176.8,165521.98,165518.52,165525.45,41587.379,41586.652,41588.105,41645.004,41644.168,41645.84,166970.41,166378.25,167562.56 +3,1389.7032,1389.1039,1390.3026,5034.1958,5032.4849,5035.9067,9240.4053,9239.6436,9241.167,18330.793,18329.785,18331.801,21035.393,21035.094,21035.691,20310.59,20310.031,20311.148,171050.78,171046.12,171055.44,165172.27,165167.89,165176.64,41433.27,41280.215,41586.324,41569.391,41568.371,41570.41,166967.72,166962.97,166972.47 diff --git a/tests/workloads/join_type_grid/MI200/sysinfo.csv b/tests/workloads/join_type_grid/MI200/sysinfo.csv index 5bbcaa02f5..975adc5e90 100644 --- a/tests/workloads/join_type_grid/MI200/sysinfo.csv +++ b/tests/workloads/join_type_grid/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -join_type_grid,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:08:18 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +join_type_grid,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:13:03 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/join_type_grid/MI200/timestamps.csv b/tests/workloads/join_type_grid/MI200/timestamps.csv index 498169935f..d137a6c8f5 100644 --- a/tests/workloads/join_type_grid/MI200/timestamps.csv +++ b/tests/workloads/join_type_grid/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,273424,273424,1048576,256,0,0,8,0,16,64,0x0,0x7f334f7d0ec0,197844341928655,197844341953097,197844341974057,197844341984981 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,273424,273424,1048576,256,0,0,8,0,16,64,0x0,0x7f334f7d0ec0,197844341984380,197844342059817,197844342076617,197844342077587 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,273424,273424,1048576,256,0,0,8,0,16,64,0x0,0x7f334f7d0ec0,197844342087405,197844342096937,197844342112777,197844342113544 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4096839,4096839,1048576,256,0,0,8,0,16,64,0x0,0x7fcc2a4c0ec0,1411329731591762,1411329731616837,1411329731637157,1411329731649401 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4096839,4096839,1048576,256,0,0,8,0,16,64,0x0,0x7fcc2a4c0ec0,1411329731647918,1411329731745477,1411329731761797,1411329731762745 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4096839,4096839,1048576,256,0,0,8,0,16,64,0x0,0x7fcc2a4c0ec0,1411329731772774,1411329731781797,1411329731797477,1411329731798392 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv index 7e971f2dec..e4b3963225 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,107324,107324,1048576,256,0,0,8,8,16,64,0x0,0x7f9e0721ce80,48789,48789,16384,65536,14279,1856036,194072742742975,194084901267928,194084901291928,194072750548113 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107324,107324,1048576,256,0,0,8,8,16,64,0x0,0x7f9e0721ce80,42404,42404,16384,65536,8167,1048576,194072750570585,194084901373528,194084901392248,194072750884239 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,107324,107324,1048576,256,0,0,8,8,16,64,0x0,0x7f9e0721ce80,42548,42548,16384,65536,8218,1048576,194072750916059,194084901413848,194084901433048,194072751093325 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1203028,1203028,1048576,256,0,0,8,8,16,64,0x0,0x7f63e855cec0,48837,48837,16384,65536,14301,1859040,1410001716053160,1410013407844900,1410013407869220,1410001723853992 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1203028,1203028,1048576,256,0,0,8,8,16,64,0x0,0x7f63e855cec0,43639,43639,16384,65536,8200,1048588,1410001723877016,1410013407960580,1410013407979300,1410001724194294 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1203028,1203028,1048576,256,0,0,8,8,16,64,0x0,0x7f63e855cec0,42556,42556,16384,65536,8087,1048580,1410001724225613,1410013407999460,1410013408018340,1410001724398950 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv index e16792aa9a..b9aeb051ce 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,107512,107512,1048576,256,0,0,8,8,16,64,0x0,0x7f219311ae80,0,0,0,194073237479869,194084901267928,194084901291928,194073245258187 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107512,107512,1048576,256,0,0,8,8,16,64,0x0,0x7f219311ae80,0,0,0,194073245279247,194084901373528,194084901392248,194073245605574 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,107512,107512,1048576,256,0,0,8,8,16,64,0x0,0x7f219311ae80,0,0,0,194073245634449,194084901413848,194084901433048,194073245820271 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1203228,1203228,1048576,256,0,0,8,8,16,64,0x0,0x7f4c44fd8ec0,0,0,0,1410002200817299,1410013407844900,1410013407869220,1410002208416761 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1203228,1203228,1048576,256,0,0,8,8,16,64,0x0,0x7f4c44fd8ec0,0,0,0,1410002208435457,1410013407960580,1410013407979300,1410002208762022 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1203228,1203228,1048576,256,0,0,8,8,16,64,0x0,0x7f4c44fd8ec0,0,0,0,1410002208789945,1410013407999460,1410013408018340,1410002208965196 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv index fdc6eadf7a..79562e702c 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,107700,107700,1048576,256,0,0,8,8,16,64,0x0,0x7f85a6368e80,65536,169686,21865424,194073731739119,194084901267928,194084901291928,194073739288864 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107700,107700,1048576,256,0,0,8,8,16,64,0x0,0x7f85a6368e80,65536,173334,22159048,194073739309193,194084901373528,194084901392248,194073739595585 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,107700,107700,1048576,256,0,0,8,8,16,64,0x0,0x7f85a6368e80,65536,162678,20825528,194073739623377,194084901413848,194084901433048,194073739793309 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1203429,1203429,1048576,256,0,0,8,8,16,64,0x0,0x7fda222f4ec0,65536,190654,24437080,1410002685495515,1410013407844900,1410013407869220,1410002693075842 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1203429,1203429,1048576,256,0,0,8,8,16,64,0x0,0x7fda222f4ec0,65536,171472,21893376,1410002693096881,1410013407960580,1410013407979300,1410002693494151 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1203429,1203429,1048576,256,0,0,8,8,16,64,0x0,0x7fda222f4ec0,65536,194396,24909496,1410002693522183,1410013407999460,1410013408018340,1410002693695410 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv index cd1876f940..0c62c36dbf 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,107890,107890,1048576,256,0,0,8,8,16,64,0x0,0x7f0b3aa6ce80,32768,656568,84046520,194074222823518,194084901267928,194084901291928,194074230843173 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,107890,107890,1048576,256,0,0,8,8,16,64,0x0,0x7f0b3aa6ce80,32768,678091,86774128,194074230863100,194084901373528,194084901392248,194074231212693 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,107890,107890,1048576,256,0,0,8,8,16,64,0x0,0x7f0b3aa6ce80,32768,662440,84790852,194074231241938,194084901413848,194084901433048,194074231406800 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1203618,1203618,1048576,256,0,0,8,8,16,64,0x0,0x7f4befa10ec0,32768,644192,82470356,1410003161143270,1410013407844900,1410013407869220,1410003168914997 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1203618,1203618,1048576,256,0,0,8,8,16,64,0x0,0x7f4befa10ec0,32768,658825,84320580,1410003168935747,1410013407960580,1410013407979300,1410003169234049 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1203618,1203618,1048576,256,0,0,8,8,16,64,0x0,0x7f4befa10ec0,32768,646768,82777228,1410003169262232,1410013407999460,1410013408018340,1410003169433145 diff --git a/tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv index 3c0df479b6..f8a3d890ca 100644 --- a/tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,108080,108080,1048576,256,0,0,8,8,16,64,0x0,0x7f1bafecee80,48611,48611,16931,388896,16384,25448970,234378,0,102279796,194074720168701,194084901267928,194084901291928,194074727847260 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,108080,108080,1048576,256,0,0,8,8,16,64,0x0,0x7f1bafecee80,43466,43466,13493,347736,16384,25133504,238792,0,101023004,194074727875574,194084901373528,194084901392248,194074728202763 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,108080,108080,1048576,256,0,0,8,8,16,64,0x0,0x7f1bafecee80,42354,42354,13000,338840,16384,25537295,234589,0,102649744,194074728241056,194084901413848,194084901433048,194074728433761 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1203806,1203806,1048576,256,0,0,8,8,16,64,0x0,0x7f2c0b830ec0,48322,48322,17207,386584,16384,24320004,233590,0,97811132,1410003633597713,1410013407844900,1410013407869220,1410003641237331 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1203806,1203806,1048576,256,0,0,8,8,16,64,0x0,0x7f2c0b830ec0,43253,43253,13453,346032,16384,24912642,236697,0,100177420,1410003641267277,1410013407960580,1410013407979300,1410003641577102 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1203806,1203806,1048576,256,0,0,8,8,16,64,0x0,0x7f2c0b830ec0,42775,42775,12392,342208,16384,24294095,235290,0,97706760,1410003641615805,1410013407999460,1410013408018340,1410003641820140 diff --git a/tests/workloads/join_type_kernel/MI100/log.txt b/tests/workloads/join_type_kernel/MI100/log.txt new file mode 100644 index 0000000000..4b0e0e163a --- /dev/null +++ b/tests/workloads/join_type_kernel/MI100/log.txt @@ -0,0 +1,679 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/join_type_kernel/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155107' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155107_1202868' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155107_1202868/input0_results_240321_155107' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155107_1202868/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155107_1202868/input0_results_240321_155107 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155108' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155108_1203068' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155108_1203068/input0_results_240321_155108' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155108_1203068/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155108_1203068/input0_results_240321_155108 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155108' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155108_1203269' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155108_1203269/input0_results_240321_155108' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155108_1203269/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155108_1203269/input0_results_240321_155108 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155109' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155109_1203458' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155109_1203458/input0_results_240321_155109' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155109_1203458/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155109_1203458/input0_results_240321_155109 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155109' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155109_1203646' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155109_1203646/input0_results_240321_155109' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155109_1203646/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155109_1203646/input0_results_240321_155109 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155110' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155110_1203830' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155110_1203830/input0_results_240321_155110' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155110_1203830/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155110_1203830/input0_results_240321_155110 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155110' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155110_1204030' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155110_1204030/input0_results_240321_155110' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155110_1204030/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155110_1204030/input0_results_240321_155110 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155111' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155111_1204217' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155111_1204217/input0_results_240321_155111' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155111_1204217/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155111_1204217/input0_results_240321_155111 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155111' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155111_1204418' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155111_1204418/input0_results_240321_155111' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155111_1204418/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155111_1204418/input0_results_240321_155111 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155112' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155112_1204619' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155112_1204619/input0_results_240321_155112' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155112_1204619/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155112_1204619/input0_results_240321_155112 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155112' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155112_1204804' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155112_1204804/input0_results_240321_155112' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155112_1204804/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155112_1204804/input0_results_240321_155112 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155113' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155113_1204987' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155113_1204987/input0_results_240321_155113' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155113_1204987/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155113_1204987/input0_results_240321_155113 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155114' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155114_1205173' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155114_1205173/input0_results_240321_155114' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155114_1205173/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155114_1205173/input0_results_240321_155114 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155114' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155114_1205374' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155114_1205374/input0_results_240321_155114' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155114_1205374/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155114_1205374/input0_results_240321_155114 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155115' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155115_1205560' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155115_1205560/input0_results_240321_155115' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155115_1205560/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155115_1205560/input0_results_240321_155115 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155116' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155116_1205745' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155116_1205745/input0_results_240321_155116' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155116_1205745/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155116_1205745/input0_results_240321_155116 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155116' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155116_1205945' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155116_1205945/input0_results_240321_155116' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155116_1205945/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155116_1205945/input0_results_240321_155116 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155117' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155117_1206146' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155117_1206146/input0_results_240321_155117' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155117_1206146/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155117_1206146/input0_results_240321_155117 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155117' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155117_1206340' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155117_1206340/input0_results_240321_155117' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155117_1206340/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155117_1206340/input0_results_240321_155117 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155117' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155117_1206541' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155117_1206541/input0_results_240321_155117' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155117_1206541/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155117_1206541/input0_results_240321_155117 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155118' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155118_1206727' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155118_1206727/input0_results_240321_155118' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155118_1206727/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155118_1206727/input0_results_240321_155118 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155118' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155118_1206927' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155118_1206927/input0_results_240321_155118' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155118_1206927/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155118_1206927/input0_results_240321_155118 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155119' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155119_1207111' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155119_1207111/input0_results_240321_155119' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155119_1207111/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155119_1207111/input0_results_240321_155119 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/join_type_kernel/MI100/pmc_dispatch_info.csv b/tests/workloads/join_type_kernel/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/join_type_kernel/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/join_type_kernel/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/join_type_kernel/MI100/pmc_perf.csv b/tests/workloads/join_type_kernel/MI100/pmc_perf.csv index a7093fd748..dea5a6ec55 100644 --- a/tests/workloads/join_type_kernel/MI100/pmc_perf.csv +++ b/tests/workloads/join_type_kernel/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_3,obj_3,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_6,obj_6,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_10,obj_10,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_11,obj_11,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_12,obj_12,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_13,obj_13,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_14,obj_14,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f308a89ae80,32768,0,0,0,16384,16384,393216,23021945,960.0,513880.0,0.0,524288.0,1035416.0,32768.0,0,0,0,16452,131072.0,131072.0,0.0,131072.0,64,0x7f68e6ccee80,0.0,64,0x7fae8f0bae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86591.0,44481.0,131112.0,0.0,64,0x7fe717cf8e80,4096,0,6029,0,4096,0,928,0,4099,0,1337,0,4096,0,1330,0,4096,0,768,0,4096,0,1127,0,4096,0,3179,0,4096,0,2371,0,4096,0,359,0,4096,0,1415,0,4144,0,2879,0,4096,0,4362,0,4144,0,550,0,4096,0,2171,0,4096,0,5017,0,4222,0,674,0,4144,0,1657,0,4096,0,4504,0,4096,0,4287,0,4097,0,1080,0,4096,0,520,0,4096,0,1875,0,4096,0,794,0,4096,0,132,0,4096,0,3468,0,4096,0,1465,0,4096,0,1816,0,4096,0,3882,0,4096,0,0,0,4096,0,0,0,4096,0,2415,0,4096,0,4937,0,64,0x7f253c6d2e80,396496,247181,3576669,16384,25746310,144,48,0,49561,49561,4060644.0,3197256.0,5271.0,1223515.0,2284571.0,0.0,3186550.0,2873089.0,394847,257128,49561,0,49561,0,1585952.0,1009554.0,0.0,0.0,64,0x7f98d4602e80,131072.0,131072.0,0.0,2533597.0,0.0,0.0,126684161.0,61263601.0,64,0x7fef762bce80,188377,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11749,28133,10075,550,0,47669,262741.0,0.0,188.0,262553.0,64,0x7fdaa3618e80,935,0,0,1689023,1232,0,0,1675081,2421,0,0,2011805,4180,0,0,2102217,1046,0,0,1710903,3766,0,0,2112402,1296,0,0,1738320,1235,0,0,1837294,1446,0,0,1816291,1553,0,0,1729779,1501,0,0,1780265,3240,0,0,2016916,1986,0,0,1845160,2348,0,0,1869493,1936,0,0,1845088,3741,0,0,2037699,644,0,0,1583892,624,0,0,1621783,1844,0,0,1881684,1523,0,0,1868360,2557,0,0,1861041,2251,0,0,1915379,2123,0,0,1838643,2373,0,0,1961977,1620,0,0,1743108,1183,0,0,1768085,1035,0,0,1752932,4966,0,0,2139336,1108,0,0,1686681,1591,0,0,1725298,1567,0,0,1831951,3238,0,0,1962881,64,0x7f9e43120e80,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,0,48412,0,0,64,0x7f85434cce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131293.0,0.0,434.0,131292.0,64,0x7f18eb488e80,0,0,192,0,65536,64466,48,1368,30943,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,46985,1710,0,48.0,201.0,0.0,262288.0,64,0x7f9688a28e80,0,3663238,4096,4096,0,3901874,4096,4096,0,4029749,4096,4096,0,3045492,4096,4096,0,3553483,4096,4096,0,3526377,4096,4096,0,3162538,4096,4096,0,5179828,4096,4096,0,3586097,4096,4096,0,3329358,4096,4096,0,3892962,4096,4096,0,3636824,4096,4096,0,4323277,4096,4096,0,3905153,4096,4096,0,2847329,4096,4096,0,3168819,4096,4096,0,4039784,4096,4096,0,5320449,4096,4096,0,3822901,4096,4096,0,3177539,4096,4096,0,3894450,4096,4096,0,3920855,4096,4096,0,2834706,4096,4096,0,2867897,4096,4096,0,3478928,4096,4096,0,5134370,4096,4096,0,2688673,4096,4096,0,3085342,4096,4096,0,3342339,4096,4096,0,4050464,4096,4096,0,2992545,4096,4096,0,2899927,4096,4096,64,0x7f4427492e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47186,0,131488.0,131072.0,0.0,131104.0,64,0x7f8f0d2b6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f583f4f0e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8218,4122,8218,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb62b0c0e80,1879014,360448,163840,0,0,180224,114688,0,66861208.0,199267740.0,79073197.0,131072.0,0.0,704340.0,0,0,26430,127544.0,0.0,0.0,127544.0,64,0x7f9f08402e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60745.0,127569.0,194084901267928,194084901291928 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f308a89ae80,32768,0,0,0,16384,16384,393216,23098874,960.0,513891.0,0.0,524288.0,1021920.0,32768.0,0,0,0,15470,86488.0,86488.0,0.0,86488.0,64,0x7f68e6ccee80,0.0,64,0x7fae8f0bae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,67412.0,18982.0,79660.0,0.0,64,0x7fe717cf8e80,4096,0,5761,0,4096,0,4077,0,4096,0,3,0,4097,0,1479,0,4096,0,3371,0,4096,0,5997,0,4097,0,5207,0,4096,0,343,0,4096,0,1771,0,4096,0,3363,0,4144,0,608,0,4097,0,3648,0,4144,0,3085,0,4096,0,3292,0,4096,0,4728,0,4228,0,0,0,4144,0,24,0,4096,0,2648,0,4096,0,1674,0,4097,0,0,0,4096,0,3427,0,4096,0,1098,0,4096,0,2348,0,4096,0,0,0,4096,0,5369,0,4096,0,1466,0,4096,0,1852,0,4098,0,1311,0,4096,0,975,0,4096,0,2491,0,4096,0,56,0,4096,0,2434,0,64,0x7f253c6d2e80,344360,233753,3409093,16384,25291285,0,48,0,43044,43044,3795786.0,3121299.0,4193.0,1099743.0,2233278.0,0.0,3111631.0,2801880.0,344352,243173,43044,0,43044,0,1377408.0,838607.0,0.0,0.0,64,0x7f98d4602e80,131072.0,131072.0,0.0,2697989.0,0.0,0.0,131643077.0,46828420.0,64,0x7fef762bce80,343319,0,0,65536,62560,96,2880,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14057,30441,20716,5245,0,43975,262740.0,0.0,94.0,262646.0,64,0x7fdaa3618e80,3486,0,0,1618217,2911,0,0,1587798,2877,0,0,1611560,4936,0,0,1712931,1643,0,0,1502838,2885,0,0,1575418,2173,0,0,1517556,6208,0,0,1762309,1251,0,0,1340381,3051,0,0,1702705,4518,0,0,1672937,3692,0,0,1588288,3623,0,0,1609830,4503,0,0,1589109,4151,0,0,1649764,4723,0,0,1681657,2612,0,0,1564365,2821,0,0,1549110,3421,0,0,1640318,6116,0,0,1794891,2764,0,0,1506976,5342,0,0,1829144,2676,0,0,1556229,2914,0,0,1649169,3790,0,0,1638053,5271,0,0,1767638,2967,0,0,1517144,4763,0,0,1634813,3110,0,0,1523754,2394,0,0,1543963,2944,0,0,1535202,5254,0,0,1730864,64,0x7f9e43120e80,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,0,42507,0,0,64,0x7f85434cce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131283.0,0.0,420.0,131282.0,64,0x7f18eb488e80,0,0,48,0,65536,65536,0,0,30271,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41630,1660,0,48.0,180.0,0.0,262144.0,64,0x7f9688a28e80,0,4508742,2718,2718,0,4230106,2680,2680,0,4696852,2682,2682,0,3305402,2677,2677,0,3623814,2700,2700,0,3141352,2714,2714,0,3909720,2708,2708,0,5003226,2702,2702,0,3343126,2712,2712,0,4761479,2684,2684,0,4181584,2706,2706,0,4693580,2728,2728,0,4314759,2710,2710,0,3292184,2650,2650,0,4923718,2714,2714,0,3181891,2672,2672,0,5101272,2701,2701,0,4029456,2688,2688,0,4093851,2714,2714,0,3434987,2700,2700,0,4152898,2700,2700,0,3373290,2724,2724,0,3629606,2679,2679,0,3555868,2696,2696,0,3670948,2700,2700,0,3231057,2680,2680,0,3161780,2750,2750,0,4051029,2695,2695,0,4535908,2708,2708,0,4124704,2685,2685,0,3799962,2739,2739,0,3374548,2664,2664,64,0x7f4427492e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,4691,115036,2648,131683.0,131072.0,0.0,86593.0,64,0x7f8f0d2b6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f583f4f0e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,64,0x7fb62b0c0e80,2138857,360448,163840,0,0,180224,114688,0,67352205.0,182483944.0,80511844.0,131072.0,0.0,1263757.0,0,0,25862,113261.0,0.0,0.0,113261.0,64,0x7f9f08402e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,57908.0,121756.0,194084901373528,194084901392248 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f308a89ae80,32768,0,0,0,16384,16384,393216,22492981,960.0,513899.0,0.0,524288.0,1016014.0,32768.0,0,0,0,13834,86625.0,86625.0,0.0,86625.0,64,0x7f68e6ccee80,0.0,64,0x7fae8f0bae80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86438.0,0.0,131112.0,0.0,64,0x7fe717cf8e80,4096,0,2318,0,4096,0,0,0,4096,0,4003,0,4097,0,99,0,4096,0,784,0,4096,0,1198,0,4097,0,5441,0,4096,0,1124,0,4096,0,1998,0,4096,0,2168,0,4144,0,4942,0,4097,0,2778,0,4144,0,5358,0,4096,0,1190,0,4096,0,3999,0,4277,0,983,0,4144,0,5333,0,4096,0,3137,0,4096,0,5825,0,4097,0,913,0,4096,0,481,0,4096,0,3286,0,4096,0,2499,0,4096,0,197,0,4096,0,1201,0,4096,0,269,0,4096,0,3096,0,4098,0,0,0,4096,0,0,0,4096,0,3804,0,4096,0,897,0,4096,0,3888,0,64,0x7f253c6d2e80,337736,227079,3307439,16384,24374740,0,48,0,42216,42216,3696092.0,3024979.0,6186.0,930092.0,2087592.0,0.0,3015989.0,2704595.0,337728,236579,42216,0,42216,0,1350912.0,806228.0,0.0,0.0,64,0x7f98d4602e80,131072.0,131072.0,0.0,2542059.0,0.0,0.0,115463903.0,48109140.0,64,0x7fef762bce80,184719,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12521,28905,8515,2383,0,40535,262485.0,0.0,47.0,262438.0,64,0x7fdaa3618e80,820,0,0,1269261,634,0,0,1249799,3827,0,0,1792084,1736,0,0,1447232,1284,0,0,1392304,1794,0,0,1403650,1715,0,0,1395218,1722,0,0,1476916,1634,0,0,1462308,2200,0,0,1507856,1161,0,0,1354323,1315,0,0,1332219,773,0,0,1263668,977,0,0,1313894,1204,0,0,1416278,2214,0,0,1429371,746,0,0,1259164,699,0,0,1268324,1409,0,0,1376564,1155,0,0,1336346,2890,0,0,1521808,541,0,0,1262555,867,0,0,1337871,1483,0,0,1410430,1866,0,0,1448175,599,0,0,1220318,1087,0,0,1376710,1926,0,0,1393188,4557,0,0,1770447,1531,0,0,1337357,1300,0,0,1473575,2615,0,0,1624433,64,0x7f9e43120e80,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,0,42563,0,0,64,0x7f85434cce80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131274.0,0.0,402.0,131273.0,64,0x7f18eb488e80,0,0,48,0,65536,65536,0,0,29759,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41192,1785,0,48.0,175.0,0.0,262144.0,64,0x7f9688a28e80,0,4579310,2718,2718,0,4578344,2730,2730,0,3494035,2694,2694,0,4590352,2716,2716,0,4072427,2687,2687,0,3994941,2718,2718,0,3822256,2708,2708,0,5133382,2684,2684,0,4701668,2696,2696,0,3795514,2678,2678,0,4550848,2722,2722,0,5019740,2718,2718,0,3653020,2690,2690,0,4588499,2690,2690,0,4528406,2698,2698,0,4991125,2688,2688,0,4909365,2688,2688,0,5394473,2704,2704,0,4546273,2682,2682,0,4742109,2725,2725,0,4447117,2697,2697,0,4353893,2730,2730,0,4613906,2684,2684,0,4689922,2696,2696,0,3349309,2688,2688,0,4785506,2708,2708,0,3834543,2708,2708,0,4525187,2708,2708,0,4155600,2713,2713,0,4661963,2699,2699,0,3452318,2732,2732,0,5077875,2685,2685,64,0x7f4427492e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2721,41522,0,131331.0,131072.0,0.0,86549.0,64,0x7f8f0d2b6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f583f4f0e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8199,4103,8199,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8360,4264,8360,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,64,0x7fb62b0c0e80,1444200,360448,163840,0,0,180224,114688,0,69800357.0,204180012.0,83768321.0,131072.0,0.0,764267.0,0,0,25149,126647.0,0.0,0.0,126647.0,64,0x7f9f08402e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,60370.0,127344.0,194084901413848,194084901433048 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_1,obj_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_2,obj_2,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_3,obj_3,TCC_EA_ATOMIC_LEVEL_sum,wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_6,obj_6,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_7,obj_7,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_8,obj_8,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_11,obj_11,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_14,obj_14,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_15,obj_15,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_16,obj_16,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fa6776e0ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86376.0,44696.0,131112.0,0.0,64,0x7f10244c8ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46680,0,131503.0,131072.0,0.0,131104.0,64,0x7fdaf2d04ec0,131072.0,131072.0,0.0,2576659.0,0.0,0.0,114964317.0,59871877.0,64,0x7fc72a020ec0,0.0,64,0x7f7c26280ec0,0,4068733,4096,4096,0,3474071,4096,4096,0,3347486,4096,4096,0,3098157,4096,4096,0,3669976,4096,4096,0,3582844,4096,4096,0,4287727,4096,4096,0,3365408,4096,4096,0,3987610,4096,4096,0,3200622,4096,4096,0,4579963,4096,4096,0,3338805,4096,4096,0,3717420,4096,4096,0,3049872,4096,4096,0,3590983,4096,4096,0,3795865,4096,4096,0,3624425,4096,4096,0,3914198,4096,4096,0,3931957,4096,4096,0,3250022,4096,4096,0,4055291,4096,4096,0,3266014,4096,4096,0,3437499,4096,4096,0,4215148,4096,4096,0,3816381,4096,4096,0,3839585,4096,4096,0,3409346,4096,4096,0,3414115,4096,4096,0,3532399,4096,4096,0,3487170,4096,4096,0,3155922,4096,4096,0,3362237,4096,4096,64,0x7ff50d018ec0,2778395,360448,163840,0,0,180224,114688,0,64856029.0,160922004.0,66213108.0,131072.0,0.0,696606.0,0,0,27696,72744.0,0.0,0.0,72744.0,64,0x7f25b92a8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fc6ee3e8ec0,4096,0,1176,0,4096,0,3573,0,4096,0,1438,0,4100,0,5183,0,4096,0,1159,0,4096,0,155,0,4096,0,2164,0,4096,0,4452,0,4096,0,3350,0,4096,0,2396,0,4144,0,1859,0,4096,0,3486,0,4096,0,3423,0,4096,0,2814,0,4096,0,2147,0,4096,0,3945,0,4096,0,1281,0,4096,0,1116,0,4096,0,3420,0,4096,0,2006,0,4096,0,1522,0,4096,0,6190,0,4096,0,1707,0,4096,0,1093,0,4096,0,3272,0,4096,0,3225,0,4096,0,1731,0,4096,0,718,0,4216,0,5466,0,4096,0,5,0,4144,0,5470,0,4096,0,1397,0,64,0x7fdd5254cec0,32768,0,0,0,16384,16384,393216,22852488,960.0,513960.0,0.0,524288.0,911930.0,32768.0,0,0,0,17189,131072.0,131072.0,0.0,131072.0,64,0x7f8dfa2c8ec0,384664,233796,3422307,16384,25189568,144,48,0,48082,48082,3859286.0,3041802.0,5449.0,926673.0,2090283.0,0.0,3032588.0,2721213.0,382951,243734,48082,0,48082,0,1538624.0,956743.0,0.0,0.0,64,0x7f7c567bcec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131340.0,0.0,528.0,131339.0,64,0x7f5eb6b50ec0,3413,0,0,1924885,2025,0,0,1945667,2174,0,0,1866904,5729,0,0,2089032,1149,0,0,1648498,2475,0,0,1881332,4193,0,0,2016712,5401,0,0,2117497,1923,0,0,1824916,3400,0,0,2027790,4777,0,0,1940172,5745,0,0,2142683,1837,0,0,1689996,6830,0,0,2220012,4223,0,0,1982429,5707,0,0,2054344,1030,0,0,1698730,3056,0,0,1962676,3207,0,0,1883352,5507,0,0,2036725,2547,0,0,1786206,3445,0,0,2033717,3549,0,0,1904295,6408,0,0,2187403,5168,0,0,2068970,2018,0,0,1768501,4687,0,0,2015334,5737,0,0,2024466,3673,0,0,1991696,4661,0,0,2079091,4768,0,0,2018258,4850,0,0,2066111,64,0x7f926d74cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,15090.0,107877.0,64,0x7fb89e6e8ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,188,8196,4288,8384,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8368,4272,8368,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f62cc984ec0,188077,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,8597,24981,9963,588,0,46634,262684.0,0.0,188.0,262496.0,64,0x7f72c6574ec0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,0,47979,0,0,64,0x7fb04b694ec0,0,0,192,0,65536,64489,48,1334,32735,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,49433,1849,0,48.0,460.0,0.0,262288.0,1410013407844900,1410013407869220 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fa6776e0ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,57192.0,39916.0,66650.0,0.0,64,0x7f10244c8ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2762,39689,0,131367.0,131072.0,0.0,86497.0,64,0x7fdaf2d04ec0,131072.0,131072.0,0.0,3097683.0,0.0,0.0,123600127.0,55603304.0,64,0x7fc72a020ec0,0.0,64,0x7f7c26280ec0,0,4451010,2752,2752,0,4521565,2704,2704,0,3512237,2724,2724,0,3528537,2698,2698,0,3506387,2700,2700,0,3628867,2735,2735,0,3728566,2712,2712,0,4101722,2696,2696,0,3483229,2720,2720,0,3664017,2682,2682,0,4573048,2728,2728,0,4034209,2698,2698,0,3956632,2718,2718,0,3529714,2684,2684,0,3897943,2740,2740,0,3734490,2690,2690,0,3605363,2700,2700,0,4049892,2724,2724,0,4040990,2704,2704,0,4047625,2700,2700,0,3706895,2704,2704,0,3606987,2733,2733,0,3775086,2704,2704,0,3763122,2725,2725,0,3604241,2704,2704,0,3904131,2708,2708,0,3253097,2740,2740,0,3208353,2738,2738,0,3754155,2728,2728,0,4026682,2710,2710,0,3778777,2694,2694,0,4057207,2700,2700,64,0x7ff50d018ec0,1101771,360448,163840,0,0,180224,114688,0,72935207.0,198234629.0,78213379.0,131072.0,0.0,621034.0,0,0,25122,53600.0,0.0,0.0,53600.0,64,0x7f25b92a8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fc6ee3e8ec0,4096,0,199,0,4096,0,2756,0,4096,0,238,0,4097,0,435,0,4096,0,4841,0,4096,0,1731,0,4096,0,821,0,4096,0,97,0,4096,0,1216,0,4096,0,7104,0,4144,0,0,0,4096,0,258,0,4097,0,2597,0,4097,0,2726,0,4096,0,156,0,4096,0,0,0,4096,0,815,0,4098,0,2241,0,4096,0,1179,0,4096,0,10,0,4096,0,4045,0,4096,0,4954,0,4096,0,152,0,4096,0,56,0,4096,0,3310,0,4096,0,4905,0,4096,0,0,0,4096,0,32,0,4216,0,4508,0,4096,0,2969,0,4144,0,0,0,4096,0,443,0,64,0x7fdd5254cec0,32768,0,0,0,16384,16384,393216,23094754,960.0,513932.0,0.0,524288.0,950259.0,32768.0,0,0,0,13984,86492.0,86492.0,0.0,86492.0,64,0x7f8dfa2c8ec0,346704,230291,3364386,16384,24786270,0,48,0,43337,43337,3743726.0,3081390.0,6199.0,1171388.0,2183759.0,0.0,3072251.0,2760927.0,346696,240061,43337,0,43337,0,1386784.0,816591.0,0.0,0.0,64,0x7f7c567bcec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131342.0,0.0,538.0,131341.0,64,0x7f5eb6b50ec0,3869,0,0,1552467,3081,0,0,1592775,3149,0,0,1562166,3044,0,0,1561862,3175,0,0,1593837,2158,0,0,1439724,5975,0,0,1820768,3617,0,0,1625349,3325,0,0,1581317,1267,0,0,1386289,4534,0,0,1644549,1429,0,0,1361901,3803,0,0,1623834,5343,0,0,1670498,2873,0,0,1638915,3382,0,0,1534090,3132,0,0,1637938,4415,0,0,1693432,2419,0,0,1571603,3453,0,0,1586312,3208,0,0,1583972,3635,0,0,1579664,3413,0,0,1645890,4947,0,0,1707107,4391,0,0,1574275,371,0,0,1325294,4183,0,0,1636207,4419,0,0,1586445,3288,0,0,1538656,1138,0,0,1410038,3917,0,0,1629135,2938,0,0,1539261,64,0x7f926d74cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,22477.0,90639.0,64,0x7fb89e6e8ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8361,4265,8361,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f62cc984ec0,185891,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14323,30707,8484,2584,0,40829,262535.0,0.0,47.0,262488.0,64,0x7f72c6574ec0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,0,43183,0,0,64,0x7fb04b694ec0,0,0,48,0,65536,65536,0,0,31420,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,44226,1735,0,48.0,464.0,0.0,262144.0,1410013407960580,1410013407979300 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fa6776e0ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86271.0,0.0,131112.0,0.0,64,0x7f10244c8ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2685,39586,0,131367.0,131072.0,0.0,86404.0,64,0x7fdaf2d04ec0,131072.0,131072.0,0.0,2549420.0,0.0,0.0,135388669.0,47374693.0,64,0x7fc72a020ec0,0.0,64,0x7f7c26280ec0,0,4277811,2721,2721,0,3986316,2702,2702,0,3595870,2698,2698,0,4185051,2703,2703,0,3592376,2664,2664,0,3961526,2689,2689,0,4060246,2704,2704,0,3758122,2716,2716,0,3646979,2716,2716,0,4423007,2682,2682,0,4475902,2704,2704,0,3905316,2724,2724,0,3825601,2706,2706,0,4150454,2693,2693,0,3906832,2700,2700,0,3772219,2730,2730,0,3944748,2716,2716,0,4789863,2692,2692,0,4405857,2700,2700,0,3838330,2722,2722,0,3653309,2708,2708,0,3772735,2727,2727,0,3914817,2672,2672,0,3978786,2710,2710,0,3498218,2680,2680,0,3535576,2716,2716,0,3676812,2712,2712,0,3693764,2733,2733,0,3569475,2702,2702,0,4028020,2681,2681,0,3742385,2692,2692,0,3946129,2744,2744,64,0x7ff50d018ec0,1395340,360448,163840,0,0,180224,114688,0,71506852.0,210217050.0,79416776.0,131072.0,0.0,559131.0,0,0,25024,78324.0,0.0,0.0,78324.0,64,0x7f25b92a8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fc6ee3e8ec0,4096,0,1167,0,4096,0,605,0,4096,0,0,0,4097,0,0,0,4096,0,533,0,4096,0,520,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4144,0,821,0,4096,0,428,0,4097,0,833,0,4097,0,0,0,4096,0,85,0,4096,0,997,0,4096,0,0,0,4098,0,6994,0,4096,0,0,0,4096,0,0,0,4096,0,4399,0,4096,0,300,0,4096,0,0,0,4096,0,1311,0,4096,0,205,0,4096,0,754,0,4096,0,132,0,4096,0,0,0,4216,0,2526,0,4096,0,1090,0,4144,0,0,0,4096,0,373,0,64,0x7fdd5254cec0,32768,0,0,0,16384,16384,393216,22810326,960.0,513926.0,0.0,524288.0,882066.0,32768.0,0,0,0,14117,86320.0,86320.0,0.0,86320.0,64,0x7f8dfa2c8ec0,341760,230103,3374812,16384,24041302,0,48,0,42719,42719,3740512.0,3090121.0,5355.0,993840.0,2107898.0,0.0,3080662.0,2770066.0,341752,239423,42719,0,42719,0,1367008.0,804179.0,0.0,0.0,64,0x7f7c567bcec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131342.0,0.0,538.0,131341.0,64,0x7f5eb6b50ec0,3655,0,0,1545154,3666,0,0,1585751,4863,0,0,1653720,3235,0,0,1502063,1921,0,0,1492836,3274,0,0,1569230,4995,0,0,1648566,2603,0,0,1503030,2033,0,0,1457569,1103,0,0,1360467,4511,0,0,1609534,1178,0,0,1271315,4153,0,0,1692418,3095,0,0,1502770,4590,0,0,1642764,1655,0,0,1336977,2807,0,0,1645053,2172,0,0,1538877,2029,0,0,1471456,2290,0,0,1451952,3591,0,0,1591483,2250,0,0,1522204,3212,0,0,1522992,1477,0,0,1325004,5296,0,0,1670935,1574,0,0,1409536,3897,0,0,1523570,2728,0,0,1514920,4324,0,0,1638092,1182,0,0,1312683,4581,0,0,1559795,1507,0,0,1386129,64,0x7f926d74cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,22311.0,137697.0,64,0x7fb89e6e8ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8362,4266,8362,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f62cc984ec0,186470,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13363,29747,8556,2391,0,41216,262536.0,0.0,47.0,262489.0,64,0x7f72c6574ec0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,0,43020,0,0,64,0x7fb04b694ec0,0,0,48,0,65536,65536,0,0,32052,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,43832,1777,0,48.0,462.0,0.0,262144.0,1410013407999460,1410013408018340 diff --git a/tests/workloads/join_type_kernel/MI100/sysinfo.csv b/tests/workloads/join_type_kernel/MI100/sysinfo.csv index 829f442436..97e3890573 100644 --- a/tests/workloads/join_type_kernel/MI100/sysinfo.csv +++ b/tests/workloads/join_type_kernel/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -join_type_kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:05:37 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +join_type_kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:51:07 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/join_type_kernel/MI100/timestamps.csv b/tests/workloads/join_type_kernel/MI100/timestamps.csv index a222669d1d..70168ddc43 100644 --- a/tests/workloads/join_type_kernel/MI100/timestamps.csv +++ b/tests/workloads/join_type_kernel/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,111541,111541,1048576,256,0,0,8,8,16,64,0x0,0x7f92adaaae80,194084901241938,194084901267928,194084901291928,194084901302753 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,111541,111541,1048576,256,0,0,8,8,16,64,0x0,0x7f92adaaae80,194084901304466,194084901373528,194084901392248,194084901393525 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,111541,111541,1048576,256,0,0,8,8,16,64,0x0,0x7f92adaaae80,194084901404696,194084901413848,194084901433048,194084901433981 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1207271,1207271,1048576,256,0,0,8,8,16,64,0x0,0x7f1b5928cec0,1410013407817614,1410013407844900,1410013407869220,1410013407881515 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1207271,1207271,1048576,256,0,0,8,8,16,64,0x0,0x7f1b5928cec0,1410013407881836,1410013407960580,1410013407979300,1410013407980972 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1207271,1207271,1048576,256,0,0,8,8,16,64,0x0,0x7f1b5928cec0,1410013407991583,1410013407999460,1410013408018340,1410013408019745 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv index 3a04c9a50d..9276a887b0 100644 --- a/tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,255986,255986,1048576,256,0,0,8,0,16,64,0x0,0x7fb7bd7d8ec0,27983,27983,16384,65536,13707,1560612,197521716951863,197534469403014,197534469423814,197521733076207 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,255986,255986,1048576,256,0,0,8,0,16,64,0x0,0x7fb7bd7d8ec0,42909,42909,16384,65536,9425,1048676,197521733096034,197534469442374,197534469458214,197521733407794 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,255986,255986,1048576,256,0,0,8,0,16,64,0x0,0x7fb7bd7d8ec0,41713,41713,16384,65536,9886,1048628,197521733437200,197534469518374,197534469534854,197521733601480 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4079368,4079368,1048576,256,0,0,8,0,16,64,0x0,0x7fb8b4c24ec0,28569,28569,16384,65536,13504,1520136,1411006894038570,1411019767037523,1411019767058003,1411006910178913 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4079368,4079368,1048576,256,0,0,8,0,16,64,0x0,0x7fb8b4c24ec0,41376,41376,16384,65536,9285,1048672,1411006910199512,1411019767148243,1411019767164883,1411006910513736 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4079368,4079368,1048576,256,0,0,8,0,16,64,0x0,0x7fb8b4c24ec0,42022,42022,16384,65536,9239,1048608,1411006910543182,1411019767186003,1411019767201683,1411006910707814 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv index eac310db69..185c985ffe 100644 --- a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,256171,256171,1048576,256,0,0,8,0,16,64,0x0,0x7f568c1c0ec0,0,0,0,197522204232008,197534469403014,197534469423814,197522219925467 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,256171,256171,1048576,256,0,0,8,0,16,64,0x0,0x7f568c1c0ec0,0,0,0,197522219945194,197534469442374,197534469458214,197522220218641 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,256171,256171,1048576,256,0,0,8,0,16,64,0x0,0x7f568c1c0ec0,0,0,0,197522220245552,197534469518374,197534469534854,197522220377843 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4079569,4079569,1048576,256,0,0,8,0,16,64,0x0,0x7efe2baf8ec0,0,0,0,1411007376726088,1411019767037523,1411019767058003,1411007392962785 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4079569,4079569,1048576,256,0,0,8,0,16,64,0x0,0x7efe2baf8ec0,0,0,0,1411007392979476,1411019767148243,1411019767164883,1411007393309621 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4079569,4079569,1048576,256,0,0,8,0,16,64,0x0,0x7efe2baf8ec0,0,0,0,1411007393336331,1411019767186003,1411019767201683,1411007393498097 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv index 3ec66409cc..f9f5c68edd 100644 --- a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,256357,256357,1048576,256,0,0,8,0,16,64,0x0,0x7fa7558e0ec0,65536,170284,19010128,197522677930159,197534469403014,197534469423814,197522694066336 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,256357,256357,1048576,256,0,0,8,0,16,64,0x0,0x7fa7558e0ec0,65536,246650,27715904,197522694083328,197534469442374,197534469458214,197522694399366 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,256357,256357,1048576,256,0,0,8,0,16,64,0x0,0x7fa7558e0ec0,65536,270936,30238816,197522694425665,197534469518374,197534469534854,197522694583033 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4079771,4079771,1048576,256,0,0,8,0,16,64,0x0,0x7febb0bc8ec0,65536,167308,18890256,1411007855983531,1411019767037523,1411019767058003,1411007872410086 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4079771,4079771,1048576,256,0,0,8,0,16,64,0x0,0x7febb0bc8ec0,65536,238164,26687088,1411007872428511,1411019767148243,1411019767164883,1411007872722958 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4079771,4079771,1048576,256,0,0,8,0,16,64,0x0,0x7febb0bc8ec0,65536,239132,26817016,1411007872749337,1411019767186003,1411019767201683,1411007872901856 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv index 7766ad598d..c6b8ea4c47 100644 --- a/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,256558,256558,1048576,256,0,0,8,0,16,64,0x0,0x7f3982d4cec0,32768,303049,33928300,197523157025941,197534469403014,197534469423814,197523172794913 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,256558,256558,1048576,256,0,0,8,0,16,64,0x0,0x7f3982d4cec0,32768,579114,64866424,197523172814270,197534469442374,197534469458214,197523173100291 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,256558,256558,1048576,256,0,0,8,0,16,64,0x0,0x7f3982d4cec0,32768,588082,65852356,197523173126430,197534469518374,197534469534854,197523173306040 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4079954,4079954,1048576,256,0,0,8,0,16,64,0x0,0x7fe060840ec0,32768,295367,33086452,1411008337142459,1411019767037523,1411019767058003,1411008353105698 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4079954,4079954,1048576,256,0,0,8,0,16,64,0x0,0x7fe060840ec0,32768,577616,64686436,1411008353123943,1411019767148243,1411019767164883,1411008353462352 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4079954,4079954,1048576,256,0,0,8,0,16,64,0x0,0x7fe060840ec0,32768,577276,64656432,1411008353488963,1411019767186003,1411019767201683,1411008353639227 diff --git a/tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv index 85f2e22670..f2ab09c42c 100644 --- a/tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,256756,256756,1048576,256,0,0,8,0,16,64,0x0,0x7fa46fc68ec0,27731,27731,11030,221856,16384,10910338,129553,0,44147600,197523639048099,197534469403014,197534469423814,197523656028593 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,256756,256756,1048576,256,0,0,8,0,16,64,0x0,0x7fa46fc68ec0,41874,41874,14115,335000,16384,19688539,225944,0,79236504,197523656056957,197534469442374,197534469458214,197523656351574 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,256756,256756,1048576,256,0,0,8,0,16,64,0x0,0x7fa46fc68ec0,44053,44053,13987,352432,16384,20594261,236972,0,82853636,197523656386520,197534469518374,197534469534854,197523656560850 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4080137,4080137,1048576,256,0,0,8,0,16,64,0x0,0x7fd3e7934ec0,28713,28713,11022,229712,16384,11522264,136850,0,46603440,1411008821342308,1411019767037523,1411019767058003,1411008837780104 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4080137,4080137,1048576,256,0,0,8,0,16,64,0x0,0x7fd3e7934ec0,41690,41690,13953,333528,16384,19522526,224323,0,78572160,1411008837806113,1411019767148243,1411019767164883,1411008838114256 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4080137,4080137,1048576,256,0,0,8,0,16,64,0x0,0x7fd3e7934ec0,42336,42336,14014,338696,16384,20130582,229491,0,81006268,1411008838149433,1411019767186003,1411019767201683,1411008838334433 diff --git a/tests/workloads/join_type_kernel/MI200/log.txt b/tests/workloads/join_type_kernel/MI200/log.txt new file mode 100644 index 0000000000..29b2d637f2 --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/log.txt @@ -0,0 +1,739 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/join_type_kernel/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_160754' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160754_4079208' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160754_4079208/input0_results_240321_160754' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160754_4079208/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160754_4079208/input0_results_240321_160754 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_160755' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160755_4079409' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160755_4079409/input0_results_240321_160755' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160755_4079409/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160755_4079409/input0_results_240321_160755 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_160755' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160755_4079611' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160755_4079611/input0_results_240321_160755' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160755_4079611/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160755_4079611/input0_results_240321_160755 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_160756' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160756_4079794' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160756_4079794/input0_results_240321_160756' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160756_4079794/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160756_4079794/input0_results_240321_160756 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_160756' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160756_4079977' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160756_4079977/input0_results_240321_160756' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160756_4079977/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160756_4079977/input0_results_240321_160756 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_160757' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160757_4080160' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160757_4080160/input0_results_240321_160757' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160757_4080160/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160757_4080160/input0_results_240321_160757 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_160757' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160757_4080361' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160757_4080361/input0_results_240321_160757' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160757_4080361/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160757_4080361/input0_results_240321_160757 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_160758' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160758_4080544' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160758_4080544/input0_results_240321_160758' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160758_4080544/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160758_4080544/input0_results_240321_160758 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_160758' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160758_4080745' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160758_4080745/input0_results_240321_160758' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160758_4080745/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160758_4080745/input0_results_240321_160758 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_160759' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160759_4080948' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160759_4080948/input0_results_240321_160759' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160759_4080948/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160759_4080948/input0_results_240321_160759 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_160759' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160759_4081133' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160759_4081133/input0_results_240321_160759' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160759_4081133/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160759_4081133/input0_results_240321_160759 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_160800' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160800_4081334' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160800_4081334/input0_results_240321_160800' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160800_4081334/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160800_4081334/input0_results_240321_160800 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_160800' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160800_4081535' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160800_4081535/input0_results_240321_160800' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160800_4081535/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160800_4081535/input0_results_240321_160800 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_160801' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160801_4081751' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160801_4081751/input0_results_240321_160801' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160801_4081751/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160801_4081751/input0_results_240321_160801 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_160802' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160802_4081952' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160802_4081952/input0_results_240321_160802' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160802_4081952/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160802_4081952/input0_results_240321_160802 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_160803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160803_4082147' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160803_4082147/input0_results_240321_160803' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160803_4082147/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160803_4082147/input0_results_240321_160803 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_160803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160803_4082348' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160803_4082348/input0_results_240321_160803' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160803_4082348/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160803_4082348/input0_results_240321_160803 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_160804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160804_4082551' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160804_4082551/input0_results_240321_160804' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160804_4082551/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160804_4082551/input0_results_240321_160804 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_160804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160804_4082735' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160804_4082735/input0_results_240321_160804' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160804_4082735/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160804_4082735/input0_results_240321_160804 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_160805' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160805_4082918' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160805_4082918/input0_results_240321_160805' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160805_4082918/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160805_4082918/input0_results_240321_160805 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_160805' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160805_4083102' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160805_4083102/input0_results_240321_160805' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160805_4083102/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160805_4083102/input0_results_240321_160805 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_160806' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160806_4083285' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160806_4083285/input0_results_240321_160806' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160806_4083285/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160806_4083285/input0_results_240321_160806 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_160806' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160806_4083478' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160806_4083478/input0_results_240321_160806' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160806_4083478/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160806_4083478/input0_results_240321_160806 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_160807' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160807_4083662' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160807_4083662/input0_results_240321_160807' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160807_4083662/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160807_4083662/input0_results_240321_160807 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/join_type_kernel/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_160807' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/join_type_kernel/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160807_4083847' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160807_4083847/input0_results_240321_160807' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160807_4083847/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160807_4083847/input0_results_240321_160807 + |-> [rocprof] File 'tests/workloads/join_type_kernel/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/join_type_kernel/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/join_type_kernel/MI200/pmc_dispatch_info.csv b/tests/workloads/join_type_kernel/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/join_type_kernel/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/join_type_kernel/MI200/pmc_perf.csv b/tests/workloads/join_type_kernel/MI200/pmc_perf.csv index 237ce3d740..968a7759b8 100644 --- a/tests/workloads/join_type_kernel/MI200/pmc_perf.csv +++ b/tests/workloads/join_type_kernel/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_1,obj_1,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_2,obj_2,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_9,obj_9,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_13,obj_13,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_14,obj_14,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_17,obj_17,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_18,obj_18,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f11a8ec4ec0,0,0,0,1007315,39,0,0,1189616,0,0,0,983513,0,0,0,1163357,34,0,0,1147616,53,0,0,1304235,0,0,0,1077073,0,0,0,1214153,0,0,0,1022398,0,0,0,1068386,0,0,0,1105803,0,0,0,1116189,0,0,0,1070696,27,0,0,1071708,0,0,0,1207237,0,0,0,1120617,0,0,0,1112790,0,0,0,1059857,0,0,0,1139084,0,0,0,1098929,0,0,0,1066184,0,0,0,1133197,140,0,0,1300501,64,0,0,1196834,8,0,0,1119984,0,0,0,1064790,0,0,0,1011992,0,0,0,1267494,0,0,0,1101867,15,0,0,1136857,0,0,0,1086574,61,0,0,1329069,64,0x7f2565a40ec0,0,1238939,4096,4096,0,1321796,4096,4096,0,1141522,4096,4096,0,1279820,4096,4096,0,1086877,4096,4096,0,1365916,4096,4096,0,1185993,4096,4096,0,1280162,4096,4096,0,1333014,4096,4096,0,1118567,4096,4096,0,1144647,4096,4096,0,1083558,4096,4096,0,1006637,4096,4096,0,1438187,4096,4096,0,1299268,4096,4096,0,1353210,4096,4096,0,1385738,4096,4096,0,1209166,4096,4096,0,1009855,4096,4096,0,1262748,4096,4096,0,1126406,4096,4096,0,1135359,4096,4096,0,1421713,4096,4096,0,1139755,4096,4096,0,1505235,4096,4096,0,1201582,4096,4096,0,1286286,4096,4096,0,1227006,4096,4096,0,1129740,4096,4096,0,1136219,4096,4096,0,1051905,4096,4096,0,1406964,4096,4096,64,0x7f5315864ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f57d2d58ec0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,0,28097,0,0,64,0x7ff75c550ec0,226816,128040,16384,0,16384,16384,32768,49152,28351,28351,1942270.0,1348362.0,3425.0,160830.0,1054361.0,0.0,1340808.0,1041641.0,225105,136176,28351,0,28351,0,907232.0,489526.0,0.0,0.0,64,0x7f49b0804ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10546,0,814,28606,0,73239.0,131072.0,0.0,65568.0,64,0x7fbb4b638ec0,1311,117096,0,0,65536,63800,56,1680,64,0x7fc7a1990ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,37032652.0,33925784.0,0.0,64,0x7f77b9620ec0,2247,4096,2247,6343,2316,4096,2316,6412,2307,4096,2307,6403,2258,4096,2258,6354,2305,4096,2305,6401,2321,4096,2321,6417,2268,4096,2268,6364,2303,4096,2303,6399,2305,4096,2305,6401,2248,4096,2248,6344,2322,4096,2322,6418,2309,4100,2313,6409,2263,4096,2263,6359,2309,4096,2309,6405,2378,4097,2379,6475,2272,4096,2272,6368,2270,4096,2270,6366,2321,4096,2321,6417,2271,4096,2271,6367,2299,4096,2299,6395,2279,4096,2279,6375,2285,4096,2285,6381,2273,4097,2274,6370,2432,4098,2434,6530,2266,4096,2266,6362,2269,4096,2269,6365,2321,4096,2321,6417,2273,4096,2273,6369,2296,4096,2296,6392,2276,4096,2276,6372,2287,4097,2288,6384,2278,4096,2278,6374,64,0x7fc48fcfcec0,32768,32768,0,64,0x7f758889cec0,0,0,0,224,0,65536,64195,56,64,0x7f65ea01cec0,10536395,9608540,583791,344064,1591722,0,0,163840,832.0,515136.0,0.0,524288.0,303839.0,32768.0,439353,0,0,10677,131072.0,131072.0,0.0,131072.0,64,0x7f010467cec0,114688,0,32768,32768,16384,16384,65536,49152,28113989.0,87706208.0,39298511.0,131072.0,0.0,251262.0,0,0,15324,317.0,131081.0,0.0,10.0,64,0x7f4cdd6c0ec0,6356,0,4096,6449,0,4096,6342,0,4096,6397,0,4096,6393,0,4096,6409,0,4096,6406,0,4096,6413,0,4096,6412,0,4096,6361,0,4096,6450,0,4096,6343,0,4096,6400,0,4096,6392,0,4096,6419,0,4096,6404,0,4096,6365,0,4096,6397,0,4096,6400,0,4096,6393,0,4096,6391,0,4096,6395,0,4096,6403,0,4096,6556,0,4096,6392,0,4096,6369,0,4096,6397,0,4096,6399,0,4096,6396,0,4096,6390,0,4096,6395,0,4096,6407,0,4096,64,0x7f1533aa4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13188,19029,7031,545,0,26645,204262.0,0.0,73181.0,131081.0,64,0x7f47a23e8ec0,4096,0,0,0,4096,0,96,0,4096,0,3,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,4,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,9,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f60839d8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,966657.0,64,0x7f8798ba0ec0,0,393216,163840,0,0,0,0,0,17846,0.0,0.0,0.0,32768.0,0.0,0.0,406.0,32768.0,4096,16384,352,28073,1977,0,56.0,6.0,0.0,204188.0,64,0x7f58eb278ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,34822.0,46066.0,19470.0,197534469403014,197534469423814 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f11a8ec4ec0,0,0,0,1681864,1157,0,0,2336782,0,0,0,1880973,0,0,0,1739457,0,0,0,2105791,98,0,0,2009773,0,0,0,1417692,0,0,0,1569072,45,0,0,1787526,0,0,0,1664234,327,0,0,2201628,0,0,0,1505290,0,0,0,1645125,0,0,0,1790717,399,0,0,1969953,0,0,0,1808482,0,0,0,2109567,0,0,0,1639341,0,0,0,1611493,27,0,0,2029072,45,0,0,2037365,0,0,0,1964090,0,0,0,1548459,0,0,0,1590182,0,0,0,1681430,0,0,0,1508421,0,0,0,1594495,0,0,0,2017490,294,0,0,2323506,0,0,0,1541346,0,0,0,1708532,0,0,0,1671681,64,0x7f2565a40ec0,0,4104088,2832,2832,0,3377787,2888,2888,0,3154501,2864,2864,0,3691821,2846,2846,0,4274405,2848,2848,0,4078805,2840,2840,0,3832564,2860,2860,0,4344106,2816,2816,0,3777759,2812,2812,0,4215638,2832,2832,0,3372974,2892,2892,0,3513156,2864,2864,0,3319756,2844,2844,0,3725769,2844,2844,0,5032648,2836,2836,0,4076490,2864,2864,0,4442759,2788,2788,0,3998065,2844,2844,0,3291996,2860,2860,0,3732274,2858,2858,0,3725579,2832,2832,0,3790802,2876,2876,0,4323988,2812,2812,0,4531118,2792,2792,0,4215108,2800,2800,0,3480650,2788,2788,0,4051515,2848,2848,0,3345974,2864,2864,0,3962030,2860,2860,0,3277791,2832,2832,0,3759086,2876,2876,0,4003262,2812,2812,64,0x7f5315864ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f57d2d58ec0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,0,41267,0,0,64,0x7ff75c550ec0,304808,208114,16384,0,16384,16384,32768,49152,38100,38100,2981450.0,2420731.0,4870.0,349336.0,1696772.0,0.0,2409153.0,2100771.0,304800,217129,38100,0,38100,0,1219200.0,782406.0,0.0,0.0,64,0x7f49b0804ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20028,0,2682,38394,0,69683.0,131072.0,0.0,45702.0,64,0x7fbb4b638ec0,0,183466,0,0,65536,63800,56,1680,64,0x7fc7a1990ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120711565.0,61038459.0,0.0,64,0x7f77b9620ec0,2178,4096,2178,6274,2156,4096,2156,6252,2178,4096,2178,6274,2192,4096,2192,6288,2167,4096,2167,6263,2188,4096,2188,6284,2170,4097,2171,6267,2170,4096,2170,6266,2172,4096,2172,6268,2178,4096,2178,6274,2157,4096,2157,6253,2176,4099,2179,6275,2192,4098,2194,6290,2170,4096,2170,6266,2249,4097,2250,6346,2173,4096,2173,6269,2189,4096,2189,6285,2185,4096,2185,6281,2177,4096,2177,6273,2189,4096,2189,6285,2179,4096,2179,6275,2201,4096,2201,6297,2176,4098,2178,6274,2189,4096,2189,6285,2194,4096,2194,6290,2188,4096,2188,6284,2190,4096,2190,6286,2177,4096,2177,6273,2188,4096,2188,6284,2176,4096,2176,6272,2204,4097,2205,6301,2180,4096,2180,6276,64,0x7fc48fcfcec0,32768,32768,0,64,0x7f758889cec0,0,0,0,56,0,65536,65536,0,64,0x7f65ea01cec0,18105127,17480878,280185,344064,2621959,0,0,163840,0.0,524288.0,0.0,524288.0,450660.0,32768.0,811541,0,0,11440,91086.0,91086.0,0.0,91086.0,64,0x7f010467cec0,114688,0,32768,32768,16384,16384,65536,49152,58171621.0,205626661.0,50069959.0,131072.0,0.0,611898.0,0,0,25318,21712.0,131081.0,0.0,16.0,64,0x7f4cdd6c0ec0,6275,0,4096,6271,0,4096,6253,0,4096,6292,0,4096,6312,0,4096,6297,0,4096,6244,0,4096,6310,0,4096,6306,0,4096,6278,0,4096,6270,0,4096,6255,0,4096,6298,0,4096,6318,0,4096,6298,0,4096,6244,0,4096,6258,0,4096,6272,0,4096,6307,0,4096,6295,0,4096,6298,0,4096,6283,0,4096,6290,0,4096,6308,0,4096,6309,0,4096,6262,0,4096,6274,0,4096,6305,0,4096,6296,0,4096,6300,0,4096,6290,0,4096,6293,0,4096,64,0x7f1533aa4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,35077,27652,9637,2428,0,41696,200942.0,0.0,69860.0,131082.0,64,0x7f47a23e8ec0,4096,0,655,0,4096,0,2647,0,4096,0,0,0,4096,0,384,0,4097,0,200,0,4096,0,786,0,4096,0,0,0,4096,0,1515,0,4096,0,140,0,4096,0,0,0,4097,0,379,0,4097,0,10,0,4097,0,7,0,4096,0,129,0,4097,0,0,0,4096,0,0,0,4096,0,671,0,4096,0,379,0,4097,0,0,0,4096,0,251,0,4096,0,17,0,4096,0,336,0,4096,0,634,0,4096,0,485,0,4096,0,384,0,4096,0,10,0,4096,0,2050,0,4096,0,0,0,4096,0,0,0,4098,0,0,0,4096,0,77,0,4096,0,0,0,64,0x7f60839d8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2067361.0,64,0x7f8798ba0ec0,0,393216,163840,0,0,0,0,0,29500,0.0,0.0,0.0,32768.0,0.0,0.0,229.0,32768.0,4096,16384,302,40644,2105,0,56.0,10.0,0.0,200748.0,64,0x7f58eb278ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,94206.0,45662.0,0.0,197534469442374,197534469458214 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f11a8ec4ec0,0,0,0,1676454,2428,0,0,2483059,727,0,0,2334287,83,0,0,1904635,1843,0,0,2594182,525,0,0,2145105,1210,0,0,2029494,605,0,0,2044622,272,0,0,2110620,133,0,0,1724892,463,0,0,1964694,81,0,0,1864282,99,0,0,1984387,23,0,0,1692604,300,0,0,1768711,365,0,0,2071225,990,0,0,2056212,775,0,0,2085514,0,0,0,1792482,642,0,0,2009626,0,0,0,1713394,73,0,0,1794106,99,0,0,1728848,384,0,0,2034476,110,0,0,1996001,354,0,0,1938879,1189,0,0,1895653,432,0,0,2095128,2816,0,0,2406156,0,0,0,1435593,546,0,0,2094062,204,0,0,1915341,64,0x7f2565a40ec0,0,3592130,2824,2824,0,3698511,2880,2880,0,3497819,2864,2864,0,4380389,2856,2856,0,4988869,2892,2892,0,4209329,2844,2844,0,3240813,2878,2878,0,4263186,2840,2840,0,3708697,2840,2840,0,3411640,2828,2828,0,3100503,2880,2880,0,3842991,2864,2864,0,4218852,2856,2856,0,4227496,2892,2892,0,4021193,2844,2844,0,3606101,2880,2880,0,3715972,2824,2824,0,3782859,2880,2880,0,3622843,2844,2844,0,4120590,2828,2828,0,3724007,2848,2848,0,3860902,2880,2880,0,4457536,2826,2826,0,4703301,2816,2816,0,4309151,2820,2820,0,3726238,2824,2824,0,3711726,2876,2876,0,3926718,2848,2848,0,3807224,2832,2832,0,3491191,2850,2850,0,3645776,2884,2884,0,3988806,2826,2826,64,0x7f5315864ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f57d2d58ec0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,0,41409,0,0,64,0x7ff75c550ec0,331000,222485,16384,0,16384,16384,32768,49152,41374,41374,3169657.0,2441507.0,4418.0,376238.0,1761790.0,0.0,2429080.0,2119462.0,330992,231875,41374,0,41374,0,1323968.0,775441.0,0.0,0.0,64,0x7f49b0804ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20411,0,2658,38528,0,69749.0,131072.0,0.0,45660.0,64,0x7fbb4b638ec0,0,182840,0,0,65536,63800,56,1680,64,0x7fc7a1990ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119592813.0,61322433.0,0.0,64,0x7f77b9620ec0,2156,4096,2156,6252,2194,4096,2194,6290,2182,4096,2182,6278,2183,4096,2183,6279,2161,4096,2161,6257,2199,4096,2199,6295,2211,4097,2212,6308,2155,4096,2155,6251,2158,4096,2158,6254,2158,4096,2158,6254,2195,4096,2195,6291,2186,4099,2189,6285,2183,4098,2185,6281,2157,4096,2157,6253,2256,4097,2257,6353,2213,4096,2213,6309,2172,4096,2172,6268,2169,4096,2169,6265,2193,4096,2193,6289,2191,4096,2191,6287,2159,4096,2159,6255,2165,4096,2165,6261,2193,4098,2195,6291,2164,4096,2164,6260,2169,4096,2169,6265,2177,4096,2177,6273,2171,4096,2171,6267,2198,4096,2198,6294,2191,4096,2191,6287,2165,4096,2165,6261,2168,4097,2169,6265,2196,4096,2196,6292,64,0x7fc48fcfcec0,32768,32768,0,64,0x7f758889cec0,0,0,0,56,0,65536,65536,0,64,0x7f65ea01cec0,18870452,17817949,708439,344064,2697996,0,0,163840,832.0,515136.0,0.0,524288.0,724474.0,32768.0,906239,0,0,13414,91254.0,91254.0,0.0,91254.0,64,0x7f010467cec0,114688,0,32768,32768,16384,16384,65536,49152,59663501.0,198207422.0,49042649.0,131072.0,0.0,599383.0,0,0,26243,5758.0,131082.0,0.0,18.0,64,0x7f4cdd6c0ec0,6255,0,4096,6276,0,4096,6279,0,4096,6285,0,4096,6314,0,4096,6292,0,4096,6270,0,4096,6267,0,4096,6267,0,4096,6255,0,4096,6275,0,4096,6278,0,4096,6288,0,4096,6312,0,4096,6294,0,4096,6268,0,4096,6262,0,4096,6286,0,4096,6269,0,4096,6281,0,4096,6272,0,4096,6268,0,4096,6273,0,4096,6299,0,4096,6300,0,4096,6264,0,4096,6290,0,4096,6268,0,4096,6286,0,4096,6273,0,4096,6267,0,4096,6275,0,4096,64,0x7f1533aa4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31105,26693,9697,2761,0,40064,200968.0,0.0,69885.0,131083.0,64,0x7f47a23e8ec0,4096,0,120,0,4096,0,153,0,4096,0,89,0,4096,0,241,0,4097,0,245,0,4096,0,578,0,4096,0,16,0,4096,0,856,0,4096,0,304,0,4096,0,0,0,4097,0,288,0,4097,0,285,0,4097,0,119,0,4096,0,912,0,4097,0,531,0,4096,0,421,0,4096,0,0,0,4096,0,8,0,4097,0,90,0,4096,0,1574,0,4096,0,727,0,4096,0,395,0,4096,0,493,0,4096,0,372,0,4096,0,4,0,4096,0,0,0,4096,0,261,0,4096,0,247,0,4096,0,0,0,4098,0,0,0,4096,0,0,0,4096,0,425,0,64,0x7f60839d8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,1994953.0,64,0x7f8798ba0ec0,0,393216,163840,0,0,0,0,0,29389,0.0,0.0,0.0,32768.0,0.0,0.0,222.0,32768.0,4096,16384,302,40513,2024,0,56.0,9.0,0.0,200689.0,64,0x7f58eb278ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,93329.0,45635.0,0.0,197534469518374,197534469534854 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_5,obj_5,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_6,obj_6,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_12,obj_12,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_13,obj_13,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_16,obj_16,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_17,obj_17,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_18,obj_18,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f7970538ec0,0,1249788,4096,4096,0,1262535,4096,4096,0,1043091,4096,4096,0,1348045,4096,4096,0,1197468,4096,4096,0,1690532,4096,4096,0,1309393,4096,4096,0,1283645,4096,4096,0,1128210,4096,4096,0,1141214,4096,4096,0,1222034,4096,4096,0,1048326,4096,4096,0,1186889,4096,4096,0,1185698,4096,4096,0,1310695,4096,4096,0,1719398,4096,4096,0,1147802,4096,4096,0,1267899,4096,4096,0,1127699,4096,4096,0,1394262,4096,4096,0,1034589,4096,4096,0,1173078,4096,4096,0,1362048,4096,4096,0,1234310,4096,4096,0,1180887,4096,4096,0,1145928,4096,4096,0,1060944,4096,4096,0,1169404,4096,4096,0,1249970,4096,4096,0,1024705,4096,4096,0,1005637,4096,4096,0,1264032,4096,4096,64,0x7f83a94b0ec0,4096,0,0,0,4096,0,0,0,4096,0,6,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,90,0,4096,0,24,0,4096,0,0,0,4101,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4097,0,0,0,64,0x7fb84ed94ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10233,0,820,27797,0,73540.0,131072.0,0.0,65568.0,64,0x7f6dc2f94ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13100,19193,8271,549,0,27024,204484.0,0.0,73402.0,131082.0,64,0x7f57e3be4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40811984.0,35605181.0,0.0,64,0x7f9173718ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f0818568ec0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,0,27610,0,0,64,0x7fc9f0ce0ec0,0,0,0,1012247,0,0,0,1144188,0,0,0,1003069,0,0,0,1138579,0,0,0,1180531,4,0,0,1237475,0,0,0,1062627,0,0,0,1128361,0,0,0,1038854,0,0,0,1024182,0,0,0,1039206,0,0,0,1201055,54,0,0,1044948,0,0,0,1171574,0,0,0,1179401,0,0,0,1135409,0,0,0,1077524,0,0,0,1106150,0,0,0,1105303,63,0,0,1204725,127,0,0,1103734,57,0,0,1120126,0,0,0,1080516,0,0,0,1146207,0,0,0,1075682,0,0,0,1100600,0,0,0,1066688,0,0,0,1129653,0,0,0,1137791,58,0,0,1082137,10,0,0,1032273,98,0,0,1251998,64,0x7fee90990ec0,0,0,0,224,0,65536,64241,56,64,0x7f13fcc60ec0,32768,32768,0,64,0x7f18cce3cec0,234608,131991,16384,0,16384,16384,32768,49152,29325,29325,1993438.0,1383266.0,3941.0,174392.0,1085498.0,0.0,1375236.0,1076460.0,232897,140120,29325,0,29325,0,938400.0,497940.0,0.0,0.0,64,0x7f9c5aa74ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,967704.0,64,0x7f644623cec0,0,393216,163840,0,0,0,0,0,17968,0.0,0.0,0.0,32768.0,0.0,0.0,376.0,32768.0,4096,16384,352,28705,2183,0,56.0,8.0,0.0,204334.0,64,0x7f4a67724ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,34296.0,46074.0,19462.0,64,0x7f6fa2578ec0,6364,0,4096,6444,0,4096,6363,0,4096,6358,0,4096,6357,0,4096,6440,0,4096,6374,0,4096,6335,0,4096,6335,0,4096,6370,0,4096,6444,0,4096,6366,0,4096,6359,0,4096,6361,0,4096,6441,0,4096,6374,0,4096,6394,0,4096,6390,0,4096,6376,0,4096,6430,0,4096,6352,0,4096,6381,0,4096,6397,0,4096,6580,0,4096,6413,0,4096,6395,0,4096,6392,0,4096,6379,0,4096,6431,0,4096,6357,0,4096,6385,0,4096,6398,0,4096,64,0x7f2619b38ec0,10525405,9512024,669317,344064,1596885,0,0,163840,832.0,515136.0,0.0,524288.0,253846.0,32768.0,456071,0,0,10997,131072.0,131072.0,0.0,131072.0,64,0x7f5cebe14ec0,2253,4096,2253,6349,2264,4096,2264,6360,2309,4096,2309,6405,2364,4096,2364,6460,2228,4096,2228,6324,2275,4096,2275,6371,2257,4096,2257,6353,2307,4096,2307,6403,2309,4096,2309,6405,2253,4096,2253,6349,2266,4096,2266,6362,2308,4096,2308,6404,2362,4096,2362,6458,2231,4096,2231,6327,2281,4096,2281,6377,2258,4096,2258,6354,2300,4096,2300,6396,2299,4096,2299,6395,2270,4097,2271,6367,2271,4096,2271,6367,2315,4096,2315,6411,2301,4096,2301,6397,2239,4096,2239,6335,2418,4098,2420,6516,2253,4096,2253,6349,2303,4098,2305,6401,2302,4096,2302,6398,2273,4096,2273,6369,2269,4096,2269,6365,2310,4096,2310,6406,2293,4096,2293,6389,2297,4097,2298,6394,64,0x7f205861cec0,114688,0,32768,32768,16384,16384,65536,49152,27793171.0,87664531.0,39578025.0,131072.0,0.0,189345.0,0,0,15801,559.0,131084.0,0.0,16.0,64,0x7fa16b794ec0,1202,124937,0,0,65536,63800,56,1680,1411019767037523,1411019767058003 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f7970538ec0,0,3280378,2804,2804,0,4310426,2842,2842,0,3518331,2868,2868,0,4785751,2884,2884,0,4124683,2896,2896,0,4045245,2852,2852,0,3038907,2868,2868,0,4469663,2832,2832,0,3327781,2832,2832,0,3555130,2800,2800,0,3162389,2834,2834,0,3596330,2868,2868,0,4726539,2870,2870,0,3206114,2900,2900,0,3092872,2850,2850,0,3517641,2868,2868,0,4123365,2824,2824,0,4621553,2868,2868,0,3273393,2840,2840,0,3477417,2824,2824,0,3335650,2856,2856,0,3448831,2884,2884,0,4525446,2836,2836,0,3513837,2824,2824,0,3603258,2824,2824,0,3772083,2824,2824,0,3389636,2872,2872,0,4483207,2840,2840,0,3654434,2824,2824,0,2752429,2856,2856,0,3635991,2882,2882,0,3375753,2840,2840,64,0x7f83a94b0ec0,4096,0,2342,0,4096,0,304,0,4096,0,1044,0,4096,0,550,0,4096,0,53,0,4096,0,633,0,4096,0,0,0,4096,0,939,0,4096,0,345,0,4096,0,386,0,4100,0,365,0,4098,0,289,0,4096,0,1,0,4096,0,129,0,4096,0,65,0,4096,0,415,0,4096,0,230,0,4096,0,567,0,4097,0,73,0,4097,0,1281,0,4096,0,460,0,4096,0,1115,0,4096,0,377,0,4096,0,1334,0,4096,0,199,0,4096,0,4,0,4096,0,329,0,4097,0,2183,0,4096,0,674,0,4097,0,144,0,4096,0,707,0,4097,0,286,0,64,0x7fb84ed94ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20089,0,3180,38140,0,69332.0,131072.0,0.0,45609.0,64,0x7f6dc2f94ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27984,27465,8703,550,0,35392,200954.0,0.0,69881.0,131073.0,64,0x7f57e3be4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118294981.0,58609686.0,0.0,64,0x7f9173718ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f0818568ec0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,0,40970,0,0,64,0x7fc9f0ce0ec0,0,0,0,1470791,186,0,0,1757655,182,0,0,1929910,212,0,0,1732185,361,0,0,2190814,0,0,0,1812384,84,0,0,1523761,0,0,0,1561372,0,0,0,1723381,0,0,0,1710769,268,0,0,1652805,0,0,0,1344456,144,0,0,1767763,0,0,0,1908379,104,0,0,1846315,153,0,0,1994987,91,0,0,1899320,40,0,0,1817062,269,0,0,1547681,427,0,0,2068071,99,0,0,1822468,797,0,0,2093804,0,0,0,1572890,0,0,0,2081393,0,0,0,1740065,119,0,0,1829646,36,0,0,1993512,280,0,0,1703845,817,0,0,2289631,50,0,0,1803876,0,0,0,1327788,0,0,0,1765127,64,0x7fee90990ec0,0,0,0,56,0,65536,65536,0,64,0x7f13fcc60ec0,32768,32768,0,64,0x7f18cce3cec0,328744,220536,16384,0,16384,16384,32768,49152,41092,41092,3144404.0,2483661.0,4095.0,360217.0,1746504.0,0.0,2472648.0,2165579.0,328736,230313,41092,0,41092,0,1314944.0,783067.0,0.0,0.0,64,0x7f9c5aa74ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2052855.0,64,0x7f644623cec0,0,393216,163840,0,0,0,0,0,29456,0.0,0.0,0.0,32768.0,0.0,0.0,223.0,32768.0,4096,16384,302,40845,1968,0,56.0,11.0,0.0,200485.0,64,0x7f4a67724ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,84165.0,45512.0,0.0,64,0x7f6fa2578ec0,6260,0,4096,6256,0,4096,6252,0,4096,6258,0,4096,6259,0,4096,6316,0,4096,6267,0,4096,6260,0,4096,6261,0,4096,6261,0,4096,6263,0,4096,6256,0,4096,6261,0,4096,6262,0,4096,6324,0,4096,6270,0,4096,6309,0,4096,6277,0,4096,6258,0,4096,6275,0,4096,6277,0,4096,6265,0,4096,6273,0,4096,6258,0,4096,6265,0,4096,6312,0,4096,6276,0,4096,6262,0,4096,6276,0,4096,6275,0,4096,6268,0,4096,6281,0,4096,64,0x7f2619b38ec0,19321277,18223536,753677,344064,2746152,0,0,163840,832.0,515136.0,0.0,524288.0,663593.0,32768.0,978903,0,0,12811,90920.0,90920.0,0.0,90920.0,64,0x7f5cebe14ec0,2212,4096,2212,6308,2207,4096,2207,6303,2175,4097,2176,6272,2205,4096,2205,6301,2173,4096,2173,6269,2177,4096,2177,6273,2193,4096,2193,6289,2173,4096,2173,6269,2178,4096,2178,6274,2211,4096,2211,6307,2213,4096,2213,6309,2177,4098,2179,6275,2208,4096,2208,6304,2172,4096,2172,6268,2182,4096,2182,6278,2197,4096,2197,6293,2184,4096,2184,6280,2196,4096,2196,6292,2204,4097,2205,6301,2195,4096,2195,6291,2194,4096,2194,6290,2175,4096,2175,6271,2178,4096,2178,6274,2170,4096,2170,6266,2176,4096,2176,6272,2187,4098,2189,6285,2198,4096,2198,6294,2210,4097,2211,6307,2197,4096,2197,6293,2196,4096,2196,6292,2180,4096,2180,6276,2232,4097,2233,6329,64,0x7f205861cec0,114688,0,32768,32768,16384,16384,65536,49152,58028994.0,195837600.0,52048905.0,131072.0,0.0,496576.0,0,0,25992,12030.0,131084.0,0.0,22.0,64,0x7fa16b794ec0,0,199773,0,0,65536,63800,56,1680,1411019767148243,1411019767164883 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f7970538ec0,0,4255713,2848,2848,0,3522978,2872,2872,0,3768091,2872,2872,0,4182191,2870,2870,0,3149126,2868,2868,0,3885342,2844,2844,0,4457783,2876,2876,0,5000898,2832,2832,0,3549131,2836,2836,0,2947017,2846,2846,0,3575754,2876,2876,0,3453562,2872,2872,0,4497001,2864,2864,0,3323510,2868,2868,0,3598079,2844,2844,0,3501185,2878,2878,0,3714425,2822,2822,0,3529160,2864,2864,0,4563865,2842,2842,0,4138032,2844,2844,0,3955602,2840,2840,0,4302820,2876,2876,0,3121104,2792,2792,0,3291568,2812,2812,0,3065944,2812,2812,0,3129128,2816,2816,0,3661527,2862,2862,0,3929273,2846,2846,0,3652974,2842,2842,0,3520714,2838,2838,0,3446501,2876,2876,0,4268465,2792,2792,64,0x7f83a94b0ec0,4096,0,993,0,4096,0,1150,0,4096,0,138,0,4096,0,515,0,4096,0,64,0,4096,0,124,0,4096,0,285,0,4096,0,90,0,4096,0,338,0,4096,0,634,0,4099,0,263,0,4098,0,253,0,4096,0,124,0,4096,0,208,0,4096,0,647,0,4096,0,707,0,4096,0,805,0,4096,0,5,0,4097,0,286,0,4097,0,160,0,4096,0,328,0,4096,0,583,0,4096,0,413,0,4096,0,519,0,4096,0,782,0,4096,0,66,0,4096,0,113,0,4097,0,426,0,4096,0,825,0,4097,0,20,0,4096,0,320,0,4097,0,565,0,64,0x7fb84ed94ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,23615,0,3185,39930,0,70428.0,131072.0,0.0,45690.0,64,0x7f6dc2f94ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,33639,28163,9740,2905,0,40269,201022.0,0.0,69938.0,131084.0,64,0x7f57e3be4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,124245029.0,67304627.0,0.0,64,0x7f9173718ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f0818568ec0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,0,40614,0,0,64,0x7fc9f0ce0ec0,1428,0,0,2435001,356,0,0,2461566,961,0,0,2307278,606,0,0,2144215,653,0,0,2061861,108,0,0,2074131,0,0,0,1600187,0,0,0,1849491,2026,0,0,2664553,16,0,0,1834756,988,0,0,2421230,0,0,0,1614449,360,0,0,2047208,335,0,0,1645436,0,0,0,1882305,103,0,0,2067880,33,0,0,1986246,0,0,0,1665969,0,0,0,1568877,503,0,0,2303593,1642,0,0,2383483,1367,0,0,2375781,0,0,0,2059109,0,0,0,2176332,94,0,0,2325187,158,0,0,1755558,109,0,0,1899537,151,0,0,1976567,158,0,0,2057126,2200,0,0,2443645,3178,0,0,2481573,709,0,0,2380951,64,0x7fee90990ec0,0,0,0,56,0,65536,65536,0,64,0x7f13fcc60ec0,32768,32768,0,64,0x7f18cce3cec0,325768,217915,16384,0,16384,16384,32768,49152,40720,40720,3105700.0,2406839.0,4558.0,334251.0,1791006.0,0.0,2395101.0,2084493.0,325760,226531,40720,0,40720,0,1303040.0,770466.0,0.0,0.0,64,0x7f9c5aa74ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2110300.0,64,0x7f644623cec0,0,393216,163840,0,0,0,0,0,29610,0.0,0.0,0.0,32768.0,0.0,0.0,219.0,32768.0,4096,16384,302,41090,2018,0,56.0,11.0,0.0,200699.0,64,0x7f4a67724ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,117063.0,45600.0,0.0,64,0x7f6fa2578ec0,6309,0,4096,6310,0,4096,6258,0,4096,6286,0,4096,6268,0,4096,6289,0,4096,6246,0,4096,6293,0,4096,6295,0,4096,6310,0,4096,6315,0,4096,6263,0,4096,6287,0,4096,6263,0,4096,6291,0,4096,6248,0,4096,6272,0,4096,6281,0,4096,6278,0,4096,6297,0,4096,6273,0,4096,6273,0,4096,6268,0,4096,6315,0,4096,6317,0,4096,6277,0,4096,6284,0,4096,6283,0,4096,6302,0,4096,6275,0,4096,6276,0,4096,6273,0,4096,64,0x7f2619b38ec0,19779006,18428483,1006459,344064,2849950,0,0,163840,832.0,515146.0,0.0,524288.0,535601.0,32768.0,1007909,0,0,13891,91324.0,91324.0,0.0,91324.0,64,0x7f5cebe14ec0,2166,4096,2166,6262,2177,4096,2177,6273,2176,4097,2177,6273,2149,4096,2149,6245,2231,4096,2231,6327,2218,4096,2218,6314,2164,4096,2164,6260,2160,4096,2160,6256,2159,4096,2159,6255,2165,4096,2165,6261,2180,4096,2180,6276,2176,4098,2178,6274,2149,4096,2149,6245,2223,4096,2223,6319,2222,4096,2222,6318,2165,4096,2165,6261,2160,4096,2160,6256,2161,4096,2161,6257,2133,4097,2134,6230,2173,4096,2173,6269,2181,4096,2181,6277,2169,4096,2169,6265,2192,4096,2192,6288,2238,4096,2238,6334,2238,4096,2238,6334,2162,4098,2164,6260,2160,4096,2160,6256,2134,4097,2135,6231,2177,4096,2177,6273,2186,4096,2186,6282,2172,4096,2172,6268,2251,4097,2252,6348,64,0x7f205861cec0,114688,0,32768,32768,16384,16384,65536,49152,58841672.0,202403042.0,49940943.0,131072.0,0.0,547089.0,0,0,26075,9817.0,131084.0,0.0,22.0,64,0x7fa16b794ec0,0,196659,0,0,65536,63800,56,1680,1411019767186003,1411019767201683 diff --git a/tests/workloads/join_type_kernel/MI200/roofline.csv b/tests/workloads/join_type_kernel/MI200/roofline.csv index 7b3165d959..445182ed84 100644 --- a/tests/workloads/join_type_kernel/MI200/roofline.csv +++ b/tests/workloads/join_type_kernel/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.448,1387.9089,1388.9871,5016.7466,5013.8638,5019.6294,9226.7217,9226.0068,9227.4365,18059.045,18058.148,18059.941,20942.623,20882.143,21003.104,20269.439,20268.814,20270.064,170476.59,170471.94,170481.25,164897.83,164892.17,164903.48,41427.602,41426.875,41428.328,41486.352,41485.453,41487.25,166360.88,165867.45,166854.3 -1,1389.4307,1388.9183,1389.943,5028.0605,5026.0166,5030.1045,9234.3291,9233.6504,9235.0078,18092.57,18089.195,18095.945,20972.26,20905.045,21039.475,20293.436,20292.846,20294.025,170832.91,170827.86,170837.95,165101.39,165098.03,165104.75,41481.762,41480.953,41482.57,41539.949,41538.82,41541.078,166855.14,166852.22,166858.06 -2,1388.6045,1387.962,1389.2469,5036.2583,5033.9248,5038.5918,9262.8096,9262.124,9263.4951,18108.311,18107.41,18109.211,21047.432,21047.041,21047.822,20350.363,20349.795,20350.932,171113.05,171108.91,171117.19,165496.91,165492.88,165500.94,41579.336,41578.238,41580.434,41638.969,41637.676,41640.262,166966.22,166370.66,167561.78 -3,1388.9966,1388.4054,1389.5878,5031.7676,5030.1387,5033.3965,9239.9658,9239.4111,9240.5205,18026.248,18022.998,18029.498,21033.547,21033.039,21034.055,20311.645,20310.9,20312.389,171005.2,171001.67,171008.73,165217.73,165214.55,165220.92,41441.426,41287.215,41595.637,41579.938,41579.328,41580.547,167016.2,167014.12,167018.28 +0,1388.8696,1388.2517,1389.4875,5016.3364,5013.4775,5019.1953,9226.4629,9225.8838,9227.042,17716.154,17713.24,17719.068,20947.631,20887.26,21008.002,20275.967,20275.412,20276.521,170548.78,170545.11,170552.45,164946.52,164941.38,164951.66,41444.496,41443.984,41445.008,41498.934,41497.922,41499.945,166423.8,165932.42,166915.17 +1,1389.0171,1388.4265,1389.6077,5027.6577,5025.8765,5029.439,9234.5,9233.7549,9235.2451,18235.537,18233.129,18237.945,20980.029,20912.494,21047.564,20300.5,20300.018,20300.982,170890.59,170886.62,170894.56,165104.64,165101,165108.28,41493.906,41492.832,41494.98,41548.566,41547.68,41549.453,166914.86,166910.55,166919.17 +2,1388.0889,1387.5483,1388.6294,5037.3511,5035.2812,5039.4209,9261.4072,9260.5811,9262.2334,18219.209,18218.299,18220.119,21053.266,21052.859,21053.672,20351.578,20350.986,20352.17,171142.64,171139.2,171146.08,165546.12,165543.11,165549.14,41591.863,41590.57,41593.156,41655.738,41654.684,41656.793,167018.7,166421,167616.41 +3,1388.8175,1388.2073,1389.4277,5032.9917,5031.2617,5034.7217,9237.9424,9237.2607,9238.624,18325.16,18324.49,18325.83,21032.465,21032.104,21032.826,20307.248,20306.738,20307.758,171041.78,171037.45,171046.11,165156.92,165152.19,165161.66,41433.641,41278.996,41588.285,41572.273,41571.234,41573.312,166950.2,166947.11,166953.3 diff --git a/tests/workloads/join_type_kernel/MI200/sysinfo.csv b/tests/workloads/join_type_kernel/MI200/sysinfo.csv index bc3b3ff1cf..9fd5a9a343 100644 --- a/tests/workloads/join_type_kernel/MI200/sysinfo.csv +++ b/tests/workloads/join_type_kernel/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -join_type_kernel,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:03:08 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +join_type_kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:07:54 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/join_type_kernel/MI200/timestamps.csv b/tests/workloads/join_type_kernel/MI200/timestamps.csv index 3e4c203ff4..c10032db4b 100644 --- a/tests/workloads/join_type_kernel/MI200/timestamps.csv +++ b/tests/workloads/join_type_kernel/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,260525,260525,1048576,256,0,0,8,0,16,64,0x0,0x7fb4f00c4ec0,197534469378582,197534469403014,197534469423814,197534469440359 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,260525,260525,1048576,256,0,0,8,0,16,64,0x0,0x7fb4f00c4ec0,197534469434578,197534469442374,197534469458214,197534469515060 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,260525,260525,1048576,256,0,0,8,0,16,64,0x0,0x7fb4f00c4ec0,197534469468642,197534469518374,197534469534854,197534469536010 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4084007,4084007,1048576,256,0,0,8,0,16,64,0x0,0x7fd8da020ec0,1411019767012459,1411019767037523,1411019767058003,1411019767069737 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4084007,4084007,1048576,256,0,0,8,0,16,64,0x0,0x7fd8da020ec0,1411019767069126,1411019767148243,1411019767164883,1411019767166240 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4084007,4084007,1048576,256,0,0,8,0,16,64,0x0,0x7fd8da020ec0,1411019767176609,1411019767186003,1411019767201683,1411019767203029 diff --git a/tests/workloads/kernel/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel/MI100/SQ_IFETCH_LEVEL.csv index 22456dbcab..9748a5c7b6 100644 --- a/tests/workloads/kernel/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel/MI100/SQ_IFETCH_LEVEL.csv @@ -1 +1,4 @@ -Index,KernelName +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295056,1295056,1048576,256,0,0,8,8,16,64,0x0,0x7fcafc83cec0,47758,47758,16384,65536,14395,1831576,1414609382362391,1414621055425142,1414621055449622,1414609390882981 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295056,1295056,1048576,256,0,0,8,8,16,64,0x0,0x7fcafc83cec0,46493,46493,16384,65536,8138,1048588,1414609390906726,1414621055537142,1414621055556022,1414609391222231 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295056,1295056,1048576,256,0,0,8,8,16,64,0x0,0x7fcafc83cec0,44994,44994,16384,65536,8169,1048584,1414609391254421,1414621055576182,1414621055595542,1414609391431225 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel/MI100/SQ_INST_LEVEL_LDS.csv similarity index 52% rename from tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_LDS.csv rename to tests/workloads/kernel/MI100/SQ_INST_LEVEL_LDS.csv index f883ac47e7..9ff8ef2bdb 100644 --- a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,358586,358586,1048576,256,0,0,8,0,16,64,0x0,0x7fce8eef4ec0,0,0,0,199949379551109,199961732754864,199961732775184,199949395620397 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,358586,358586,1048576,256,0,0,8,0,16,64,0x0,0x7fce8eef4ec0,0,0,0,199949395646166,199961732860464,199961732876784,199949395893174 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,358586,358586,1048576,256,0,0,8,0,16,64,0x0,0x7fce8eef4ec0,0,0,0,199949395919734,199961732897264,199961732913104,199949396052224 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295257,1295257,1048576,256,0,0,8,8,16,64,0x0,0x7ff0afd60ec0,0,0,0,1414609872531785,1414621055425142,1414621055449622,1414609880166996 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295257,1295257,1048576,256,0,0,8,8,16,64,0x0,0x7ff0afd60ec0,0,0,0,1414609880186282,1414621055537142,1414621055556022,1414609880519821 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295257,1295257,1048576,256,0,0,8,8,16,64,0x0,0x7ff0afd60ec0,0,0,0,1414609880548024,1414621055576182,1414621055595542,1414609880734476 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel/MI100/SQ_INST_LEVEL_SMEM.csv similarity index 50% rename from tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_SMEM.csv rename to tests/workloads/kernel/MI100/SQ_INST_LEVEL_SMEM.csv index aabdafc9b1..422281af80 100644 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189497,189497,1048576,256,0,0,8,8,16,64,0x0,0x7f84a049ae80,65536,212580,27329616,194328661888318,194339836161015,194339836185335,194328669468581 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189497,189497,1048576,256,0,0,8,8,16,64,0x0,0x7f84a049ae80,65536,174110,22221416,194328669488829,194339836365335,194339836384535,194328669746277 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189497,189497,1048576,256,0,0,8,8,16,64,0x0,0x7f84a049ae80,65536,175038,22381160,194328669774400,194339836406935,194339836425975,194328669923212 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295459,1295459,1048576,256,0,0,8,8,16,64,0x0,0x7fbaa9898ec0,65536,192926,24614264,1414610346774400,1414621055425142,1414621055449622,1414610354390535 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295459,1295459,1048576,256,0,0,8,8,16,64,0x0,0x7fbaa9898ec0,65536,170544,21889328,1414610354409831,1414621055537142,1414621055556022,1414610354715538 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295459,1295459,1048576,256,0,0,8,8,16,64,0x0,0x7fbaa9898ec0,65536,173974,22234656,1414610354743811,1414621055576182,1414621055595542,1414610354923470 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel/MI100/SQ_INST_LEVEL_VMEM.csv similarity index 50% rename from tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_VMEM.csv rename to tests/workloads/kernel/MI100/SQ_INST_LEVEL_VMEM.csv index 4cd2c1dd12..ca06a74c3b 100644 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,194046,194046,1048576,256,0,0,8,8,16,64,0x0,0x7f79e60bce80,32768,651688,83428332,194342851989768,194353571654480,194353571678800,194342859796379 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,194046,194046,1048576,256,0,0,8,8,16,64,0x0,0x7f79e60bce80,32768,670969,85898616,194342859817529,194353571699280,194353571718320,194342860100144 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,194046,194046,1048576,256,0,0,8,8,16,64,0x0,0x7f79e60bce80,32768,680763,87111400,194342860128348,194353571787600,194353571806320,194342860305774 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295661,1295661,1048576,256,0,0,8,8,16,64,0x0,0x7fcdb12dcec0,32768,664178,85014096,1414610810961751,1414621055425142,1414621055449622,1414610818650923 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295661,1295661,1048576,256,0,0,8,8,16,64,0x0,0x7fcdb12dcec0,32768,662767,84821212,1414610818672203,1414621055537142,1414621055556022,1414610818960106 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295661,1295661,1048576,256,0,0,8,8,16,64,0x0,0x7fcdb12dcec0,32768,655809,83963416,1414610818988480,1414621055576182,1414621055595542,1414610819205870 diff --git a/tests/workloads/kernel/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel/MI100/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..39b2c23c48 --- /dev/null +++ b/tests/workloads/kernel/MI100/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1295847,1295847,1048576,256,0,0,8,8,16,64,0x0,0x7f5c3f6e4ec0,48355,48355,17730,386848,16384,24958385,233718,0,100367700,1414611287019490,1414621055425142,1414621055449622,1414611294707580 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1295847,1295847,1048576,256,0,0,8,8,16,64,0x0,0x7f5c3f6e4ec0,43528,43528,13690,348232,16384,25762917,238429,0,103589552,1414611294736925,1414621055537142,1414621055556022,1414611295058863 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1295847,1295847,1048576,256,0,0,8,8,16,64,0x0,0x7f5c3f6e4ec0,43639,43639,13971,349120,16384,25009170,233467,0,100574040,1414611295096984,1414621055576182,1414621055595542,1414611295279148 diff --git a/tests/workloads/kernel/MI100/log.txt b/tests/workloads/kernel/MI100/log.txt new file mode 100644 index 0000000000..62ed8cf2b7 --- /dev/null +++ b/tests/workloads/kernel/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: ['vecCopy'] +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_170755' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170755_1294896' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170755_1294896/input0_results_240321_170755' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170755_1294896/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170755_1294896/input0_results_240321_170755 + |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_170755' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170755_1295097' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170755_1295097/input0_results_240321_170755' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170755_1295097/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170755_1295097/input0_results_240321_170755 + |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_170756' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170756_1295299' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170756_1295299/input0_results_240321_170756' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170756_1295299/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170756_1295299/input0_results_240321_170756 + |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_170756' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170756_1295501' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170756_1295501/input0_results_240321_170756' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170756_1295501/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170756_1295501/input0_results_240321_170756 + |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_170757' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170757_1295687' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170757_1295687/input0_results_240321_170757' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170757_1295687/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170757_1295687/input0_results_240321_170757 + |-> [rocprof] File 'tests/workloads/kernel/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_170757' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170757_1295888' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170757_1295888/input0_results_240321_170757' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170757_1295888/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170757_1295888/input0_results_240321_170757 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_170758' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170758_1296091' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170758_1296091/input0_results_240321_170758' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170758_1296091/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170758_1296091/input0_results_240321_170758 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_170758' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170758_1296294' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170758_1296294/input0_results_240321_170758' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170758_1296294/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170758_1296294/input0_results_240321_170758 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_170759' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170759_1296495' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170759_1296495/input0_results_240321_170759' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170759_1296495/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170759_1296495/input0_results_240321_170759 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_170759' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170759_1296697' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170759_1296697/input0_results_240321_170759' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170759_1296697/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170759_1296697/input0_results_240321_170759 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_170800' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170800_1296901' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170800_1296901/input0_results_240321_170800' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170800_1296901/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170800_1296901/input0_results_240321_170800 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_170801' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170801_1297099' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170801_1297099/input0_results_240321_170801' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170801_1297099/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170801_1297099/input0_results_240321_170801 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_170801' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170801_1297303' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170801_1297303/input0_results_240321_170801' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170801_1297303/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170801_1297303/input0_results_240321_170801 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_170802' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170802_1297506' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170802_1297506/input0_results_240321_170802' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170802_1297506/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170802_1297506/input0_results_240321_170802 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_170803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170803_1297703' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170803_1297703/input0_results_240321_170803' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170803_1297703/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170803_1297703/input0_results_240321_170803 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_170803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170803_1297890' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170803_1297890/input0_results_240321_170803' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170803_1297890/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170803_1297890/input0_results_240321_170803 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_170804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170804_1298091' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170804_1298091/input0_results_240321_170804' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170804_1298091/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170804_1298091/input0_results_240321_170804 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_170804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170804_1298276' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170804_1298276/input0_results_240321_170804' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170804_1298276/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170804_1298276/input0_results_240321_170804 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_170805' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170805_1298477' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170805_1298477/input0_results_240321_170805' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170805_1298477/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170805_1298477/input0_results_240321_170805 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_170805' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170805_1298679' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170805_1298679/input0_results_240321_170805' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170805_1298679/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170805_1298679/input0_results_240321_170805 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_170806' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170806_1298868' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170806_1298868/input0_results_240321_170806' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170806_1298868/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170806_1298868/input0_results_240321_170806 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_170806' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170806_1299070' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170806_1299070/input0_results_240321_170806' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170806_1299070/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170806_1299070/input0_results_240321_170806 + |-> [rocprof] File 'tests/workloads/kernel/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_170807' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170807_1299273' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170807_1299273/input0_results_240321_170807' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170807_1299273/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170807_1299273/input0_results_240321_170807 + |-> [rocprof] File 'tests/workloads/kernel/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt index 7000361619..3b68e4a38c 100644 --- a/tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ b/tests/workloads/kernel/MI100/perfmon/SQ_IFETCH_LEVEL.txt @@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PRE gpu: range: -kernel: "vecCopy(double*,,double*,,double*,,int,,int),[clone,.kd]" +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt index 08439eedce..f0b07be064 100644 --- a/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt +++ b/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_LDS.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt index 6cca322d4e..b65eec769f 100644 --- a/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt +++ b/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt index e527ad31ba..3fa3c03388 100644 --- a/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt +++ b/tests/workloads/kernel/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt index 3f8e04adb3..8661e665cb 100644 --- a/tests/workloads/kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt +++ b/tests/workloads/kernel/MI100/perfmon/SQ_LEVEL_WAVES.txt @@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVE gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_0.txt index 202141726e..41b9b08d03 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_0.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_0.txt @@ -2,4 +2,4 @@ pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_1.txt index 6f289aa046..fb139262ad 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_1.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_1.txt @@ -2,4 +2,4 @@ pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_10.txt index a00555d953..8fbda70008 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_10.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_10.txt @@ -2,4 +2,4 @@ pmc: TCC_EA_ATOMIC_LEVEL_sum gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_11.txt index 062fc9644a..91838b92f1 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_11.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_11.txt @@ -2,4 +2,4 @@ pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATO gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_12.txt index e0698dbf57..3f8f0de0e8 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_12.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_12.txt @@ -2,4 +2,4 @@ pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_13.txt index 77ad088669..8e4abc1269 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_13.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_13.txt @@ -2,4 +2,4 @@ pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_14.txt index d0628bb948..19aada1248 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_14.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_14.txt @@ -2,4 +2,4 @@ pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_15.txt index 343869c5f1..d25d8f61df 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_15.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_15.txt @@ -2,4 +2,4 @@ pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_R gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt index a74cefd281..8f3a4cf638 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_16.txt @@ -2,4 +2,4 @@ pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] T gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_2.txt index 2180ee3f63..635f74c7f7 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_2.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_2.txt @@ -2,4 +2,4 @@ pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_3.txt index 8f1ba90d04..00d2b875c5 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_3.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_3.txt @@ -2,4 +2,4 @@ pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_4.txt index 9a82481329..6d5e9a4740 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_4.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_4.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH S gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_5.txt index bbc1f21123..f060cf740c 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_5.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_5.txt @@ -2,4 +2,4 @@ pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_A gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_6.txt index b6368182b4..b7558b5b08 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_6.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_6.txt @@ -2,4 +2,4 @@ pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYC gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_7.txt index 3f7673fd23..73d19b31c4 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_7.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_7.txt @@ -2,4 +2,4 @@ pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_8.txt index facba6bd95..8c70145766 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_8.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_8.txt @@ -2,4 +2,4 @@ pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_W gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/kernel/MI100/perfmon/pmc_perf_9.txt index d458645ea4..07e1e87f12 100644 --- a/tests/workloads/kernel/MI100/perfmon/pmc_perf_9.txt +++ b/tests/workloads/kernel/MI100/perfmon/pmc_perf_9.txt @@ -2,4 +2,4 @@ pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/perfmon/timestamps.txt b/tests/workloads/kernel/MI100/perfmon/timestamps.txt index 676cca1b80..2970e26c4e 100644 --- a/tests/workloads/kernel/MI100/perfmon/timestamps.txt +++ b/tests/workloads/kernel/MI100/perfmon/timestamps.txt @@ -2,4 +2,4 @@ pmc: gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel/MI100/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/kernel/MI100/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/kernel/MI100/pmc_perf.csv b/tests/workloads/kernel/MI100/pmc_perf.csv new file mode 100644 index 0000000000..e74bdb17fb --- /dev/null +++ b/tests/workloads/kernel/MI100/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_1,obj_1,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_3,obj_3,TCC_EA_ATOMIC_LEVEL_sum,wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_6,obj_6,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_7,obj_7,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_8,obj_8,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_11,obj_11,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_12,obj_12,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_13,obj_13,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_14,obj_14,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_15,obj_15,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_16,obj_16,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f16d0bf8ec0,131072.0,131072.0,0.0,2615278.0,0.0,0.0,123379904.0,62305292.0,64,0x7fc87a4f0ec0,32768,0,0,0,16384,16384,393216,22515878,960.0,513898.0,0.0,524288.0,989354.0,32768.0,0,0,0,16851,131072.0,131072.0,0.0,131072.0,64,0x7f75bc214ec0,386632,229686,3367615,16384,25020769,144,48,0,48328,48328,3797486.0,3002822.0,6413.0,881838.0,2048958.0,0.0,2993839.0,2682444.0,385311,239640,48328,0,48328,0,1546496.0,949723.0,0.0,0.0,64,0x7f5fdcae4ec0,0.0,64,0x7f710323cec0,0,4898961,4096,4096,0,4768675,4096,4096,0,4439123,4096,4096,0,2801723,4096,4096,0,4323529,4096,4096,0,4721290,4096,4096,0,3698615,4096,4096,0,4051742,4096,4096,0,3552294,4096,4096,0,4319020,4096,4096,0,4523357,4096,4096,0,4669698,4096,4096,0,4915318,4096,4096,0,4138758,4096,4096,0,3045545,4096,4096,0,2948476,4096,4096,0,4203904,4096,4096,0,5348884,4096,4096,0,3211752,4096,4096,0,4647416,4096,4096,0,3455650,4096,4096,0,4727791,4096,4096,0,3700007,4096,4096,0,4148715,4096,4096,0,3752770,4096,4096,0,4102383,4096,4096,0,3226830,4096,4096,0,3368687,4096,4096,0,4323847,4096,4096,0,4393998,4096,4096,0,3320188,4096,4096,0,3565744,4096,4096,64,0x7f35434c4ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8480,4384,8480,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fc0d8dd0ec0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,0,48915,0,0,64,0x7f9424684ec0,0,0,192,0,65536,64467,48,1319,33754,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,564,49766,1844,0,48.0,410.0,0.0,262288.0,64,0x7fe3fa2d4ec0,196818,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11381,27765,9852,588,0,47748,262673.0,0.0,188.0,262485.0,64,0x7f087f044ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48432,0,131600.0,131072.0,0.0,131104.0,64,0x7f3ab1be8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f0593688ec0,2459,0,0,1764810,1979,0,0,1838578,1535,0,0,1657882,6075,0,0,2100968,818,0,0,1558548,4760,0,0,2047977,1267,0,0,1711073,4361,0,0,2058461,2862,0,0,1828486,1253,0,0,1708143,5248,0,0,2076818,1311,0,0,1756819,2393,0,0,1946677,2057,0,0,1825813,1407,0,0,1701290,5980,0,0,2117540,1854,0,0,1762775,1058,0,0,1692848,2214,0,0,1814230,4425,0,0,2003558,2710,0,0,1839791,3176,0,0,1918853,1564,0,0,1779929,3413,0,0,1975162,3483,0,0,1877349,1826,0,0,1685642,1922,0,0,1772035,4838,0,0,1946711,1178,0,0,1676592,1097,0,0,1627412,2148,0,0,1764064,3811,0,0,1960061,64,0x7f028639cec0,4096,0,3926,0,4096,0,0,0,4096,0,1508,0,4099,0,774,0,4096,0,1593,0,4096,0,1300,0,4096,0,0,0,4096,0,1608,0,4096,0,1614,0,4096,0,900,0,4144,0,309,0,4096,0,3144,0,4096,0,233,0,4096,0,841,0,4096,0,244,0,4096,0,454,0,4096,0,46,0,4144,0,1553,0,4096,0,1746,0,4096,0,1720,0,4096,0,1491,0,4096,0,123,0,4097,0,0,0,4096,0,216,0,4096,0,2896,0,4216,0,6921,0,4096,0,189,0,4096,0,1180,0,4096,0,704,0,4096,0,794,0,4096,0,4106,0,4096,0,1290,0,64,0x7f2a00204ec0,2418593,360448,163840,0,0,180224,114688,0,68874994.0,193039936.0,77703498.0,131072.0,0.0,596428.0,0,0,26692,74658.0,0.0,0.0,74658.0,64,0x7fee0f1e4ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86798.0,44274.0,131112.0,0.0,64,0x7fefb359cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,52941.0,121137.0,64,0x7efccbc90ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131484.0,0.0,816.0,131483.0,1414621055425142,1414621055449622 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f16d0bf8ec0,131072.0,131072.0,0.0,2665690.0,0.0,0.0,107481255.0,47596765.0,64,0x7fc87a4f0ec0,32768,0,0,0,16384,16384,393216,23526151,960.0,513914.0,0.0,524288.0,1160583.0,32768.0,0,0,0,14184,86733.0,86733.0,0.0,86733.0,64,0x7f75bc214ec0,350920,232945,3410379,16384,25380738,0,48,0,43864,43864,3782958.0,3130994.0,6703.0,986793.0,2118712.0,0.0,3122395.0,2810966.0,350912,242193,43864,0,43864,0,1403648.0,825675.0,0.0,0.0,64,0x7f5fdcae4ec0,0.0,64,0x7f710323cec0,0,4732126,2734,2734,0,2811599,2698,2698,0,4154474,2668,2668,0,3455890,2674,2674,0,3886498,2706,2706,0,3026770,2700,2700,0,4146938,2742,2742,0,4274258,2676,2676,0,4495454,2718,2718,0,3584509,2661,2661,0,4029099,2720,2720,0,3569490,2700,2700,0,4288982,2736,2736,0,4280237,2668,2668,0,4598690,2696,2696,0,3238747,2688,2688,0,4183974,2697,2697,0,4412322,2672,2672,0,4983899,2714,2714,0,4892826,2694,2694,0,3141047,2716,2716,0,4607822,2730,2730,0,3361706,2704,2704,0,4074588,2664,2664,0,4752874,2690,2690,0,3168362,2674,2674,0,4757935,2746,2746,0,4367853,2660,2660,0,3114350,2716,2716,0,3025509,2684,2684,0,4490510,2710,2710,0,3276284,2667,2667,64,0x7f35434c4ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8480,4384,8480,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,64,0x7fc0d8dd0ec0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,0,43085,0,0,64,0x7f9424684ec0,0,0,48,0,65536,65536,0,0,31036,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,484,42670,1761,0,48.0,460.0,0.0,262144.0,64,0x7fe3fa2d4ec0,197769,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13997,30381,8715,2430,0,42109,262533.0,0.0,47.0,262486.0,64,0x7f087f044ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2777,40314,80,131460.0,131072.0,0.0,87406.0,64,0x7f3ab1be8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f0593688ec0,2712,0,0,1589566,4270,0,0,1748803,255,0,0,1080508,4989,0,0,1663988,1160,0,0,1307038,2607,0,0,1631420,1529,0,0,1390949,4904,0,0,1725398,2838,0,0,1556483,620,0,0,1296372,2332,0,0,1545746,711,0,0,1397725,1511,0,0,1386879,884,0,0,1426489,1137,0,0,1303677,5059,0,0,1644598,1790,0,0,1438655,930,0,0,1316632,2543,0,0,1555894,3374,0,0,1642192,1673,0,0,1429797,1712,0,0,1530600,4150,0,0,1719348,2923,0,0,1549097,1820,0,0,1451298,2208,0,0,1627140,727,0,0,1242387,2930,0,0,1526857,2448,0,0,1448351,1428,0,0,1459587,1359,0,0,1258475,4147,0,0,1586751,64,0x7f028639cec0,4096,0,5957,0,4096,0,1430,0,4096,0,262,0,4098,0,212,0,4096,0,0,0,4096,0,652,0,4096,0,894,0,4097,0,1370,0,4097,0,1782,0,4096,0,331,0,4144,0,2323,0,4096,0,5495,0,4096,0,525,0,4096,0,1212,0,4096,0,2898,0,4096,0,622,0,4096,0,36,0,4144,0,972,0,4096,0,3096,0,4096,0,516,0,4096,0,0,0,4096,0,4328,0,4097,0,288,0,4096,0,0,0,4096,0,245,0,4216,0,6685,0,4096,0,494,0,4096,0,452,0,4096,0,3876,0,4096,0,0,0,4096,0,175,0,4096,0,4585,0,64,0x7f2a00204ec0,3246635,360448,163840,0,0,180224,114688,0,66978628.0,188749015.0,78559880.0,131072.0,0.0,770755.0,0,0,28102,62361.0,0.0,0.0,62361.0,64,0x7fee0f1e4ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86532.0,0.0,131112.0,0.0,64,0x7fefb359cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,45361.0,111707.0,64,0x7efccbc90ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131842.0,0.0,1536.0,131840.0,1414621055537142,1414621055556022 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f16d0bf8ec0,131072.0,131072.0,0.0,2543198.0,0.0,0.0,119423196.0,50935608.0,64,0x7fc87a4f0ec0,32768,0,0,0,16384,16384,393216,22750565,960.0,513905.0,0.0,524288.0,932773.0,32768.0,0,0,0,14116,86392.0,86392.0,0.0,86392.0,64,0x7f75bc214ec0,340808,229584,3352881,16384,24669349,0,48,0,42600,42600,3732667.0,3067097.0,5795.0,1019359.0,2148876.0,0.0,3057972.0,2746289.0,340800,238899,42600,0,42600,0,1363200.0,808670.0,0.0,0.0,64,0x7f5fdcae4ec0,0.0,64,0x7f710323cec0,0,5356285,2724,2724,0,3582018,2718,2718,0,3892553,2656,2656,0,4225049,2702,2702,0,3879338,2716,2716,0,4642595,2732,2732,0,3681407,2702,2702,0,3710033,2714,2714,0,4516837,2720,2720,0,4265677,2696,2696,0,3644320,2704,2704,0,4948292,2700,2700,0,3168985,2708,2708,0,4376172,2684,2684,0,4042820,2694,2694,0,3271818,2682,2682,0,4610621,2712,2712,0,4650853,2720,2720,0,4504544,2696,2696,0,3936491,2673,2673,0,4647780,2706,2706,0,4777108,2736,2736,0,4003997,2680,2680,0,2792404,2666,2666,0,2892822,2694,2694,0,4171748,2710,2710,0,4065312,2708,2708,0,3959144,2672,2672,0,3616952,2730,2730,0,4821943,2710,2710,0,3743525,2704,2704,0,3054328,2660,2660,64,0x7f35434c4ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8480,4384,8480,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,64,0x7fc0d8dd0ec0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,0,44631,0,0,64,0x7f9424684ec0,0,0,48,0,65536,65536,0,0,30780,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,484,41999,1710,0,48.0,447.0,0.0,262144.0,64,0x7fe3fa2d4ec0,206296,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12207,28591,8557,2438,0,40415,262535.0,0.0,47.0,262488.0,64,0x7f087f044ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3827,39899,0,131461.0,131072.0,0.0,87163.0,64,0x7f3ab1be8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f0593688ec0,3361,0,0,1490469,3914,0,0,1567263,1727,0,0,1378785,3448,0,0,1489247,1304,0,0,1360316,2702,0,0,1502675,2337,0,0,1498039,3217,0,0,1475102,3162,0,0,1506696,3438,0,0,1511514,2653,0,0,1387895,1518,0,0,1321851,3958,0,0,1642434,4155,0,0,1619045,2263,0,0,1449888,2609,0,0,1525852,2938,0,0,1454919,3233,0,0,1508636,3943,0,0,1670194,3550,0,0,1515365,1380,0,0,1335522,3855,0,0,1551073,1902,0,0,1387746,3183,0,0,1601184,3192,0,0,1480846,3233,0,0,1410389,1652,0,0,1322731,2159,0,0,1441893,2539,0,0,1384398,3731,0,0,1540461,1428,0,0,1293464,2383,0,0,1469248,64,0x7f028639cec0,4096,0,4062,0,4096,0,3052,0,4096,0,1409,0,4098,0,0,0,4096,0,396,0,4096,0,1139,0,4096,0,257,0,4097,0,1210,0,4097,0,815,0,4096,0,2983,0,4144,0,140,0,4096,0,316,0,4096,0,0,0,4096,0,81,0,4096,0,362,0,4096,0,0,0,4096,0,2113,0,4144,0,1745,0,4096,0,635,0,4096,0,0,0,4096,0,7372,0,4096,0,584,0,4097,0,248,0,4096,0,0,0,4096,0,0,0,4216,0,4499,0,4096,0,782,0,4096,0,0,0,4096,0,4912,0,4096,0,133,0,4096,0,0,0,4096,0,723,0,64,0x7f2a00204ec0,1736907,360448,163840,0,0,180224,114688,0,70026159.0,192861691.0,77123010.0,131072.0,0.0,581446.0,0,0,25399,79333.0,0.0,0.0,79333.0,64,0x7fee0f1e4ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86583.0,0.0,131112.0,0.0,64,0x7fefb359cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,49780.0,117573.0,64,0x7efccbc90ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131528.0,0.0,910.0,131527.0,1414621055576182,1414621055595542 diff --git a/tests/workloads/kernel_summaries/MI100/sysinfo.csv b/tests/workloads/kernel/MI100/sysinfo.csv similarity index 52% rename from tests/workloads/kernel_summaries/MI100/sysinfo.csv rename to tests/workloads/kernel/MI100/sysinfo.csv index 839cbfe9e1..e9151330ba 100644 --- a/tests/workloads/kernel_summaries/MI100/sysinfo.csv +++ b/tests/workloads/kernel/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_summaries,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:11:21 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 05:07:54 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_summaries/MI200/timestamps.csv b/tests/workloads/kernel/MI100/timestamps.csv similarity index 50% rename from tests/workloads/kernel_summaries/MI200/timestamps.csv rename to tests/workloads/kernel/MI100/timestamps.csv index 543a02dd02..37179c6b2a 100644 --- a/tests/workloads/kernel_summaries/MI200/timestamps.csv +++ b/tests/workloads/kernel/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,392801,392801,1048576,256,0,0,8,0,16,64,0x0,0x7ffa15fd4ec0,200787787600454,200787787628212,200787787648052,200787787659796 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,392801,392801,1048576,256,0,0,8,0,16,64,0x0,0x7ffa15fd4ec0,200787787659115,200787787740532,200787787757172,200787787758633 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,392801,392801,1048576,256,0,0,8,0,16,64,0x0,0x7ffa15fd4ec0,200787787768803,200787787778292,200787787794132,200787787795423 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1299433,1299433,1048576,256,0,0,8,8,16,64,0x0,0x7fc619c60ec0,1414621055400032,1414621055425142,1414621055449622,1414621055460846 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1299433,1299433,1048576,256,0,0,8,8,16,64,0x0,0x7fc619c60ec0,1414621055462319,1414621055537142,1414621055556022,1414621055557449 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1299433,1299433,1048576,256,0,0,8,8,16,64,0x0,0x7fc619c60ec0,1414621055567848,1414621055576182,1414621055595542,1414621055596913 diff --git a/tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv index 22456dbcab..6400fc7520 100644 --- a/tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv @@ -1 +1,4 @@ -Index,KernelName +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4190428,4190428,1048576,256,0,0,8,0,16,64,0x0,0x7f94512c0ec0,27378,27378,16384,65536,13161,1467220,1414432756404789,1414445656659785,1414445656680105,1414432772257328 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4190428,4190428,1048576,256,0,0,8,0,16,64,0x0,0x7f94512c0ec0,40627,40627,16384,65536,9359,1048624,1414432772278037,1414445656699625,1414445656715145,1414432772686309 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4190428,4190428,1048576,256,0,0,8,0,16,64,0x0,0x7f94512c0ec0,40747,40747,16384,65536,9106,1048600,1414432772715755,1414445656774345,1414445656790665,1414432772875517 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel/MI200/SQ_INST_LEVEL_LDS.csv similarity index 52% rename from tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_LDS.csv rename to tests/workloads/kernel/MI200/SQ_INST_LEVEL_LDS.csv index 7788abc5e0..a8476e6b20 100644 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189312,189312,1048576,256,0,0,8,8,16,64,0x0,0x7fad7f8bae80,0,0,0,194328163709266,194339836161015,194339836185335,194328171429995 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189312,189312,1048576,256,0,0,8,8,16,64,0x0,0x7fad7f8bae80,0,0,0,194328171450363,194339836365335,194339836384535,194328171753527 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189312,189312,1048576,256,0,0,8,8,16,64,0x0,0x7fad7f8bae80,0,0,0,194328171783003,194339836406935,194339836425975,194328171979305 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4190642,4190642,1048576,256,0,0,8,0,16,64,0x0,0x7f6c840ecec0,0,0,0,1414433244984736,1414445656659785,1414445656680105,1414433261546075 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4190642,4190642,1048576,256,0,0,8,0,16,64,0x0,0x7f6c840ecec0,0,0,0,1414433261564100,1414445656699625,1414445656715145,1414433261863666 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4190642,4190642,1048576,256,0,0,8,0,16,64,0x0,0x7f6c840ecec0,0,0,0,1414433261890016,1414445656774345,1414445656790665,1414433262043226 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel/MI200/SQ_INST_LEVEL_SMEM.csv similarity index 50% rename from tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_SMEM.csv rename to tests/workloads/kernel/MI200/SQ_INST_LEVEL_SMEM.csv index fc6baf80e9..2c9cc35f04 100644 --- a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,358785,358785,1048576,256,0,0,8,0,16,64,0x0,0x7f4fb6f60ec0,65536,192650,21532128,199949862529729,199961732754864,199961732775184,199949878310071 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,358785,358785,1048576,256,0,0,8,0,16,64,0x0,0x7f4fb6f60ec0,65536,261854,29352464,199949878328526,199961732860464,199961732876784,199949878604739 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,358785,358785,1048576,256,0,0,8,0,16,64,0x0,0x7f4fb6f60ec0,65536,262932,29314240,199949878631169,199961732897264,199961732913104,199949878784980 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4190847,4190847,1048576,256,0,0,8,0,16,64,0x0,0x7f19e81d0ec0,65536,187730,20996312,1414433732354835,1414445656659785,1414445656680105,1414433748542708 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4190847,4190847,1048576,256,0,0,8,0,16,64,0x0,0x7f19e81d0ec0,65536,281018,31378144,1414433748560412,1414445656699625,1414445656715145,1414433748861932 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4190847,4190847,1048576,256,0,0,8,0,16,64,0x0,0x7f19e81d0ec0,65536,258024,28932200,1414433748888122,1414445656774345,1414445656790665,1414433749041842 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel/MI200/SQ_INST_LEVEL_VMEM.csv similarity index 50% rename from tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_VMEM.csv rename to tests/workloads/kernel/MI200/SQ_INST_LEVEL_VMEM.csv index f1372153bd..273dde303a 100644 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189683,189683,1048576,256,0,0,8,8,16,64,0x0,0x7f75c51c0e80,32768,655761,83926252,194329155359106,194339836161015,194339836185335,194329163428154 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189683,189683,1048576,256,0,0,8,8,16,64,0x0,0x7f75c51c0e80,32768,661507,84658544,194329163446258,194339836365335,194339836384535,194329163755814 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189683,189683,1048576,256,0,0,8,8,16,64,0x0,0x7f75c51c0e80,32768,665810,85240480,194329163783727,194339836406935,194339836425975,194329163954160 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4191050,4191050,1048576,256,0,0,8,0,16,64,0x0,0x7fcf14168ec0,32768,306417,34321340,1414434204510803,1414445656659785,1414445656680105,1414434220573068 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4191050,4191050,1048576,256,0,0,8,0,16,64,0x0,0x7fcf14168ec0,32768,580620,65031856,1414434220596282,1414445656699625,1414445656715145,1414434220884157 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4191050,4191050,1048576,256,0,0,8,0,16,64,0x0,0x7fcf14168ec0,32768,586983,65717864,1414434220910687,1414445656774345,1414445656790665,1414434221039700 diff --git a/tests/workloads/kernel/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..efd2e66bf6 --- /dev/null +++ b/tests/workloads/kernel/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4191237,4191237,1048576,256,0,0,8,0,16,64,0x0,0x7ffbe6b9cec0,27648,27648,11103,221192,16384,10666434,128024,0,43180252,1414434690769320,1414445656659785,1414445656680105,1414434706762735 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4191237,4191237,1048576,256,0,0,8,0,16,64,0x0,0x7ffbe6b9cec0,41673,41673,14419,333392,16384,19327058,223251,0,77801560,1414434706790227,1414445656699625,1414445656715145,1414434707222514 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4191237,4191237,1048576,256,0,0,8,0,16,64,0x0,0x7ffbe6b9cec0,41027,41027,13871,328224,16384,18889841,217781,0,76050388,1414434707257661,1414445656774345,1414445656790665,1414434707434395 diff --git a/tests/workloads/kernel/MI200/log.txt b/tests/workloads/kernel/MI200/log.txt new file mode 100644 index 0000000000..5c09829a0c --- /dev/null +++ b/tests/workloads/kernel/MI200/log.txt @@ -0,0 +1,764 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: ['vecCopy'] +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_170500' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170500_4190268' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170500_4190268/input0_results_240321_170500' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170500_4190268/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170500_4190268/input0_results_240321_170500 + |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_170501' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170501_4190482' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170501_4190482/input0_results_240321_170501' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170501_4190482/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170501_4190482/input0_results_240321_170501 + |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_170501' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170501_4190684' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170501_4190684/input0_results_240321_170501' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170501_4190684/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170501_4190684/input0_results_240321_170501 + |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_170502' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170502_4190890' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170502_4190890/input0_results_240321_170502' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170502_4190890/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170502_4190890/input0_results_240321_170502 + |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_170502' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170502_4191077' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170502_4191077/input0_results_240321_170502' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170502_4191077/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170502_4191077/input0_results_240321_170502 + |-> [rocprof] File 'tests/workloads/kernel/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_170502' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170502_4191279' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170502_4191279/input0_results_240321_170502' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170502_4191279/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170502_4191279/input0_results_240321_170502 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_170503' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170503_4191481' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170503_4191481/input0_results_240321_170503' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170503_4191481/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170503_4191481/input0_results_240321_170503 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_170503' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170503_4191685' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170503_4191685/input0_results_240321_170503' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170503_4191685/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170503_4191685/input0_results_240321_170503 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_170504' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170504_4191871' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170504_4191871/input0_results_240321_170504' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170504_4191871/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170504_4191871/input0_results_240321_170504 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_170504' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170504_4192073' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170504_4192073/input0_results_240321_170504' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170504_4192073/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170504_4192073/input0_results_240321_170504 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_170505' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170505_4192275' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170505_4192275/input0_results_240321_170505' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170505_4192275/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170505_4192275/input0_results_240321_170505 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_170506' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170506_4192465' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170506_4192465/input0_results_240321_170506' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170506_4192465/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170506_4192465/input0_results_240321_170506 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_170506' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170506_4192664' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170506_4192664/input0_results_240321_170506' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170506_4192664/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170506_4192664/input0_results_240321_170506 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_170507' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170507_4192866' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170507_4192866/input0_results_240321_170507' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170507_4192866/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170507_4192866/input0_results_240321_170507 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_170508' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170508_4193068' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170508_4193068/input0_results_240321_170508' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170508_4193068/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170508_4193068/input0_results_240321_170508 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_170508' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170508_4193269' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170508_4193269/input0_results_240321_170508' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170508_4193269/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170508_4193269/input0_results_240321_170508 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_170509' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170509_4193471' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170509_4193471/input0_results_240321_170509' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170509_4193471/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170509_4193471/input0_results_240321_170509 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_170510' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170510_4193673' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170510_4193673/input0_results_240321_170510' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170510_4193673/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170510_4193673/input0_results_240321_170510 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_170510' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170510_4193875' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170510_4193875/input0_results_240321_170510' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170510_4193875/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170510_4193875/input0_results_240321_170510 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_170510' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170510_4194077' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170510_4194077/input0_results_240321_170510' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170510_4194077/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170510_4194077/input0_results_240321_170510 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_170511' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170511_4194261' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170511_4194261/input0_results_240321_170511' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170511_4194261/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170511_4194261/input0_results_240321_170511 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_170511' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170511_672' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170511_672/input0_results_240321_170511' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170511_672/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170511_672/input0_results_240321_170511 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_170512' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170512_894' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170512_894/input0_results_240321_170512' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170512_894/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170512_894/input0_results_240321_170512 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_170512' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170512_1097' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170512_1097/input0_results_240321_170512' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170512_1097/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170512_1097/input0_results_240321_170512 + |-> [rocprof] File 'tests/workloads/kernel/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_170513' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_170513_1301' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_170513_1301/input0_results_240321_170513' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_170513_1301/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_170513_1301/input0_results_240321_170513 + |-> [rocprof] File 'tests/workloads/kernel/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/kernel/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt index 7000361619..3b68e4a38c 100644 --- a/tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ b/tests/workloads/kernel/MI200/perfmon/SQ_IFETCH_LEVEL.txt @@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PRE gpu: range: -kernel: "vecCopy(double*,,double*,,double*,,int,,int),[clone,.kd]" +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt index 08439eedce..f0b07be064 100644 --- a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_LDS.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt index 6cca322d4e..b65eec769f 100644 --- a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt index e527ad31ba..3fa3c03388 100644 --- a/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ b/tests/workloads/kernel/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt index 3f8e04adb3..8661e665cb 100644 --- a/tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ b/tests/workloads/kernel/MI200/perfmon/SQ_LEVEL_WAVES.txt @@ -2,4 +2,4 @@ pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVE gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt index 4ffdc32149..69f342e7c8 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_0.txt @@ -2,4 +2,4 @@ pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_IN gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt index 6c277f4a37..0b6980af5f 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_1.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VA gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt index 7053d4dce6..273f5e8845 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_10.txt @@ -2,4 +2,4 @@ pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_D gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt index 77ae8b461f..44076517f1 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_11.txt @@ -2,4 +2,4 @@ pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMI gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt index dfb2cf65e5..227e3e928b 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_12.txt @@ -2,4 +2,4 @@ pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt index 062fc9644a..91838b92f1 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_13.txt @@ -2,4 +2,4 @@ pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATO gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt index e0698dbf57..3f8f0de0e8 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_14.txt @@ -2,4 +2,4 @@ pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt index 77ad088669..8e4abc1269 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_15.txt @@ -2,4 +2,4 @@ pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt index d0628bb948..19aada1248 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_16.txt @@ -2,4 +2,4 @@ pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt index 343869c5f1..d25d8f61df 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_17.txt @@ -2,4 +2,4 @@ pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_R gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt index a74cefd281..8f3a4cf638 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_18.txt @@ -2,4 +2,4 @@ pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] T gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt index 70b69f8928..7db4b6a839 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_2.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INS gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt index e47f8e33c9..52db85736f 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_3.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt index 2d96f365a9..33da211e5f 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_4.txt @@ -2,4 +2,4 @@ pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt index e50beed390..b6ed310959 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_5.txt @@ -2,4 +2,4 @@ pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_IN gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt index 15a2277c1b..91a56b0bc3 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_6.txt @@ -2,4 +2,4 @@ pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt index b42ce91618..4ad70275a5 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_7.txt @@ -2,4 +2,4 @@ pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt index 21d4c7a998..68e1a43fe9 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_8.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt index 9ffe5778c3..24450898ad 100644 --- a/tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt +++ b/tests/workloads/kernel/MI200/perfmon/pmc_perf_9.txt @@ -2,4 +2,4 @@ pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_ gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/perfmon/timestamps.txt b/tests/workloads/kernel/MI200/perfmon/timestamps.txt index 676cca1b80..2970e26c4e 100644 --- a/tests/workloads/kernel/MI200/perfmon/timestamps.txt +++ b/tests/workloads/kernel/MI200/perfmon/timestamps.txt @@ -2,4 +2,4 @@ pmc: gpu: range: -kernel: +kernel: vecCopy diff --git a/tests/workloads/kernel/MI200/pmc_dispatch_info.csv b/tests/workloads/kernel/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/kernel/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/kernel/MI200/pmc_perf.csv b/tests/workloads/kernel/MI200/pmc_perf.csv new file mode 100644 index 0000000000..f88edd5951 --- /dev/null +++ b/tests/workloads/kernel/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_1,obj_1,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_3,obj_3,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_4,obj_4,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_5,obj_5,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_6,obj_6,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_7,obj_7,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_12,obj_12,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_13,obj_13,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_14,obj_14,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_15,obj_15,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_16,obj_16,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_17,obj_17,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_18,obj_18,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f068cd38ec0,114688,0,32768,32768,16384,16384,65536,49152,29241516.0,91908828.0,39871868.0,131072.0,0.0,284244.0,0,0,15650,1140.0,131083.0,0.0,14.0,64,0x7f9ff3dd8ec0,0,393216,163840,0,0,0,0,0,18419,0.0,0.0,0.0,32768.0,0.0,0.0,410.0,32768.0,4096,16384,352,28231,1902,0,56.0,6.0,0.0,204089.0,64,0x7f212a390ec0,4096,0,0,0,4096,0,2,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,402,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4097,0,0,0,64,0x7f3f7beb0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,34559.0,46248.0,19288.0,64,0x7f61283c0ec0,0,0,0,1059362,0,0,0,1149208,0,0,0,1075506,0,0,0,1170751,0,0,0,1035359,0,0,0,1209839,0,0,0,1132550,0,0,0,1193694,0,0,0,1075828,0,0,0,1030146,0,0,0,1052989,0,0,0,1110683,0,0,0,1124050,0,0,0,1048495,0,0,0,1094370,0,0,0,1137701,0,0,0,1106635,34,0,0,1266109,0,0,0,1106331,10,0,0,1345424,0,0,0,1027778,0,0,0,1169670,0,0,0,1080402,0,0,0,1179357,0,0,0,1059978,0,0,0,1127264,0,0,0,1068488,0,0,0,1198174,0,0,0,1012208,0,0,0,1061385,0,0,0,1057826,0,0,0,1158275,64,0x7fecc49e4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12802,18941,7500,545,0,26354,203998.0,0.0,72918.0,131080.0,64,0x7f14d7a0cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39028246.0,34197991.0,0.0,64,0x7f643173cec0,1224,120583,0,0,65536,63800,56,1680,64,0x7f99479b0ec0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,0,27889,0,0,64,0x7f39768d0ec0,2242,4096,2242,6338,2323,4096,2323,6419,2226,4096,2226,6322,2310,4096,2310,6406,2258,4096,2258,6354,2283,4096,2283,6379,2237,4100,2241,6337,2293,4096,2293,6389,2293,4096,2293,6389,2244,4096,2244,6340,2323,4096,2323,6419,2222,4096,2222,6318,2312,4096,2312,6408,2261,4096,2261,6357,2340,4098,2342,6438,2235,4096,2235,6331,2258,4096,2258,6354,2260,4096,2260,6356,2242,4096,2242,6338,2326,4096,2326,6422,2267,4096,2267,6363,2251,4096,2251,6347,2275,4097,2276,6372,2461,4098,2463,6559,2300,4096,2300,6396,2260,4096,2260,6356,2264,4096,2264,6360,2241,4096,2241,6337,2330,4096,2330,6426,2268,4096,2268,6364,2254,4096,2254,6350,2277,4096,2277,6373,64,0x7f50abb68ec0,228008,127423,16384,0,16384,16384,32768,49152,28500,28500,1935198.0,1360916.0,3707.0,161395.0,1049292.0,0.0,1353356.0,1056360.0,226297,135566,28500,0,28500,0,912000.0,492102.0,0.0,0.0,64,0x7fe7f9954ec0,0,1044356,4096,4096,0,1056787,4096,4096,0,1048696,4096,4096,0,1294506,4096,4096,0,1095755,4096,4096,0,1485101,4096,4096,0,1000004,4096,4096,0,1508544,4096,4096,0,1444514,4096,4096,0,1222295,4096,4096,0,1260290,4096,4096,0,1220333,4096,4096,0,964204,4096,4096,0,1233765,4096,4096,0,1294592,4096,4096,0,1159325,4096,4096,0,1450740,4096,4096,0,1125038,4096,4096,0,1032018,4096,4096,0,1143152,4096,4096,0,1352346,4096,4096,0,1063951,4096,4096,0,1014228,4096,4096,0,1313861,4096,4096,0,1367138,4096,4096,0,1520194,4096,4096,0,1072386,4096,4096,0,994398,4096,4096,0,966613,4096,4096,0,1207999,4096,4096,0,961721,4096,4096,0,1155934,4096,4096,64,0x7f9aa9a34ec0,0,0,0,224,0,65536,64163,56,64,0x7f3b79768ec0,6349,0,4096,6426,0,4096,6385,0,4096,6382,0,4096,6370,0,4096,6391,0,4096,6385,0,4096,6348,0,4096,6352,0,4096,6349,0,4096,6428,0,4096,6387,0,4096,6380,0,4096,6375,0,4096,6391,0,4096,6384,0,4096,6350,0,4096,6409,0,4096,6386,0,4096,6380,0,4096,6367,0,4096,6391,0,4096,6361,0,4096,6559,0,4096,6393,0,4096,6351,0,4096,6413,0,4096,6386,0,4096,6381,0,4096,6368,0,4096,6394,0,4096,6364,0,4096,64,0x7fdeaf890ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,950492.0,64,0x7ff3f3a4cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10397,0,815,26913,0,73492.0,131072.0,0.0,65568.0,64,0x7ffab4118ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fd3cd578ec0,32768,32768,0,64,0x7f9875900ec0,10368194,9428960,595170,344064,1586177,0,0,163840,832.0,515136.0,0.0,524288.0,272290.0,32768.0,424821,0,0,10691,131072.0,131072.0,0.0,131072.0,1414445656659785,1414445656680105 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f068cd38ec0,114688,0,32768,32768,16384,16384,65536,49152,57296939.0,194714927.0,43784062.0,131072.0,0.0,608117.0,0,0,24725,9737.0,131083.0,0.0,20.0,64,0x7f9ff3dd8ec0,0,393216,163840,0,0,0,0,0,29281,0.0,0.0,0.0,32768.0,0.0,0.0,245.0,32768.0,4096,16384,302,40398,2074,0,56.0,9.0,0.0,200292.0,64,0x7f212a390ec0,4096,0,1072,0,4097,0,480,0,4096,0,296,0,4096,0,335,0,4096,0,143,0,4096,0,369,0,4096,0,0,0,4096,0,1161,0,4096,0,127,0,4096,0,1369,0,4096,0,0,0,4098,0,0,0,4096,0,275,0,4096,0,210,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,256,0,4097,0,211,0,4097,0,161,0,4096,0,0,0,4096,0,245,0,4096,0,48,0,4096,0,573,0,4096,0,0,0,4096,0,165,0,4097,0,0,0,4096,0,184,0,4096,0,226,0,4097,0,0,0,4096,0,23,0,4097,0,125,0,64,0x7f3f7beb0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131085.0,113064.0,45571.0,0.0,64,0x7f61283c0ec0,0,0,0,1783305,58,0,0,1948013,0,0,0,1780051,0,0,0,1573404,0,0,0,1869282,37,0,0,1940292,0,0,0,1490918,80,0,0,2067967,78,0,0,2091072,0,0,0,1661372,0,0,0,1884465,0,0,0,1537638,0,0,0,1678337,117,0,0,2020497,0,0,0,1516074,1478,0,0,2712144,0,0,0,1554534,32,0,0,1817434,0,0,0,1698579,220,0,0,2200911,0,0,0,1570440,181,0,0,2096067,0,0,0,1404607,0,0,0,1795719,0,0,0,1712146,0,0,0,1542939,0,0,0,1829694,129,0,0,1700779,278,0,0,2063763,0,0,0,1623904,0,0,0,1670248,0,0,0,1543267,64,0x7fecc49e4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31373,27009,9599,2450,0,39652,200843.0,0.0,69761.0,131082.0,64,0x7f14d7a0cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,121988781.0,60774740.0,0.0,64,0x7f643173cec0,0,183326,0,0,65536,63800,56,1680,64,0x7f99479b0ec0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,0,42375,0,0,64,0x7f39768d0ec0,2177,4096,2177,6273,2165,4097,2166,6262,2146,4096,2146,6242,2137,4096,2137,6233,2155,4096,2155,6251,2157,4096,2157,6253,2166,4100,2170,6266,2167,4096,2167,6263,2172,4096,2172,6268,2174,4096,2174,6270,2171,4096,2171,6267,2146,4096,2146,6242,2138,4096,2138,6234,2152,4096,2152,6248,2214,4098,2216,6312,2167,4096,2167,6263,2160,4096,2160,6256,2152,4096,2152,6248,2204,4097,2205,6301,2177,4096,2177,6273,2151,4096,2151,6247,2156,4098,2158,6254,2183,4097,2184,6280,2193,4096,2193,6289,2193,4096,2193,6289,2169,4096,2169,6265,2154,4096,2154,6250,2200,4096,2200,6296,2183,4096,2183,6279,2156,4096,2156,6252,2154,4096,2154,6250,2182,4096,2182,6278,64,0x7f50abb68ec0,328160,219475,16384,0,16384,16384,32768,49152,41019,41019,3128773.0,2456676.0,4592.0,349139.0,1758562.0,0.0,2444640.0,2135440.0,328152,228445,41019,0,41019,0,1312608.0,776141.0,0.0,0.0,64,0x7fe7f9954ec0,0,4362816,2846,2846,0,3267809,2880,2880,0,3178397,2852,2852,0,4704152,2852,2852,0,4088841,2866,2866,0,4408054,2832,2832,0,3816595,2872,2872,0,4264516,2816,2816,0,3683243,2816,2816,0,4209198,2844,2844,0,3335891,2880,2880,0,3598909,2852,2852,0,2990983,2856,2856,0,4443509,2876,2876,0,3425950,2832,2832,0,3627575,2872,2872,0,4077582,2836,2836,0,4432008,2852,2852,0,3540133,2860,2860,0,4478275,2828,2828,0,3629016,2856,2856,0,3742249,2872,2872,0,3613240,2806,2806,0,4434787,2820,2820,0,3990615,2820,2820,0,3611539,2832,2832,0,3015612,2852,2852,0,3609389,2860,2860,0,3201195,2828,2828,0,3163706,2862,2862,0,3663650,2872,2872,0,3300297,2808,2808,64,0x7f9aa9a34ec0,0,0,0,56,0,65536,65536,0,64,0x7f3b79768ec0,6230,0,4096,6249,0,4096,6278,0,4096,6279,0,4096,6231,0,4096,6254,0,4096,6260,0,4096,6243,0,4096,6248,0,4096,6226,0,4096,6247,0,4096,6280,0,4096,6279,0,4096,6233,0,4096,6254,0,4096,6258,0,4096,6264,0,4096,6233,0,4096,6260,0,4096,6259,0,4096,6265,0,4096,6288,0,4096,6253,0,4096,6259,0,4096,6259,0,4096,6264,0,4096,6236,0,4096,6256,0,4096,6265,0,4096,6260,0,4096,6291,0,4096,6256,0,4096,64,0x7fdeaf890ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2034495.0,64,0x7ff3f3a4cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,16858,0,819,36564,0,69104.0,131072.0,0.0,45541.0,64,0x7ffab4118ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fd3cd578ec0,32768,32768,0,64,0x7f9875900ec0,17570515,16965690,260761,344064,2524933,0,0,163840,0.0,524288.0,0.0,524288.0,494890.0,32768.0,768389,0,0,10991,90726.0,90726.0,0.0,90726.0,1414445656699625,1414445656715145 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f068cd38ec0,114688,0,32768,32768,16384,16384,65536,49152,56756142.0,198507461.0,47046883.0,131072.0,0.0,529208.0,0,0,25050,21280.0,131083.0,0.0,20.0,64,0x7f9ff3dd8ec0,0,393216,163840,0,0,0,0,0,29613,0.0,0.0,0.0,32768.0,0.0,0.0,227.0,32768.0,4096,16384,302,40679,2061,0,56.0,10.0,0.0,200460.0,64,0x7f212a390ec0,4096,0,1127,0,4097,0,104,0,4096,0,408,0,4096,0,1869,0,4096,0,498,0,4096,0,315,0,4096,0,226,0,4096,0,297,0,4096,0,97,0,4096,0,374,0,4096,0,1547,0,4098,0,15,0,4096,0,490,0,4096,0,760,0,4096,0,458,0,4096,0,42,0,4096,0,75,0,4096,0,1621,0,4097,0,870,0,4097,0,157,0,4096,0,11,0,4096,0,438,0,4096,0,814,0,4096,0,699,0,4096,0,85,0,4096,0,1083,0,4097,0,178,0,4096,0,227,0,4096,0,95,0,4097,0,236,0,4096,0,228,0,4097,0,1092,0,64,0x7f3f7beb0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,97968.0,45412.0,0.0,64,0x7f61283c0ec0,0,0,0,1455721,0,0,0,1876213,11,0,0,2055236,10,0,0,2192454,0,0,0,1736617,1579,0,0,2371798,0,0,0,1637225,149,0,0,2082933,0,0,0,1988082,114,0,0,1772278,14,0,0,1820368,0,0,0,1641053,0,0,0,1932596,0,0,0,1676361,0,0,0,1696710,482,0,0,1851604,0,0,0,1619200,0,0,0,2003862,0,0,0,1935784,0,0,0,1846541,0,0,0,1855686,0,0,0,1888651,0,0,0,1973624,127,0,0,2041758,0,0,0,1743498,0,0,0,1534667,0,0,0,1647111,74,0,0,2056868,0,0,0,1950211,0,0,0,1626405,211,0,0,2038450,0,0,0,1515685,64,0x7fecc49e4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30581,26995,9581,3087,0,39466,200729.0,0.0,69647.0,131082.0,64,0x7f14d7a0cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,113060632.0,58084497.0,0.0,64,0x7f643173cec0,0,183182,0,0,65536,63800,56,1680,64,0x7f99479b0ec0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,0,40977,0,0,64,0x7f39768d0ec0,2160,4096,2160,6256,2168,4097,2169,6265,2145,4096,2145,6241,2164,4096,2164,6260,2176,4096,2176,6272,2199,4096,2199,6295,2140,4099,2143,6239,2157,4096,2157,6253,2156,4096,2156,6252,2166,4096,2166,6262,2171,4096,2171,6267,2143,4096,2143,6239,2166,4096,2166,6262,2174,4096,2174,6270,2259,4098,2261,6357,2145,4096,2145,6241,2145,4096,2145,6241,2156,4096,2156,6252,2152,4097,2153,6249,2154,4096,2154,6250,2164,4096,2164,6260,2166,4098,2168,6264,2166,4097,2167,6263,2190,4096,2190,6286,2190,4096,2190,6286,2148,4096,2148,6244,2157,4096,2157,6253,2153,4096,2153,6249,2160,4096,2160,6256,2165,4096,2165,6261,2166,4096,2166,6262,2166,4096,2166,6262,64,0x7f50abb68ec0,331280,222058,16384,0,16384,16384,32768,49152,41409,41409,3163743.0,2467375.0,4599.0,377805.0,1734510.0,0.0,2455281.0,2147305.0,331272,231435,41409,0,41409,0,1325088.0,786459.0,0.0,0.0,64,0x7fe7f9954ec0,0,2743955,2860,2860,0,3209205,2888,2888,0,3008075,2832,2832,0,3421305,2852,2852,0,3510943,2890,2890,0,3522228,2866,2866,0,3313749,2864,2864,0,3471419,2788,2788,0,3167013,2788,2788,0,3184786,2860,2860,0,4907420,2880,2880,0,2709892,2832,2832,0,2463451,2848,2848,0,2902637,2900,2900,0,5617416,2864,2864,0,3052071,2860,2860,0,3460680,2828,2828,0,3181911,2828,2828,0,3262740,2876,2876,0,3055179,2892,2892,0,3079981,2840,2840,0,3646352,2864,2864,0,3519755,2814,2814,0,3679483,2852,2852,0,3248924,2852,2852,0,2907076,2824,2824,0,3146460,2824,2824,0,3400202,2876,2876,0,3091041,2892,2892,0,2962177,2840,2840,0,3076460,2864,2864,0,3279208,2816,2816,64,0x7f9aa9a34ec0,0,0,0,56,0,65536,65536,0,64,0x7f3b79768ec0,6282,0,4096,6280,0,4096,6308,0,4096,6305,0,4096,6263,0,4096,6288,0,4096,6247,0,4096,6274,0,4096,6274,0,4096,6284,0,4096,6277,0,4096,6308,0,4096,6306,0,4096,6271,0,4096,6289,0,4096,6251,0,4096,6260,0,4096,6281,0,4096,6278,0,4096,6298,0,4096,6282,0,4096,6302,0,4096,6280,0,4096,6277,0,4096,6282,0,4096,6259,0,4096,6282,0,4096,6278,0,4096,6299,0,4096,6290,0,4096,6302,0,4096,6279,0,4096,64,0x7fdeaf890ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2005571.0,64,0x7ff3f3a4cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20973,0,2663,39483,0,70247.0,131072.0,0.0,45633.0,64,0x7ffab4118ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fd3cd578ec0,32768,32768,0,64,0x7f9875900ec0,18861648,17880123,637461,344064,2745838,0,0,163840,832.0,515150.0,0.0,524288.0,561645.0,32768.0,905482,0,0,13467,91112.0,91112.0,0.0,91112.0,1414445656774345,1414445656790665 diff --git a/tests/workloads/kernel/MI200/roofline.csv b/tests/workloads/kernel/MI200/roofline.csv new file mode 100644 index 0000000000..83ea48d570 --- /dev/null +++ b/tests/workloads/kernel/MI200/roofline.csv @@ -0,0 +1,5 @@ +device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh +0,1388.8003,1388.2018,1389.3988,5018.0034,5014.9653,5021.0415,9227.3828,9226.832,9227.9336,17715.787,17712.695,17718.879,20942.057,20881.729,21002.385,20273.387,20272.754,20274.02,170490.59,170486.83,170494.36,164905.91,164902.36,164909.45,41435.109,41434.566,41435.652,41490.23,41489.523,41490.938,166390.95,165895.59,166886.31 +1,1389.1022,1388.6135,1389.5908,5028.1416,5026.2451,5030.0381,9235.0059,9234.3955,9235.6162,18231.234,18229.113,18233.355,20975.01,20907.771,21042.248,20293.785,20293.287,20294.283,170865.64,170860.17,170871.11,165134.81,165131.06,165138.56,41491.012,41490.277,41491.746,41546.773,41546.109,41547.438,166891.17,166888.8,166893.55 +2,1388.7727,1388.2306,1389.3148,5035.6616,5033.3149,5038.0083,9261.2324,9260.5088,9261.9561,18217.076,18216.133,18218.02,21049.338,21048.953,21049.723,20351.391,20350.875,20351.906,171111.95,171108.86,171115.05,165494.22,165491.36,165497.08,41585.855,41584.934,41586.777,41643.219,41642.5,41643.938,166984.53,166391.91,167577.16 +3,1389.2549,1388.5906,1389.9192,5032.6069,5031.0239,5034.1899,9239.5078,9238.6982,9240.3174,18329.676,18328.783,18330.568,21036.42,21036.109,21036.73,20313.297,20312.844,20313.75,171033,171029.09,171036.91,165165.02,165160.69,165169.34,41426.988,41272.484,41581.492,41573.762,41572.508,41575.016,166972.52,166968.34,166976.69 diff --git a/tests/workloads/kernel_verbose_1/MI100/sysinfo.csv b/tests/workloads/kernel/MI200/sysinfo.csv similarity index 52% rename from tests/workloads/kernel_verbose_1/MI100/sysinfo.csv rename to tests/workloads/kernel/MI200/sysinfo.csv index 5cd2292750..d52c86c1f4 100644 --- a/tests/workloads/kernel_verbose_1/MI100/sysinfo.csv +++ b/tests/workloads/kernel/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_1,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:10:20 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 05:04:59 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_0/MI100/timestamps.csv b/tests/workloads/kernel/MI200/timestamps.csv similarity index 52% rename from tests/workloads/kernel_verbose_0/MI100/timestamps.csv rename to tests/workloads/kernel/MI200/timestamps.csv index 9e0c9e65c0..e099910a15 100644 --- a/tests/workloads/kernel_verbose_0/MI100/timestamps.csv +++ b/tests/workloads/kernel/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,197559,197559,1048576,256,0,0,8,8,16,64,0x0,0x7fd5bf49ee80,194353571628315,194353571654480,194353571678800,194353571697315 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,197559,197559,1048576,256,0,0,8,8,16,64,0x0,0x7fd5bf49ee80,194353571691414,194353571699280,194353571718320,194353571785462 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,197559,197559,1048576,256,0,0,8,8,16,64,0x0,0x7fd5bf49ee80,194353571729666,194353571787600,194353571806320,194353571807423 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1463,1463,1048576,256,0,0,8,0,16,64,0x0,0x7f09a4408ec0,1414445656634195,1414445656659785,1414445656680105,1414445656694409 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1463,1463,1048576,256,0,0,8,0,16,64,0x0,0x7f09a4408ec0,1414445656691093,1414445656699625,1414445656715145,1414445656771244 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1463,1463,1048576,256,0,0,8,0,16,64,0x0,0x7f09a4408ec0,1414445656725698,1414445656774345,1414445656790665,1414445656791793 diff --git a/tests/workloads/kernel_inv_int/MI100/log.txt b/tests/workloads/kernel_inv_int/MI100/log.txt new file mode 100644 index 0000000000..4660a49de6 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel_inv_int/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: ['42'] +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155200' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155200_1221330' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155200_1221330/input0_results_240321_155200' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155200_1221330/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155200_1221330/input0_results_240321_155200 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155200' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155200_1221517' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155200_1221517/input0_results_240321_155200' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155200_1221517/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155200_1221517/input0_results_240321_155200 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155200' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155200_1221705' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155200_1221705/input0_results_240321_155200' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155200_1221705/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155200_1221705/input0_results_240321_155200 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155201' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155201_1221895' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155201_1221895/input0_results_240321_155201' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155201_1221895/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155201_1221895/input0_results_240321_155201 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155201' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155201_1222097' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155201_1222097/input0_results_240321_155201' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155201_1222097/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155201_1222097/input0_results_240321_155201 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155202' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155202_1222295' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155202_1222295/input0_results_240321_155202' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155202_1222295/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155202_1222295/input0_results_240321_155202 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155202' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155202_1222498' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155202_1222498/input0_results_240321_155202' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155202_1222498/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155202_1222498/input0_results_240321_155202 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155203' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155203_1222683' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155203_1222683/input0_results_240321_155203' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155203_1222683/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155203_1222683/input0_results_240321_155203 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155203' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155203_1222874' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155203_1222874/input0_results_240321_155203' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155203_1222874/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155203_1222874/input0_results_240321_155203 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155204' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155204_1223062' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155204_1223062/input0_results_240321_155204' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155204_1223062/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155204_1223062/input0_results_240321_155204 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155205' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155205_1223247' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155205_1223247/input0_results_240321_155205' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155205_1223247/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155205_1223247/input0_results_240321_155205 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155205' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155205_1223432' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155205_1223432/input0_results_240321_155205' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155205_1223432/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155205_1223432/input0_results_240321_155205 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155206' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155206_1223634' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155206_1223634/input0_results_240321_155206' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155206_1223634/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155206_1223634/input0_results_240321_155206 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155207' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155207_1223822' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155207_1223822/input0_results_240321_155207' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155207_1223822/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155207_1223822/input0_results_240321_155207 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155207' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155207_1224012' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155207_1224012/input0_results_240321_155207' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155207_1224012/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155207_1224012/input0_results_240321_155207 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155208' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155208_1224201' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155208_1224201/input0_results_240321_155208' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155208_1224201/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155208_1224201/input0_results_240321_155208 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155208' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155208_1224387' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155208_1224387/input0_results_240321_155208' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155208_1224387/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155208_1224387/input0_results_240321_155208 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155209' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155209_1224574' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155209_1224574/input0_results_240321_155209' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155209_1224574/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155209_1224574/input0_results_240321_155209 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155209' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155209_1224773' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155209_1224773/input0_results_240321_155209' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155209_1224773/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155209_1224773/input0_results_240321_155209 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155210' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155210_1224958' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155210_1224958/input0_results_240321_155210' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155210_1224958/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155210_1224958/input0_results_240321_155210 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155210' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155210_1225160' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155210_1225160/input0_results_240321_155210' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155210_1225160/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155210_1225160/input0_results_240321_155210 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155211' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155211_1225345' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155211_1225345/input0_results_240321_155211' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155211_1225345/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155211_1225345/input0_results_240321_155211 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155211' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155211_1225534' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155211_1225534/input0_results_240321_155211' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155211_1225534/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155211_1225534/input0_results_240321_155211 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/kernel_inv_int/MI100/sysinfo.csv b/tests/workloads/kernel_inv_int/MI100/sysinfo.csv index b5ef0b1e21..3654a9c34f 100644 --- a/tests/workloads/kernel_inv_int/MI100/sysinfo.csv +++ b/tests/workloads/kernel_inv_int/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:06:32 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:51:59 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_inv_int/MI200/log.txt b/tests/workloads/kernel_inv_int/MI200/log.txt new file mode 100644 index 0000000000..986a1476a0 --- /dev/null +++ b/tests/workloads/kernel_inv_int/MI200/log.txt @@ -0,0 +1,762 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel_inv_int/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: ['42'] +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_161632' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161632_4100998' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161632_4100998/input0_results_240321_161632' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161632_4100998/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161632_4100998/input0_results_240321_161632 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_161633' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161633_4101182' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161633_4101182/input0_results_240321_161633' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161633_4101182/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161633_4101182/input0_results_240321_161633 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_161633' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161633_4101384' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161633_4101384/input0_results_240321_161633' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161633_4101384/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161633_4101384/input0_results_240321_161633 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_161634' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161634_4101589' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161634_4101589/input0_results_240321_161634' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161634_4101589/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161634_4101589/input0_results_240321_161634 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_161634' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161634_4101773' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161634_4101773/input0_results_240321_161634' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161634_4101773/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161634_4101773/input0_results_240321_161634 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_161635' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161635_4101979' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161635_4101979/input0_results_240321_161635' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161635_4101979/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161635_4101979/input0_results_240321_161635 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_161635' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161635_4102163' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161635_4102163/input0_results_240321_161635' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161635_4102163/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161635_4102163/input0_results_240321_161635 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_161636' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161636_4102365' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161636_4102365/input0_results_240321_161636' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161636_4102365/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161636_4102365/input0_results_240321_161636 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_161636' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161636_4102564' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161636_4102564/input0_results_240321_161636' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161636_4102564/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161636_4102564/input0_results_240321_161636 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_161636' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161636_4102757' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161636_4102757/input0_results_240321_161636' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161636_4102757/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161636_4102757/input0_results_240321_161636 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_161637' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161637_4102951' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161637_4102951/input0_results_240321_161637' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161637_4102951/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161637_4102951/input0_results_240321_161637 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_161638' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161638_4103135' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161638_4103135/input0_results_240321_161638' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161638_4103135/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161638_4103135/input0_results_240321_161638 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_161638' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161638_4103326' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161638_4103326/input0_results_240321_161638' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161638_4103326/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161638_4103326/input0_results_240321_161638 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_161639' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161639_4103517' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161639_4103517/input0_results_240321_161639' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161639_4103517/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161639_4103517/input0_results_240321_161639 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_161640' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161640_4103705' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161640_4103705/input0_results_240321_161640' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161640_4103705/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161640_4103705/input0_results_240321_161640 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_161640' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161640_4103889' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161640_4103889/input0_results_240321_161640' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161640_4103889/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161640_4103889/input0_results_240321_161640 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_161641' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161641_4104073' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161641_4104073/input0_results_240321_161641' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161641_4104073/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161641_4104073/input0_results_240321_161641 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_161641' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161641_4104264' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161641_4104264/input0_results_240321_161641' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161641_4104264/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161641_4104264/input0_results_240321_161641 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_161642' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161642_4104455' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161642_4104455/input0_results_240321_161642' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161642_4104455/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161642_4104455/input0_results_240321_161642 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_161642' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161642_4104659' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161642_4104659/input0_results_240321_161642' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161642_4104659/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161642_4104659/input0_results_240321_161642 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_161643' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161643_4104845' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161643_4104845/input0_results_240321_161643' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161643_4104845/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161643_4104845/input0_results_240321_161643 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_161643' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161643_4105047' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161643_4105047/input0_results_240321_161643' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161643_4105047/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161643_4105047/input0_results_240321_161643 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_161644' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161644_4105234' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161644_4105234/input0_results_240321_161644' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161644_4105234/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161644_4105234/input0_results_240321_161644 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_161644' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161644_4105436' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161644_4105436/input0_results_240321_161644' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161644_4105436/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161644_4105436/input0_results_240321_161644 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_int/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_161645' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_int/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161645_4105627' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161645_4105627/input0_results_240321_161645' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161645_4105627/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = 42 + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_161645_4105627/input0_results_240321_161645 + |-> [rocprof] File 'tests/workloads/kernel_inv_int/MI200/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/kernel_inv_int/MI200/sysinfo.csv b/tests/workloads/kernel_inv_int/MI200/sysinfo.csv index 35738cba51..012c9eecce 100644 --- a/tests/workloads/kernel_inv_int/MI200/sysinfo.csv +++ b/tests/workloads/kernel_inv_int/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_inv_int,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:11:46 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +kernel_inv_int,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:16:32 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_inv_str/MI100/log.txt b/tests/workloads/kernel_inv_str/MI100/log.txt new file mode 100644 index 0000000000..6d83373874 --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel_inv_str/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: ['vecPaste'] +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155406' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155406_1262953' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155406_1262953/input0_results_240321_155406' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155406_1262953/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155406_1262953/input0_results_240321_155406 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155406' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155406_1263139' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155406_1263139/input0_results_240321_155406' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155406_1263139/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155406_1263139/input0_results_240321_155406 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155407' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155407_1263328' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155407_1263328/input0_results_240321_155407' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155407_1263328/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155407_1263328/input0_results_240321_155407 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155407' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155407_1263512' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155407_1263512/input0_results_240321_155407' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155407_1263512/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155407_1263512/input0_results_240321_155407 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155408' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155408_1263696' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155408_1263696/input0_results_240321_155408' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155408_1263696/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155408_1263696/input0_results_240321_155408 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155408' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155408_1263880' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155408_1263880/input0_results_240321_155408' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155408_1263880/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155408_1263880/input0_results_240321_155408 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155409' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155409_1264068' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155409_1264068/input0_results_240321_155409' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155409_1264068/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155409_1264068/input0_results_240321_155409 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155409' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155409_1264256' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155409_1264256/input0_results_240321_155409' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155409_1264256/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155409_1264256/input0_results_240321_155409 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155410' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155410_1264443' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155410_1264443/input0_results_240321_155410' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155410_1264443/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155410_1264443/input0_results_240321_155410 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155410' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155410_1264627' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155410_1264627/input0_results_240321_155410' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155410_1264627/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155410_1264627/input0_results_240321_155410 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155411' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155411_1264816' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155411_1264816/input0_results_240321_155411' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155411_1264816/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155411_1264816/input0_results_240321_155411 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155412' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155412_1265000' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155412_1265000/input0_results_240321_155412' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155412_1265000/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155412_1265000/input0_results_240321_155412 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155412' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155412_1265186' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155412_1265186/input0_results_240321_155412' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155412_1265186/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155412_1265186/input0_results_240321_155412 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155413' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155413_1265373' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155413_1265373/input0_results_240321_155413' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155413_1265373/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155413_1265373/input0_results_240321_155413 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155414' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155414_1265561' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155414_1265561/input0_results_240321_155414' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155414_1265561/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155414_1265561/input0_results_240321_155414 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155414' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155414_1265745' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155414_1265745/input0_results_240321_155414' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155414_1265745/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155414_1265745/input0_results_240321_155414 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155415' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155415_1265933' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155415_1265933/input0_results_240321_155415' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155415_1265933/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155415_1265933/input0_results_240321_155415 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155415' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155415_1266118' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155415_1266118/input0_results_240321_155415' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155415_1266118/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155415_1266118/input0_results_240321_155415 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155415' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155415_1266306' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155415_1266306/input0_results_240321_155415' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155415_1266306/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155415_1266306/input0_results_240321_155415 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155416' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155416_1266490' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155416_1266490/input0_results_240321_155416' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155416_1266490/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155416_1266490/input0_results_240321_155416 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155416' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155416_1266678' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155416_1266678/input0_results_240321_155416' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155416_1266678/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155416_1266678/input0_results_240321_155416 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155417' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155417_1266863' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155417_1266863/input0_results_240321_155417' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155417_1266863/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155417_1266863/input0_results_240321_155417 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155417' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155417_1267048' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155417_1267048/input0_results_240321_155417' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155417_1267048/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_155417_1267048/input0_results_240321_155417 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/kernel_inv_str/MI100/sysinfo.csv b/tests/workloads/kernel_inv_str/MI100/sysinfo.csv index 69ce6185cc..89d7986234 100644 --- a/tests/workloads/kernel_inv_str/MI100/sysinfo.csv +++ b/tests/workloads/kernel_inv_str/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_inv_str,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:08:44 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_inv_str,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:54:05 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_inv_str/MI200/log.txt b/tests/workloads/kernel_inv_str/MI200/log.txt new file mode 100644 index 0000000000..d13e2b754c --- /dev/null +++ b/tests/workloads/kernel_inv_str/MI200/log.txt @@ -0,0 +1,762 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel_inv_str/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: ['vecPaste'] +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_163543' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163543_4149712' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163543_4149712/input0_results_240321_163543' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163543_4149712/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163543_4149712/input0_results_240321_163543 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_163543' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163543_4149899' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163543_4149899/input0_results_240321_163543' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163543_4149899/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163543_4149899/input0_results_240321_163543 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_163544' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163544_4150085' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163544_4150085/input0_results_240321_163544' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163544_4150085/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163544_4150085/input0_results_240321_163544 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_163544' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163544_4150269' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163544_4150269/input0_results_240321_163544' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163544_4150269/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163544_4150269/input0_results_240321_163544 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_163545' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163545_4150471' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163545_4150471/input0_results_240321_163545' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163545_4150471/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163545_4150471/input0_results_240321_163545 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_163545' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163545_4150673' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163545_4150673/input0_results_240321_163545' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163545_4150673/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163545_4150673/input0_results_240321_163545 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_163546' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163546_4150874' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163546_4150874/input0_results_240321_163546' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163546_4150874/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163546_4150874/input0_results_240321_163546 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_163546' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163546_4151063' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163546_4151063/input0_results_240321_163546' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163546_4151063/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163546_4151063/input0_results_240321_163546 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_163547' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163547_4151265' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163547_4151265/input0_results_240321_163547' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163547_4151265/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163547_4151265/input0_results_240321_163547 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_163547' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163547_4151453' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163547_4151453/input0_results_240321_163547' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163547_4151453/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163547_4151453/input0_results_240321_163547 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_163548' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163548_4151641' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163548_4151641/input0_results_240321_163548' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163548_4151641/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163548_4151641/input0_results_240321_163548 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_163548' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163548_4151829' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163548_4151829/input0_results_240321_163548' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163548_4151829/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163548_4151829/input0_results_240321_163548 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_163549' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163549_4152033' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163549_4152033/input0_results_240321_163549' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163549_4152033/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163549_4152033/input0_results_240321_163549 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_163550' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163550_4152221' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163550_4152221/input0_results_240321_163550' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163550_4152221/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163550_4152221/input0_results_240321_163550 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_163550' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163550_4152421' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163550_4152421/input0_results_240321_163550' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163550_4152421/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163550_4152421/input0_results_240321_163550 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_163551' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163551_4152609' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163551_4152609/input0_results_240321_163551' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163551_4152609/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163551_4152609/input0_results_240321_163551 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_163552' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163552_4152812' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163552_4152812/input0_results_240321_163552' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163552_4152812/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163552_4152812/input0_results_240321_163552 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_163552' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163552_4153015' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163552_4153015/input0_results_240321_163552' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163552_4153015/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163552_4153015/input0_results_240321_163552 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_163553' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163553_4153217' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163553_4153217/input0_results_240321_163553' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163553_4153217/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163553_4153217/input0_results_240321_163553 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_163553' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163553_4153404' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163553_4153404/input0_results_240321_163553' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163553_4153404/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163553_4153404/input0_results_240321_163553 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_163554' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163554_4153594' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163554_4153594/input0_results_240321_163554' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163554_4153594/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163554_4153594/input0_results_240321_163554 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_163554' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163554_4153780' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163554_4153780/input0_results_240321_163554' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163554_4153780/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163554_4153780/input0_results_240321_163554 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_163554' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163554_4153968' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163554_4153968/input0_results_240321_163554' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163554_4153968/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163554_4153968/input0_results_240321_163554 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_163555' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163555_4154152' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163555_4154152/input0_results_240321_163555' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163555_4154152/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163555_4154152/input0_results_240321_163555 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_inv_str/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_163555' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_inv_str/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163555_4154340' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163555_4154340/input0_results_240321_163555' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163555_4154340/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecPaste + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 0 contexts collected, output directory /tmp/rpl_data_240321_163555_4154340/input0_results_240321_163555 + |-> [rocprof] File 'tests/workloads/kernel_inv_str/MI200/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/kernel_inv_str/MI200/sysinfo.csv b/tests/workloads/kernel_inv_str/MI200/sysinfo.csv index f7a3faddb6..932bf8d601 100644 --- a/tests/workloads/kernel_inv_str/MI200/sysinfo.csv +++ b/tests/workloads/kernel_inv_str/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_inv_str,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:29:22 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +kernel_inv_str,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:35:42 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_fp32.pdf index 222229e7cb..122b18d708 100644 Binary files a/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_int8_fp16.pdf index 27ad9f226b..ad9cd2607b 100644 Binary files a/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/kernel_names/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/kernel_names/MI200/kernelName_legend.pdf b/tests/workloads/kernel_names/MI200/kernelName_legend.pdf index 9bc1ff0f7e..5302945d8c 100644 Binary files a/tests/workloads/kernel_names/MI200/kernelName_legend.pdf and b/tests/workloads/kernel_names/MI200/kernelName_legend.pdf differ diff --git a/tests/workloads/kernel_names/MI200/log.txt b/tests/workloads/kernel_names/MI200/log.txt new file mode 100644 index 0000000000..8473a29756 --- /dev/null +++ b/tests/workloads/kernel_names/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel_names/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/kernel_names/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_162548' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_names/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162548_4134506' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162548_4134506/input0_results_240321_162548' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162548_4134506/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162548_4134506/input0_results_240321_162548 + |-> [rocprof] File 'tests/workloads/kernel_names/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/kernel_names/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_162548' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_names/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162548_4134693' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162548_4134693/input0_results_240321_162548' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162548_4134693/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162548_4134693/input0_results_240321_162548 + |-> [rocprof] File 'tests/workloads/kernel_names/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/kernel_names/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_162549' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_names/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162549_4134881' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162549_4134881/input0_results_240321_162549' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162549_4134881/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162549_4134881/input0_results_240321_162549 + |-> [rocprof] File 'tests/workloads/kernel_names/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/kernel_names/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_162549' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_names/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162549_4135068' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162549_4135068/input0_results_240321_162549' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162549_4135068/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162549_4135068/input0_results_240321_162549 + |-> [rocprof] File 'tests/workloads/kernel_names/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/kernel_names/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/kernel_names/MI200/pmc_dispatch_info.csv b/tests/workloads/kernel_names/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/kernel_names/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/kernel_names/MI200/pmc_perf.csv b/tests/workloads/kernel_names/MI200/pmc_perf.csv index 65578bf14f..e111d2a473 100644 --- a/tests/workloads/kernel_names/MI200/pmc_perf.csv +++ b/tests/workloads/kernel_names/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7d7f73cec0,0,0,64,0x7fd57baa8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd63f95cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,131072.0,131072.0,197002149949822,197002149970142 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7d7f73cec0,0,0,64,0x7fd57baa8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd63f95cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,91410.0,91410.0,197002149989022,197002150004702 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7d7f73cec0,0,0,64,0x7fd57baa8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd63f95cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,90882.0,90882.0,197002150063742,197002150080062 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f79a6568ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f964ade8ec0,0,0,64,0x7f8ceb5a8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,131072.0,131072.0,1412081937504773,1412081937524933 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f79a6568ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f964ade8ec0,0,0,64,0x7f8ceb5a8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,91142.0,91142.0,1412081937544293,1412081937559973 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f79a6568ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f964ade8ec0,0,0,64,0x7f8ceb5a8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,91346.0,91346.0,1412081937618533,1412081937635173 diff --git a/tests/workloads/kernel_names/MI200/roofline.csv b/tests/workloads/kernel_names/MI200/roofline.csv index 9778ed8285..d607fd6e8b 100644 --- a/tests/workloads/kernel_names/MI200/roofline.csv +++ b/tests/workloads/kernel_names/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.5958,1388.0493,1389.1423,5016.0552,5013.2388,5018.8716,9224.002,9223.4004,9224.6035,17646.789,17645.832,17647.746,20937.551,20877.023,20998.078,20265.363,20264.518,20266.209,170441.44,170436.91,170445.97,164875.34,164870.25,164880.44,41419.012,41418.453,41419.57,41478.145,41477.512,41478.777,166343.12,165853.14,166833.11 -1,1389.3785,1388.7844,1389.9727,5026.104,5024.2295,5027.9785,9231.624,9231.0449,9232.2031,18072.625,18071.354,18073.896,20969.863,20903.061,21036.666,20290.215,20289.688,20290.742,170813.73,170809.58,170817.89,165053.16,165048.22,165058.09,41467.996,41467.258,41468.734,41523.824,41522.836,41524.812,166816.73,166813.39,166820.08 -2,1389.1305,1388.6124,1389.6486,5036.9468,5034.8271,5039.0664,9263.2686,9262.5059,9264.0312,18272.225,18271.135,18273.314,21051.234,21050.822,21051.646,20356.029,20355.484,20356.574,171144.91,171141.19,171148.62,165540.94,165536.42,165545.45,41592.703,41591.672,41593.734,41649.43,41648.234,41650.625,166973,166376.17,167569.83 -3,1389.0021,1388.4742,1389.5299,5030.1553,5028.6445,5031.666,9238.5254,9237.9639,9239.0869,18325.27,18323.295,18327.244,21027.713,21027.381,21028.045,20309.979,20309.316,20310.641,170994.94,170990.62,170999.25,165209.19,165206.78,165211.59,41440.266,41286.492,41594.039,41583.148,41582.602,41583.695,167001.05,166998.64,167003.45 +0,1388.9282,1388.3175,1389.5389,5017.3882,5014.4512,5020.3252,9227.0234,9226.3682,9227.6787,17716.459,17713.33,17719.588,20945.281,20884.613,21005.949,20273.305,20272.646,20273.963,170494.08,170490.92,170497.23,164927.81,164923.56,164932.06,41438.559,41437.895,41439.223,41493.992,41493.492,41494.492,166407.34,165915.83,166898.86 +1,1388.9865,1388.4292,1389.5437,5029.7632,5027.7769,5031.7495,9237.8516,9237.1484,9238.5547,18239.699,18237.943,18241.455,20986.152,20919.436,21052.869,20301.568,20300.916,20302.221,170908.56,170904.03,170913.09,165157.95,165153.84,165162.06,41499.078,41498.238,41499.918,41553.703,41552.781,41554.625,166922.34,166918.17,166926.52 +2,1388.8414,1388.2102,1389.4727,5035.4419,5033.2456,5037.6382,9262.9658,9262.335,9263.5967,18220.949,18220.014,18221.885,21057.277,21056.908,21057.646,20353.641,20352.898,20354.383,171148.84,171144.11,171153.58,165526.91,165522.73,165531.08,41582.828,41582.098,41583.559,41640.613,41639.422,41641.805,166980.31,166387.7,167572.92 +3,1389.2573,1388.7434,1389.7712,5032.5112,5030.8784,5034.144,9235.8096,9235.0342,9236.585,18324.967,18324.154,18325.779,21029.967,21029.445,21030.488,20304.945,20304.5,20305.391,171032.27,171027.84,171036.69,165140.88,165137.02,165144.73,41421.703,41268.262,41575.145,41566.469,41565.211,41567.727,166934.39,166929.88,166938.91 diff --git a/tests/workloads/kernel_names/MI200/sysinfo.csv b/tests/workloads/kernel_names/MI200/sysinfo.csv index 08d4869367..3408a5bd12 100644 --- a/tests/workloads/kernel_names/MI200/sysinfo.csv +++ b/tests/workloads/kernel_names/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_names,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:21:00 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +kernel_names,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:25:47 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_names/MI200/timestamps.csv b/tests/workloads/kernel_names/MI200/timestamps.csv index 9d5f8a6afc..edcb0f016b 100644 --- a/tests/workloads/kernel_names/MI200/timestamps.csv +++ b/tests/workloads/kernel_names/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,239056,239056,1048576,256,0,0,8,0,16,64,0x0,0x7f78041f8ec0,197002149924520,197002149949822,197002149970142,197002149986197 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,239056,239056,1048576,256,0,0,8,0,16,64,0x0,0x7f78041f8ec0,197002149981117,197002149989022,197002150004702,197002150061159 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,239056,239056,1048576,256,0,0,8,0,16,64,0x0,0x7f78041f8ec0,197002150015272,197002150063742,197002150080062,197002150081206 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4135228,4135228,1048576,256,0,0,8,0,16,64,0x0,0x7f765deb0ec0,1412081937480123,1412081937504773,1412081937524933,1412081937540988 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4135228,4135228,1048576,256,0,0,8,0,16,64,0x0,0x7f765deb0ec0,1412081937536329,1412081937544293,1412081937559973,1412081937615799 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4135228,4135228,1048576,256,0,0,8,0,16,64,0x0,0x7f765deb0ec0,1412081937570474,1412081937618533,1412081937635173,1412081937636388 diff --git a/tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv index 06b6066476..23bc53b722 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,48136,48136,16384,65536,12547,1608968,194163174117052,194175534630063,194175534654063,194163181897573 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,43175,43175,16384,65536,8463,1048596,194163181922491,194175534674223,194175534693583,194163182207089 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137526,137526,1048576,256,0,0,8,8,16,64,0x0,0x7ff7d60b8e80,44071,44071,16384,65536,8088,1048576,194163182239821,194175534779503,194175534798543,194163182401738 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1233276,1233276,1048576,256,0,0,8,8,16,64,0x0,0x7efe2639cec0,47520,47520,16384,65536,13262,1711364,1410088190828131,1410100033478037,1410100033502197,1410088198583377 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1233276,1233276,1048576,256,0,0,8,8,16,64,0x0,0x7efe2639cec0,41636,41636,16384,65536,8455,1048580,1410088198612933,1410100033593877,1410100033612597,1410088198932796 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1233276,1233276,1048576,256,0,0,8,8,16,64,0x0,0x7efe2639cec0,41636,41636,16384,65536,8143,1048580,1410088198965097,1410100033638517,1410100033657077,1410088199142181 diff --git a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv index 9540492999..1e4c4a0161 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163677587142,194175534630063,194175534654063,194163685530482 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163685548716,194175534674223,194175534693583,194163685853083 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137714,137714,1048576,256,0,0,8,8,16,64,0x0,0x7f3cb4fe8e80,0,0,0,194163685881677,194175534779503,194175534798543,194163686052871 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1233465,1233465,1048576,256,0,0,8,8,16,64,0x0,0x7fcfea990ec0,0,0,0,1410088676805908,1410100033478037,1410100033502197,1410088684337091 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1233465,1233465,1048576,256,0,0,8,8,16,64,0x0,0x7fcfea990ec0,0,0,0,1410088684356949,1410100033593877,1410100033612597,1410088684680419 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1233465,1233465,1048576,256,0,0,8,8,16,64,0x0,0x7fcfea990ec0,0,0,0,1410088684708933,1410100033638517,1410100033657077,1410088684889954 diff --git a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv index 94f7a15a3e..986436f6cb 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,188508,24142904,194164172303568,194175534630063,194175534654063,194164179881035 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,169170,21619920,194164179900282,194175534674223,194175534693583,194164180246938 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,137904,137904,1048576,256,0,0,8,8,16,64,0x0,0x7f071b3dce80,65536,168242,21557048,194164180274780,194175534779503,194175534798543,194164180454190 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1233652,1233652,1048576,256,0,0,8,8,16,64,0x0,0x7f35fba6cec0,65536,215772,27659752,1410089161300999,1410100033478037,1410100033502197,1410089168886174 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1233652,1233652,1048576,256,0,0,8,8,16,64,0x0,0x7f35fba6cec0,65536,218704,27996088,1410089168906202,1410100033593877,1410100033612597,1410089169214454 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1233652,1233652,1048576,256,0,0,8,8,16,64,0x0,0x7f35fba6cec0,65536,216244,27719712,1410089169242256,1410100033638517,1410100033657077,1410089169412888 diff --git a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv index 7f3c32976d..5d24a9ae33 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,655161,83871140,194164678008099,194175534630063,194175534654063,194164686165985 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,672735,86120852,194164686184760,194175534674223,194175534693583,194164686503344 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,138091,138091,1048576,256,0,0,8,8,16,64,0x0,0x7f290d802e80,32768,657649,84175780,194164686531978,194175534779503,194175534798543,194164686707520 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1233840,1233840,1048576,256,0,0,8,8,16,64,0x0,0x7fc449ed8ec0,32768,655957,83965736,1410089647501356,1410100033478037,1410100033502197,1410089655200997 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1233840,1233840,1048576,256,0,0,8,8,16,64,0x0,0x7fc449ed8ec0,32768,665445,85174904,1410089655222728,1410100033593877,1410100033612597,1410089655499350 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1233840,1233840,1048576,256,0,0,8,8,16,64,0x0,0x7fc449ed8ec0,32768,657926,84218544,1410089655527864,1410100033638517,1410100033657077,1410089655705819 diff --git a/tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv index d236147e08..46872ee7e7 100644 --- a/tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,47598,47598,16289,380792,16384,24789627,229303,0,99653036,194165181026564,194175534630063,194175534654063,194165189084451 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,42421,42421,14055,339376,16384,24679834,225411,0,99219160,194165189106292,194175534674223,194175534693583,194165189431618 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,138275,138275,1048576,256,0,0,8,8,16,64,0x0,0x7f5d7a4c8e80,41925,41925,13806,335408,16384,24141356,225187,0,97056972,194165189469360,194175534779503,194175534798543,194165189654570 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1234024,1234024,1048576,256,0,0,8,8,16,64,0x0,0x7f90cce04ec0,48770,48770,18412,390168,16384,24851481,236800,0,99947332,1410090131932426,1410100033478037,1410100033502197,1410090139651645 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1234024,1234024,1048576,256,0,0,8,8,16,64,0x0,0x7f90cce04ec0,42136,42136,13157,337096,16384,24727121,229507,0,99439364,1410090139682352,1410100033593877,1410100033612597,1410090139991095 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1234024,1234024,1048576,256,0,0,8,8,16,64,0x0,0x7f90cce04ec0,42472,42472,13191,339784,16384,23653826,229247,0,95156176,1410090140029487,1410100033638517,1410100033657077,1410090140209627 diff --git a/tests/workloads/kernel_substr/MI100/log.txt b/tests/workloads/kernel_substr/MI100/log.txt new file mode 100644 index 0000000000..14338c6734 --- /dev/null +++ b/tests/workloads/kernel_substr/MI100/log.txt @@ -0,0 +1,702 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel_substr/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: ['vecCopy'] +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155234' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155234_1233116' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155234_1233116/input0_results_240321_155234' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155234_1233116/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155234_1233116/input0_results_240321_155234 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155234' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155234_1233305' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155234_1233305/input0_results_240321_155234' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155234_1233305/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155234_1233305/input0_results_240321_155234 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155235' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155235_1233492' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155235_1233492/input0_results_240321_155235' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155235_1233492/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155235_1233492/input0_results_240321_155235 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155235' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155235_1233680' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155235_1233680/input0_results_240321_155235' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155235_1233680/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155235_1233680/input0_results_240321_155235 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155236' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155236_1233864' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155236_1233864/input0_results_240321_155236' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155236_1233864/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155236_1233864/input0_results_240321_155236 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155236' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155236_1234050' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155236_1234050/input0_results_240321_155236' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155236_1234050/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155236_1234050/input0_results_240321_155236 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155237' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155237_1234236' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155237_1234236/input0_results_240321_155237' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155237_1234236/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155237_1234236/input0_results_240321_155237 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155237' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155237_1234425' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155237_1234425/input0_results_240321_155237' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155237_1234425/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155237_1234425/input0_results_240321_155237 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155238' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155238_1234614' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155238_1234614/input0_results_240321_155238' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155238_1234614/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155238_1234614/input0_results_240321_155238 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155238' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155238_1234809' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155238_1234809/input0_results_240321_155238' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155238_1234809/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155238_1234809/input0_results_240321_155238 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155239' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155239_1234998' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155239_1234998/input0_results_240321_155239' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155239_1234998/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155239_1234998/input0_results_240321_155239 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155240' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155240_1235184' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155240_1235184/input0_results_240321_155240' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155240_1235184/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155240_1235184/input0_results_240321_155240 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155240' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155240_1235373' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155240_1235373/input0_results_240321_155240' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155240_1235373/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155240_1235373/input0_results_240321_155240 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155241' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155241_1235565' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155241_1235565/input0_results_240321_155241' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155241_1235565/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155241_1235565/input0_results_240321_155241 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155242' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155242_1235753' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155242_1235753/input0_results_240321_155242' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155242_1235753/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155242_1235753/input0_results_240321_155242 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155242' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155242_1235942' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155242_1235942/input0_results_240321_155242' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155242_1235942/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155242_1235942/input0_results_240321_155242 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155243' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155243_1236130' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155243_1236130/input0_results_240321_155243' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155243_1236130/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155243_1236130/input0_results_240321_155243 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155243' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155243_1236315' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155243_1236315/input0_results_240321_155243' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155243_1236315/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155243_1236315/input0_results_240321_155243 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155244' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155244_1236503' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155244_1236503/input0_results_240321_155244' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155244_1236503/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155244_1236503/input0_results_240321_155244 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155244' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155244_1236690' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155244_1236690/input0_results_240321_155244' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155244_1236690/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155244_1236690/input0_results_240321_155244 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155245' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155245_1236877' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155245_1236877/input0_results_240321_155245' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155245_1236877/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155245_1236877/input0_results_240321_155245 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155245' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155245_1237066' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155245_1237066/input0_results_240321_155245' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155245_1237066/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155245_1237066/input0_results_240321_155245 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155246' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155246_1237253' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155246_1237253/input0_results_240321_155246' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155246_1237253/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155246_1237253/input0_results_240321_155246 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/kernel_substr/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_substr/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/kernel_substr/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/kernel_substr/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/kernel_substr/MI100/pmc_perf.csv b/tests/workloads/kernel_substr/MI100/pmc_perf.csv index ac83c58934..58da9d15e4 100644 --- a/tests/workloads/kernel_substr/MI100/pmc_perf.csv +++ b/tests/workloads/kernel_substr/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_1,obj_1,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_8,obj_8,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_9,obj_9,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_12,obj_12,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_13,obj_13,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_14,obj_14,TCC_EA_ATOMIC_LEVEL_sum,wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2ff3a2ce80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f38f5026e80,0,4918466,4096,4096,0,4386322,4096,4096,0,3618875,4096,4096,0,3646552,4096,4096,0,3230998,4096,4096,0,3667123,4096,4096,0,3378349,4096,4096,0,3500357,4096,4096,0,2951144,4096,4096,0,4847587,4096,4096,0,3769941,4096,4096,0,4270450,4096,4096,0,3490697,4096,4096,0,4909128,4096,4096,0,3707545,4096,4096,0,2888229,4096,4096,0,5159646,4096,4096,0,3719452,4096,4096,0,5017223,4096,4096,0,2647461,4096,4096,0,2952867,4096,4096,0,4754845,4096,4096,0,3215894,4096,4096,0,3130743,4096,4096,0,3450164,4096,4096,0,4150606,4096,4096,0,3080691,4096,4096,0,3667284,4096,4096,0,4444846,4096,4096,0,3304170,4096,4096,0,3631015,4096,4096,0,2774500,4096,4096,64,0x7f2651730e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47208,0,131516.0,131072.0,0.0,131104.0,64,0x7f10a1dace80,186415,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13588,29972,9930,550,0,46965,262603.0,0.0,188.0,262415.0,64,0x7f54835f8e80,0,0,192,0,65536,64517,48,1355,32344,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48169,1784,0,48.0,267.0,0.0,262288.0,64,0x7f198b1aae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131499.0,0.0,846.0,131498.0,64,0x7f2f2cb3ae80,131072.0,131072.0,0.0,2568521.0,0.0,0.0,118890799.0,60770673.0,64,0x7fc916404e80,32768,0,0,0,16384,16384,393216,23843256,960.0,513869.0,0.0,524288.0,1196279.0,32768.0,0,0,0,16802,131072.0,131072.0,0.0,131072.0,64,0x7f68399ece80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,47,8241,4192,8288,0,8192,4096,8192,0,8322,4226,8322,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f04bf79ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,83775.0,151157.0,64,0x7f7d506f8e80,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,0,47716,0,0,64,0x7f7b2b544e80,381040,231164,3385172,16384,24968233,144,48,0,47629,47629,3820148.0,2957388.0,5424.0,990164.0,2034069.0,0.0,2948190.0,2636777.0,379647,241114,47629,0,47629,0,1524128.0,947184.0,0.0,0.0,64,0x7ff4f36e8e80,4096,0,978,0,4158,0,1001,0,4096,0,414,0,4096,0,0,0,4096,0,1458,0,4096,0,0,0,4096,0,0,0,4096,0,1092,0,4096,0,2987,0,4096,0,76,0,4096,0,83,0,4147,0,343,0,4097,0,609,0,4264,0,1179,0,4096,0,7370,0,4096,0,0,0,4096,0,785,0,4096,0,5350,0,4096,0,706,0,4096,0,1201,0,4144,0,0,0,4096,0,1058,0,4096,0,548,0,4096,0,36,0,4096,0,0,0,4096,0,6958,0,4096,0,0,0,4096,0,7,0,4096,0,1878,0,4096,0,8,0,4096,0,374,0,4096,0,3352,0,64,0x7fdaab01ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86816.0,44256.0,131111.0,0.0,64,0x7f9df031ce80,0.0,64,0x7f386c6e8e80,1910718,360448,163840,0,0,180224,114688,0,66539140.0,174421414.0,69256432.0,131072.0,0.0,580885.0,0,0,26416,97053.0,0.0,0.0,97053.0,64,0x7f3181e46e80,3750,0,0,2061528,4846,0,0,2080547,514,0,0,1597659,7024,0,0,2252326,1970,0,0,1894437,2134,0,0,1868633,2647,0,0,1916586,1238,0,0,1785532,2938,0,0,1948555,3066,0,0,1995087,1252,0,0,1779475,2203,0,0,1929115,786,0,0,1678182,2342,0,0,1917609,1229,0,0,1758845,4634,0,0,2114935,1336,0,0,1794762,3775,0,0,1990163,1944,0,0,1824254,4676,0,0,2077567,3157,0,0,1905990,3482,0,0,2009873,1780,0,0,1840598,2690,0,0,1943182,2748,0,0,1949612,1478,0,0,1780467,844,0,0,1690141,3646,0,0,1990961,2463,0,0,1940602,2871,0,0,1942940,822,0,0,1629396,2696,0,0,1855922,194175534630063,194175534654063 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2ff3a2ce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f38f5026e80,0,3730758,2710,2710,0,2857500,2714,2714,0,3320981,2684,2684,0,3627348,2699,2699,0,4631889,2680,2680,0,3092063,2716,2716,0,4451987,2726,2726,0,3029416,2704,2704,0,2767081,2694,2694,0,3629576,2672,2672,0,3461007,2732,2732,0,4807161,2734,2734,0,3027758,2689,2689,0,2820472,2690,2690,0,5184852,2696,2696,0,3357257,2696,2696,0,3122965,2684,2684,0,3645606,2696,2696,0,3775492,2714,2714,0,5505112,2708,2708,0,2980985,2710,2710,0,2962877,2751,2751,0,3885791,2700,2700,0,3420854,2678,2678,0,3643768,2704,2704,0,2954889,2702,2702,0,3699972,2770,2770,0,3494429,2712,2712,0,5008264,2696,2696,0,2361236,2703,2703,0,3052037,2736,2736,0,3315948,2692,2692,64,0x7f2651730e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,37896,0,131120.0,131072.0,0.0,86566.0,64,0x7f10a1dace80,188416,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14948,31332,8504,2935,0,41565,262480.0,0.0,47.0,262433.0,64,0x7f54835f8e80,0,0,48,0,65536,65536,0,0,30911,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42159,1785,0,48.0,269.0,0.0,262144.0,64,0x7f198b1aae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131502.0,0.0,858.0,131501.0,64,0x7f2f2cb3ae80,131072.0,131072.0,0.0,2608589.0,0.0,0.0,131582951.0,47551352.0,64,0x7fc916404e80,32768,0,0,0,16384,16384,393216,23044109,960.0,513965.0,0.0,524288.0,1029652.0,32768.0,0,0,0,17369,86880.0,86880.0,0.0,86880.0,64,0x7f68399ece80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,47,8241,4192,8288,0,8192,4096,8192,0,8318,4222,8318,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f04bf79ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,64651.0,132167.0,64,0x7f7d506f8e80,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,0,42653,0,0,64,0x7f7b2b544e80,345736,230713,3366319,16384,24790999,0,48,0,43216,43216,3750746.0,3029503.0,6947.0,1039487.0,1983035.0,0.0,3020525.0,2708717.0,345728,240499,43216,0,43216,0,1382912.0,809587.0,0.0,0.0,64,0x7ff4f36e8e80,4096,0,5891,0,4101,0,1534,0,4096,0,879,0,4097,0,1291,0,4096,0,2092,0,4096,0,995,0,4096,0,0,0,4096,0,124,0,4096,0,802,0,4097,0,907,0,4096,0,0,0,4144,0,306,0,4097,0,500,0,4264,0,2372,0,4096,0,737,0,4096,0,0,0,4096,0,487,0,4096,0,4067,0,4096,0,788,0,4097,0,0,0,4144,0,387,0,4098,0,8199,0,4096,0,366,0,4096,0,0,0,4096,0,243,0,4096,0,409,0,4096,0,123,0,4096,0,312,0,4096,0,457,0,4096,0,107,0,4096,0,0,0,4096,0,0,0,64,0x7fdaab01ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86987.0,0.0,131112.0,0.0,64,0x7f9df031ce80,0.0,64,0x7f386c6e8e80,1864794,360448,163840,0,0,180224,114688,0,75023055.0,181388560.0,87290481.0,131072.0,0.0,1263903.0,0,0,25952,78370.0,0.0,0.0,78370.0,64,0x7f3181e46e80,1617,0,0,1446712,1768,0,0,1399721,778,0,0,1282477,2725,0,0,1531793,1029,0,0,1309542,1118,0,0,1316644,2165,0,0,1466185,1964,0,0,1523918,584,0,0,1314175,1262,0,0,1346603,386,0,0,1209320,690,0,0,1242367,3651,0,0,1633179,1765,0,0,1435961,1484,0,0,1381723,787,0,0,1285247,1835,0,0,1424774,1178,0,0,1361958,2350,0,0,1459414,273,0,0,1237649,189,0,0,1187320,1491,0,0,1421555,2789,0,0,1523250,744,0,0,1261382,2044,0,0,1550260,1322,0,0,1379589,1369,0,0,1339007,3946,0,0,1568806,1197,0,0,1360930,4167,0,0,1673404,1069,0,0,1314914,1252,0,0,1295860,194175534674223,194175534693583 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f2ff3a2ce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f38f5026e80,0,4039275,2704,2704,0,4218459,2720,2720,0,3524312,2670,2670,0,3860485,2706,2706,0,4373901,2686,2686,0,4390180,2752,2752,0,3689027,2692,2692,0,4776511,2688,2688,0,3537225,2700,2700,0,3735470,2696,2696,0,2920512,2696,2696,0,4649975,2740,2740,0,3693519,2696,2696,0,4326681,2685,2685,0,3189227,2702,2702,0,3640645,2686,2686,0,3816684,2678,2678,0,4811703,2720,2720,0,3945291,2674,2674,0,3852008,2696,2696,0,3814103,2702,2702,0,4344788,2732,2732,0,4555691,2680,2680,0,3329113,2680,2680,0,3585353,2660,2660,0,3987490,2698,2698,0,3424274,2730,2730,0,3841736,2684,2684,0,4695746,2703,2703,0,3509414,2693,2693,0,3533763,2686,2686,0,3726479,2696,2696,64,0x7f2651730e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3254,38225,0,131432.0,131072.0,0.0,86863.0,64,0x7f10a1dace80,187879,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13677,30061,8577,2931,0,40757,262448.0,0.0,47.0,262401.0,64,0x7f54835f8e80,0,0,48,0,65536,65536,0,0,30529,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41969,1694,0,48.0,269.0,0.0,262144.0,64,0x7f198b1aae80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131513.0,0.0,880.0,131512.0,64,0x7f2f2cb3ae80,131072.0,131072.0,0.0,2561610.0,0.0,0.0,122364251.0,46993469.0,64,0x7fc916404e80,32768,0,0,0,16384,16384,393216,23716225,960.0,513941.0,0.0,524288.0,1219967.0,32768.0,0,0,0,14300,86593.0,86593.0,0.0,86593.0,64,0x7f68399ece80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,47,8241,4192,8288,0,8192,4096,8192,0,8323,4227,8323,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f04bf79ce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,39985.0,105962.0,64,0x7f7d506f8e80,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,0,44347,0,0,64,0x7f7b2b544e80,343144,231940,3377112,16384,24588238,0,48,0,42892,42892,3763830.0,3044981.0,5993.0,1281767.0,2075963.0,0.0,3035894.0,2726534.0,343136,240048,42892,0,42892,0,1372544.0,816637.0,0.0,0.0,64,0x7ff4f36e8e80,4096,0,1856,0,4131,0,1295,0,4096,0,2148,0,4097,0,2166,0,4096,0,1325,0,4096,0,1073,0,4096,0,1187,0,4096,0,671,0,4096,0,1182,0,4097,0,721,0,4096,0,509,0,4144,0,1724,0,4097,0,3309,0,4264,0,7334,0,4096,0,807,0,4096,0,308,0,4096,0,2053,0,4096,0,4881,0,4096,0,1255,0,4097,0,220,0,4144,0,3038,0,4098,0,1136,0,4096,0,2457,0,4096,0,763,0,4096,0,161,0,4096,0,2087,0,4096,0,3291,0,4096,0,143,0,4096,0,114,0,4096,0,29,0,4096,0,580,0,4096,0,1265,0,64,0x7fdaab01ee80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86738.0,0.0,131112.0,0.0,64,0x7f9df031ce80,0.0,64,0x7f386c6e8e80,1616194,360448,163840,0,0,180224,114688,0,70097697.0,201432489.0,69154637.0,131072.0,0.0,808778.0,0,0,26015,91632.0,0.0,0.0,91632.0,64,0x7f3181e46e80,1882,0,0,1459609,899,0,0,1264047,3515,0,0,1637505,4640,0,0,1673873,1149,0,0,1346630,3027,0,0,1604086,3867,0,0,1649127,2210,0,0,1492681,896,0,0,1384333,1860,0,0,1481329,1826,0,0,1445826,581,0,0,1299729,3116,0,0,1597195,787,0,0,1318848,1228,0,0,1347218,4675,0,0,1676980,1131,0,0,1323690,100,0,0,1202894,866,0,0,1372352,3110,0,0,1616044,1060,0,0,1360500,1397,0,0,1455057,2844,0,0,1539021,1756,0,0,1442569,2682,0,0,1547143,1149,0,0,1339255,4079,0,0,1662855,3832,0,0,1622283,3414,0,0,1629849,1533,0,0,1379329,4458,0,0,1734060,2138,0,0,1429122,194175534779503,194175534798543 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_1,obj_1,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_2,obj_2,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_3,obj_3,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_10,obj_10,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_11,obj_11,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_12,obj_12,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_13,obj_13,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_14,obj_14,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_15,obj_15,TCC_EA_ATOMIC_LEVEL_sum,wave_size_16,obj_16,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fc30f694ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87348.0,43724.0,131115.0,0.0,64,0x7febbf978ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131427.0,0.0,702.0,131426.0,64,0x7fd3331f8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f0423f78ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8416,4367,8463,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8288,4192,8288,0,8192,4096,8192,64,0x7f86859a0ec0,0,3512791,4096,4096,0,4075185,4096,4096,0,4050354,4096,4096,0,3291762,4096,4096,0,3648117,4096,4096,0,3475915,4096,4096,0,3401715,4096,4096,0,4876180,4096,4096,0,3564576,4096,4096,0,4954479,4096,4096,0,3577417,4096,4096,0,3897536,4096,4096,0,3937814,4096,4096,0,3200961,4096,4096,0,4307023,4096,4096,0,3437387,4096,4096,0,3469997,4096,4096,0,4081154,4096,4096,0,4559960,4096,4096,0,3410129,4096,4096,0,3622592,4096,4096,0,4278017,4096,4096,0,3663285,4096,4096,0,3512199,4096,4096,0,3747528,4096,4096,0,3763701,4096,4096,0,4056891,4096,4096,0,4076337,4096,4096,0,3769795,4096,4096,0,3456594,4096,4096,0,3737070,4096,4096,0,3683305,4096,4096,64,0x7f3533fd8ec0,0,0,192,0,65536,64483,48,1340,31836,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48894,1884,0,48.0,345.0,0.0,262288.0,64,0x7f03fadb0ec0,131072.0,131072.0,0.0,2397655.0,0.0,0.0,91464616.0,62880703.0,64,0x7f4f40544ec0,188620,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13332,29716,9867,588,0,46106,262677.0,0.0,188.0,262489.0,64,0x7f4ac1df8ec0,397360,247249,3606399,16384,26665627,144,48,0,49669,49669,4061022.0,3133855.0,7117.0,1222708.0,2219234.0,0.0,3124558.0,2812713.0,395903,257200,49669,0,49669,0,1589408.0,992409.0,0.0,0.0,64,0x7f15a9140ec0,32768,0,0,0,16384,16384,393216,22578123,960.0,513867.0,0.0,524288.0,985426.0,32768.0,0,0,0,16772,131072.0,131072.0,0.0,131072.0,64,0x7f3220bc8ec0,4096,0,1299,0,4096,0,0,0,4096,0,25,0,4099,0,0,0,4096,0,194,0,4096,0,1030,0,4097,0,0,0,4096,0,0,0,4096,0,9,0,4096,0,0,0,4096,0,843,0,4144,0,0,0,4096,0,450,0,4096,0,0,0,4096,0,747,0,4096,0,0,0,4096,0,560,0,4096,0,9570,0,4096,0,0,0,4096,0,0,0,4096,0,92,0,4096,0,0,0,4311,0,505,0,4096,0,1211,0,4096,0,1269,0,4096,0,141,0,4144,0,64,0,4096,0,95,0,4096,0,483,0,4096,0,874,0,4096,0,0,0,4096,0,88,0,64,0x7f9024270ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,56535.0,123636.0,64,0x7fa1fe0bcec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,48024,0,131602.0,131072.0,0.0,131104.0,64,0x7f999865cec0,2155958,360448,163840,0,0,180224,114688,0,63695534.0,181199542.0,74505077.0,131072.0,0.0,804135.0,0,0,26498,137304.0,0.0,0.0,137304.0,64,0x7fd2cf110ec0,1685,0,0,1826847,2360,0,0,1860759,2027,0,0,1821394,3197,0,0,1901423,1329,0,0,1716767,1034,0,0,1626266,875,0,0,1712843,2757,0,0,2059626,2470,0,0,1893736,1951,0,0,1838109,2377,0,0,1936004,1213,0,0,1798810,1258,0,0,1657001,1529,0,0,1818839,3836,0,0,2088713,1079,0,0,1761429,4638,0,0,2078907,1003,0,0,1684209,3012,0,0,2027863,2071,0,0,1863477,1709,0,0,1796774,2034,0,0,1805821,5878,0,0,2246656,1991,0,0,1868345,2172,0,0,1874076,1206,0,0,1677991,3871,0,0,2139344,5253,0,0,2076311,1859,0,0,1878838,3865,0,0,2072964,3565,0,0,1968075,1693,0,0,1859162,64,0x7fe405ce8ec0,0.0,64,0x7fd64e238ec0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,0,48276,0,0,1410100033478037,1410100033502197 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fc30f694ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,63792.0,36508.0,83751.0,0.0,64,0x7febbf978ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131791.0,0.0,1434.0,131789.0,64,0x7fd3331f8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f0423f78ec0,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8481,4432,8528,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8288,4192,8288,0,8192,4096,8192,64,0x7f86859a0ec0,0,3976751,2746,2746,0,3235262,2728,2728,0,3044451,2719,2719,0,3832340,2748,2748,0,3828952,2699,2699,0,3230555,2752,2752,0,3213971,2757,2757,0,3906586,2751,2751,0,3559697,2726,2726,0,3046972,2708,2708,0,3153001,2754,2754,0,3573120,2742,2742,0,3689377,2744,2744,0,3073893,2710,2710,0,3502741,2732,2732,0,3277733,2746,2746,0,3865264,2728,2728,0,3821840,2740,2740,0,4021725,2737,2737,0,3793872,2760,2760,0,3633571,2738,2738,0,4711348,2737,2737,0,3758264,2698,2698,0,2991069,2696,2696,0,3689540,2724,2724,0,3246738,2720,2720,0,3465070,2738,2738,0,3690412,2748,2748,0,3310688,2728,2728,0,2931025,2704,2704,0,3818240,2744,2744,0,3614424,2732,2732,64,0x7f3533fd8ec0,0,0,48,0,65536,65536,0,0,32056,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,44234,1694,0,48.0,388.0,0.0,262144.0,64,0x7f03fadb0ec0,131072.0,131072.0,0.0,2426353.0,0.0,0.0,107627540.0,49685710.0,64,0x7f4f40544ec0,189150,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12283,28667,8619,2408,0,41664,262556.0,0.0,47.0,262509.0,64,0x7f4ac1df8ec0,341384,233097,3403978,16384,25027673,0,48,0,42672,42672,3785876.0,3052246.0,7020.0,1076341.0,2098175.0,0.0,3043055.0,2731106.0,341376,242871,42672,0,42672,0,1365504.0,810597.0,0.0,0.0,64,0x7f15a9140ec0,32768,0,0,0,16384,16384,393216,22105908,960.0,513997.0,0.0,524288.0,812354.0,32768.0,0,0,0,13513,86875.0,86875.0,0.0,86875.0,64,0x7f3220bc8ec0,4096,0,531,0,4099,0,489,0,4096,0,204,0,4096,0,0,0,4096,0,9296,0,4097,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,82,0,4096,0,670,0,4144,0,1145,0,4096,0,1134,0,4096,0,0,0,4096,0,313,0,4096,0,839,0,4096,0,394,0,4096,0,1744,0,4096,0,615,0,4096,0,0,0,4096,0,500,0,4096,0,0,0,4278,0,840,0,4096,0,0,0,4096,0,0,0,4096,0,736,0,4144,0,0,0,4096,0,33,0,4096,0,0,0,4097,0,406,0,4096,0,0,0,4096,0,0,0,64,0x7f9024270ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,79567.0,149743.0,64,0x7fa1fe0bcec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5117,45204,1068,131909.0,131072.0,0.0,101064.0,64,0x7f999865cec0,2593036,360448,163840,0,0,180224,114688,0,62159453.0,174238750.0,66434037.0,131072.0,0.0,886033.0,0,0,26787,75940.0,0.0,0.0,75940.0,64,0x7fd2cf110ec0,3566,0,0,1563547,5989,0,0,1827753,2133,0,0,1558770,7918,0,0,1902753,908,0,0,1357752,2263,0,0,1533636,1389,0,0,1451083,4274,0,0,1726467,613,0,0,1284997,2826,0,0,1620161,1550,0,0,1426455,639,0,0,1397839,2395,0,0,1604147,4910,0,0,1762981,868,0,0,1357925,4618,0,0,1687716,1691,0,0,1381251,893,0,0,1401858,2622,0,0,1498832,5376,0,0,1782192,1100,0,0,1293889,2744,0,0,1590412,6568,0,0,1860968,6050,0,0,1800894,1836,0,0,1448440,1553,0,0,1434269,2760,0,0,1585630,4625,0,0,1696053,506,0,0,1202905,6189,0,0,1774715,3353,0,0,1662679,925,0,0,1406030,64,0x7fe405ce8ec0,0.0,64,0x7fd64e238ec0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,0,43847,0,0,1410100033593877,1410100033612597 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fc30f694ec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86999.0,0.0,131112.0,0.0,64,0x7febbf978ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131421.0,0.0,696.0,131420.0,64,0x7fd3331f8ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f0423f78ec0,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8458,4409,8505,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8288,4192,8288,0,8192,4096,8192,64,0x7f86859a0ec0,0,4461761,2704,2704,0,3466720,2704,2704,0,4060341,2690,2690,0,3897505,2703,2703,0,3888352,2688,2688,0,3706792,2694,2694,0,3736151,2704,2704,0,4705413,2681,2681,0,3753589,2725,2725,0,3431345,2696,2696,0,3862428,2668,2668,0,3601176,2724,2724,0,4293758,2712,2712,0,3325524,2704,2704,0,4219062,2700,2700,0,3926287,2694,2694,0,3799414,2696,2696,0,3441928,2700,2700,0,4070602,2684,2684,0,3811901,2728,2728,0,3695054,2688,2688,0,4401082,2743,2743,0,3929467,2684,2684,0,3191490,2712,2712,0,3577087,2690,2690,0,3567360,2696,2696,0,4153744,2727,2727,0,3333947,2698,2698,0,3523290,2692,2692,0,3898407,2696,2696,0,3957767,2706,2706,0,3433115,2686,2686,64,0x7f3533fd8ec0,0,0,48,0,65536,65536,0,0,31551,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,43449,1734,0,48.0,385.0,0.0,262144.0,64,0x7f03fadb0ec0,131072.0,131072.0,0.0,2483507.0,0.0,0.0,96272680.0,49886972.0,64,0x7f4f40544ec0,189766,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14437,30821,8571,2414,0,40605,262540.0,0.0,47.0,262493.0,64,0x7f4ac1df8ec0,339472,231527,3380998,16384,24964507,0,48,0,42433,42433,3761911.0,3017583.0,7070.0,1043331.0,2057628.0,0.0,3008883.0,2697688.0,339464,241095,42433,0,42433,0,1357856.0,807631.0,0.0,0.0,64,0x7f15a9140ec0,32768,0,0,0,16384,16384,393216,22475190,960.0,513889.0,0.0,524288.0,1117908.0,32768.0,0,0,0,13113,86624.0,86625.0,0.0,86624.0,64,0x7f3220bc8ec0,4096,0,1308,0,4099,0,694,0,4096,0,0,0,4096,0,0,0,4096,0,6129,0,4097,0,123,0,4097,0,842,0,4096,0,34,0,4096,0,52,0,4096,0,3785,0,4096,0,0,0,4144,0,863,0,4096,0,1047,0,4096,0,847,0,4096,0,0,0,4096,0,54,0,4096,0,1567,0,4096,0,4931,0,4096,0,1741,0,4096,0,0,0,4096,0,221,0,4096,0,644,0,4230,0,59,0,4096,0,61,0,4096,0,0,0,4096,0,1156,0,4144,0,0,0,4096,0,202,0,4096,0,40,0,4097,0,919,0,4096,0,0,0,4096,0,89,0,64,0x7f9024270ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,66174.0,140962.0,64,0x7fa1fe0bcec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2685,39960,0,131487.0,131072.0,0.0,86546.0,64,0x7f999865cec0,1825824,360448,163840,0,0,180224,114688,0,67127863.0,184758876.0,76601215.0,131072.0,0.0,858131.0,0,0,26832,108089.0,0.0,0.0,108089.0,64,0x7fd2cf110ec0,1616,0,0,1409054,2894,0,0,1594410,923,0,0,1272513,5769,0,0,1770206,814,0,0,1230202,1734,0,0,1419924,2682,0,0,1547898,2193,0,0,1491855,604,0,0,1209722,474,0,0,1236197,1189,0,0,1391919,1295,0,0,1448270,1531,0,0,1385158,1224,0,0,1371506,886,0,0,1282401,2861,0,0,1503989,771,0,0,1292369,2405,0,0,1602214,2719,0,0,1530684,2236,0,0,1439181,1134,0,0,1309982,682,0,0,1324571,1317,0,0,1375824,2983,0,0,1531154,1082,0,0,1387922,1318,0,0,1368581,1722,0,0,1485274,5935,0,0,1818492,1870,0,0,1538158,2441,0,0,1569172,701,0,0,1311460,2418,0,0,1480520,64,0x7fe405ce8ec0,0.0,64,0x7fd64e238ec0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,0,42072,0,0,1410100033638517,1410100033657077 diff --git a/tests/workloads/kernel_substr/MI100/sysinfo.csv b/tests/workloads/kernel_substr/MI100/sysinfo.csv index 05fc83f224..5e1c91244f 100644 --- a/tests/workloads/kernel_substr/MI100/sysinfo.csv +++ b/tests/workloads/kernel_substr/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:07:08 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:52:33 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_substr/MI100/timestamps.csv b/tests/workloads/kernel_substr/MI100/timestamps.csv index 0bb2631ecf..068c3433bb 100644 --- a/tests/workloads/kernel_substr/MI100/timestamps.csv +++ b/tests/workloads/kernel_substr/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534602589,194175534630063,194175534654063,194175534670638 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534666220,194175534674223,194175534693583,194175534776909 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,141682,141682,1048576,256,0,0,8,8,16,64,0x0,0x7feb54db6e80,194175534704713,194175534779503,194175534798543,194175534799382 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1237413,1237413,1048576,256,0,0,8,8,16,64,0x0,0x7f91afc6cec0,1410100033451844,1410100033478037,1410100033502197,1410100033513600 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1237413,1237413,1048576,256,0,0,8,8,16,64,0x0,0x7f91afc6cec0,1410100033514522,1410100033593877,1410100033612597,1410100033617336 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1237413,1237413,1048576,256,0,0,8,8,16,64,0x0,0x7f91afc6cec0,1410100033624710,1410100033638517,1410100033657077,1410100033658564 diff --git a/tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv index 8b70492427..cfbdb237d9 100644 --- a/tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,27737,27737,16384,65536,13722,1525308,198261588061508,198274458325591,198274458345911,198261603806363 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,41413,41413,16384,65536,9460,1048596,198261603830830,198274458365591,198274458381111,198261604082847 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291276,291276,1048576,256,0,0,8,0,16,64,0x0,0x7f1828160ec0,40275,40275,16384,65536,9096,1048700,198261604112302,198274458443671,198274458459991,198261604256605 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4114786,4114786,1048576,256,0,0,8,0,16,64,0x0,0x7f7efac7cec0,27808,27808,16384,65536,13399,1542552,1411747993352852,1411760919537410,1411760919557090,1411748009210180 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4114786,4114786,1048576,256,0,0,8,0,16,64,0x0,0x7f7efac7cec0,42345,42345,16384,65536,9466,1048672,1411748009231631,1411760919576130,1411760919591970,1411748009550113 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4114786,4114786,1048576,256,0,0,8,0,16,64,0x0,0x7f7efac7cec0,41809,41809,16384,65536,9261,1048648,1411748009579198,1411760919648450,1411760919664930,1411748009739572 diff --git a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv index c71c742441..7df0a2c619 100644 --- a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262073743594,198274458325591,198274458345911,198262089831408 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262089848571,198274458365591,198274458381111,198262090150562 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291478,291478,1048576,256,0,0,8,0,16,64,0x0,0x7f1f8e050ec0,0,0,0,198262090176932,198274458443671,198274458459991,198262090341423 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4114972,4114972,1048576,256,0,0,8,0,16,64,0x0,0x7fe2c102cec0,0,0,0,1411748492261360,1411760919537410,1411760919557090,1411748508646486 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4114972,4114972,1048576,256,0,0,8,0,16,64,0x0,0x7fe2c102cec0,0,0,0,1411748508665692,1411760919576130,1411760919591970,1411748508945812 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4114972,4114972,1048576,256,0,0,8,0,16,64,0x0,0x7fe2c102cec0,0,0,0,1411748508971250,1411760919648450,1411760919664930,1411748509120252 diff --git a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv index 53d0c0d4e9..2eccfa8d4a 100644 --- a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,187092,20917768,198262558091736,198274458325591,198274458345911,198262574290691 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,245200,27582200,198262574309346,198274458365591,198274458381111,198262574602852 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291685,291685,1048576,256,0,0,8,0,16,64,0x0,0x7fddd2fc4ec0,65536,263490,29654280,198262574629011,198274458443671,198274458459991,198262574756552 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4115172,4115172,1048576,256,0,0,8,0,16,64,0x0,0x7f98c6ce0ec0,65536,191466,21343568,1411748975548556,1411760919537410,1411760919557090,1411748991614648 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4115172,4115172,1048576,256,0,0,8,0,16,64,0x0,0x7f98c6ce0ec0,65536,266474,29803832,1411748991632112,1411760919576130,1411760919591970,1411748991928322 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4115172,4115172,1048576,256,0,0,8,0,16,64,0x0,0x7f98c6ce0ec0,65536,269860,30194104,1411748991954391,1411760919648450,1411760919664930,1411748992109995 diff --git a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv index 1ead472d42..26dc86fa12 100644 --- a/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,288882,32369320,198263038694323,198274458325591,198274458345911,198263054914017 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,596098,66767128,198263054932602,198274458365591,198274458381111,198263055228652 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,291870,291870,1048576,256,0,0,8,0,16,64,0x0,0x7f5a50b30ec0,32768,572975,64171428,198263055254551,198274458443671,198274458459991,198263055412490 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4115370,4115370,1048576,256,0,0,8,0,16,64,0x0,0x7f400bee0ec0,32768,293469,32855948,1411749461257651,1411760919537410,1411760919557090,1411749477699425 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4115370,4115370,1048576,256,0,0,8,0,16,64,0x0,0x7f400bee0ec0,32768,562268,62950004,1411749477717519,1411760919576130,1411760919591970,1411749478030080 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4115370,4115370,1048576,256,0,0,8,0,16,64,0x0,0x7f400bee0ec0,32768,583160,65318136,1411749478056540,1411760919648450,1411760919664930,1411749478223946 diff --git a/tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv index 5a7e560ed0..ce5937be30 100644 --- a/tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,27371,27371,10912,218976,16384,10605927,126253,0,42923692,198263526253279,198274458325591,198274458345911,198263542014035 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,41749,41749,13458,334000,16384,19718416,225192,0,79338420,198263542042509,198274458365591,198274458381111,198263542340142 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,292068,292068,1048576,256,0,0,8,0,16,64,0x0,0x7f06a0314ec0,41423,41423,13486,331392,16384,19225946,220329,0,77380152,198263542374808,198274458443671,198274458459991,198263542550089 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4115572,4115572,1048576,256,0,0,8,0,16,64,0x0,0x7f08ef3d8ec0,28866,28866,11064,230936,16384,11619166,137356,0,46984496,1411749950842366,1411760919537410,1411760919557090,1411749966997337 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4115572,4115572,1048576,256,0,0,8,0,16,64,0x0,0x7f08ef3d8ec0,41555,41555,13750,332448,16384,19544648,223581,0,78671448,1411749967023126,1411760919576130,1411760919591970,1411749967377907 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4115572,4115572,1048576,256,0,0,8,0,16,64,0x0,0x7f08ef3d8ec0,42294,42294,14213,338360,16384,19749746,227566,0,79473776,1411749967412673,1411760919648450,1411760919664930,1411749967581332 diff --git a/tests/workloads/kernel_substr/MI200/log.txt b/tests/workloads/kernel_substr/MI200/log.txt new file mode 100644 index 0000000000..e6b65b97ad --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/log.txt @@ -0,0 +1,764 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/kernel_substr/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: ['vecCopy'] +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_162015' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162015_4114626' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162015_4114626/input0_results_240321_162015' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162015_4114626/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162015_4114626/input0_results_240321_162015 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_162016' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162016_4114812' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162016_4114812/input0_results_240321_162016' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162016_4114812/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162016_4114812/input0_results_240321_162016 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_162016' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162016_4115012' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162016_4115012/input0_results_240321_162016' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162016_4115012/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162016_4115012/input0_results_240321_162016 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_162017' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162017_4115210' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162017_4115210/input0_results_240321_162017' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162017_4115210/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162017_4115210/input0_results_240321_162017 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_162017' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162017_4115412' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162017_4115412/input0_results_240321_162017' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162017_4115412/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162017_4115412/input0_results_240321_162017 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_162018' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162018_4115614' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162018_4115614/input0_results_240321_162018' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162018_4115614/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162018_4115614/input0_results_240321_162018 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_162018' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162018_4115800' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162018_4115800/input0_results_240321_162018' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162018_4115800/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162018_4115800/input0_results_240321_162018 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_162019' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162019_4116004' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162019_4116004/input0_results_240321_162019' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162019_4116004/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162019_4116004/input0_results_240321_162019 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_162019' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162019_4116192' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162019_4116192/input0_results_240321_162019' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162019_4116192/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162019_4116192/input0_results_240321_162019 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_162020' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162020_4116376' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162020_4116376/input0_results_240321_162020' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162020_4116376/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162020_4116376/input0_results_240321_162020 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_162020' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162020_4116562' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162020_4116562/input0_results_240321_162020' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162020_4116562/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162020_4116562/input0_results_240321_162020 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_162021' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162021_4116749' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162021_4116749/input0_results_240321_162021' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162021_4116749/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162021_4116749/input0_results_240321_162021 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_162022' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162022_4116935' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162022_4116935/input0_results_240321_162022' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162022_4116935/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162022_4116935/input0_results_240321_162022 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_162022' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162022_4117123' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162022_4117123/input0_results_240321_162022' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162022_4117123/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162022_4117123/input0_results_240321_162022 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_162023' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162023_4117308' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162023_4117308/input0_results_240321_162023' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162023_4117308/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162023_4117308/input0_results_240321_162023 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_162024' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162024_4117498' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162024_4117498/input0_results_240321_162024' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162024_4117498/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162024_4117498/input0_results_240321_162024 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_162024' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162024_4117686' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162024_4117686/input0_results_240321_162024' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162024_4117686/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162024_4117686/input0_results_240321_162024 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_162025' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162025_4117888' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162025_4117888/input0_results_240321_162025' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162025_4117888/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162025_4117888/input0_results_240321_162025 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_162025' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162025_4118072' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162025_4118072/input0_results_240321_162025' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162025_4118072/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162025_4118072/input0_results_240321_162025 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_162026' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162026_4118275' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162026_4118275/input0_results_240321_162026' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162026_4118275/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162026_4118275/input0_results_240321_162026 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_162026' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162026_4118477' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162026_4118477/input0_results_240321_162026' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162026_4118477/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162026_4118477/input0_results_240321_162026 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_162027' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162027_4118664' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162027_4118664/input0_results_240321_162027' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162027_4118664/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162027_4118664/input0_results_240321_162027 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_162027' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162027_4118848' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162027_4118848/input0_results_240321_162027' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162027_4118848/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162027_4118848/input0_results_240321_162027 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_162028' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162028_4119050' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162028_4119050/input0_results_240321_162028' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162028_4119050/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162028_4119050/input0_results_240321_162028 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] + +[profiling] Current input file: tests/workloads/kernel_substr/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_162028' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/kernel_substr/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_162028_4119234' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_162028_4119234/input0_results_240321_162028' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_162028_4119234/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = vecCopy + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_162028_4119234/input0_results_240321_162028 + |-> [rocprof] File 'tests/workloads/kernel_substr/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/kernel_substr/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/kernel_substr/MI200/pmc_dispatch_info.csv b/tests/workloads/kernel_substr/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/kernel_substr/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/kernel_substr/MI200/pmc_perf.csv b/tests/workloads/kernel_substr/MI200/pmc_perf.csv index 51c316491f..87932091b0 100644 --- a/tests/workloads/kernel_substr/MI200/pmc_perf.csv +++ b/tests/workloads/kernel_substr/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_2,obj_2,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_4,obj_4,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_8,obj_8,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_9,obj_9,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_10,obj_10,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_15,obj_15,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_16,obj_16,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_17,obj_17,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_18,obj_18,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc7904dcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13004,18932,7874,549,0,26619,204514.0,0.0,73434.0,131080.0,64,0x7faff393cec0,0,0,0,224,0,65536,64188,56,64,0x7f223ef64ec0,1313,119251,0,0,65536,63800,56,1680,64,0x7f19107b0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7feea913cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,33283.0,46226.0,19310.0,64,0x7f9ffc0b4ec0,6376,0,4096,6386,0,4096,6344,0,4096,6398,0,4096,6382,0,4096,6417,0,4096,6351,0,4096,6378,0,4096,6385,0,4096,6376,0,4096,6387,0,4096,6343,0,4096,6400,0,4096,6386,0,4096,6419,0,4096,6352,0,4096,6372,0,4096,6422,0,4096,6367,0,4096,6373,0,4096,6391,0,4096,6384,0,4096,6375,0,4096,6566,0,4096,6400,0,4096,6373,0,4096,6419,0,4096,6366,0,4096,6377,0,4096,6395,0,4096,6384,0,4096,6377,0,4096,64,0x7f67db69cec0,32768,32768,0,64,0x7f049309cec0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,0,27738,0,0,64,0x7fc6c1854ec0,114688,0,32768,32768,16384,16384,65536,49152,27257494.0,85490762.0,39095499.0,131072.0,0.0,268787.0,0,0,14989,1702.0,131084.0,0.0,16.0,64,0x7fe9e6918ec0,0,1033742,4096,4096,0,1019599,4096,4096,0,1054388,4096,4096,0,1453904,4096,4096,0,1240436,4096,4096,0,1635037,4096,4096,0,1121779,4096,4096,0,1702478,4096,4096,0,1093607,4096,4096,0,1143623,4096,4096,0,1345115,4096,4096,0,1189783,4096,4096,0,1193569,4096,4096,0,1269702,4096,4096,0,1284594,4096,4096,0,1094663,4096,4096,0,1122970,4096,4096,0,1234759,4096,4096,0,1061768,4096,4096,0,1284004,4096,4096,0,1082447,4096,4096,0,1051924,4096,4096,0,1100095,4096,4096,0,1183188,4096,4096,0,1206288,4096,4096,0,978759,4096,4096,0,990566,4096,4096,0,1215900,4096,4096,0,1238654,4096,4096,0,1146068,4096,4096,0,956874,4096,4096,0,1492576,4096,4096,64,0x7f199c754ec0,0,0,0,985896,0,0,0,994973,0,0,0,1041563,0,0,0,1103413,0,0,0,1058256,13,0,0,1173206,0,0,0,1226489,0,0,0,1172264,0,0,0,1064170,0,0,0,1002555,0,0,0,951994,0,0,0,1100200,0,0,0,1106245,0,0,0,1108103,0,0,0,1063005,0,0,0,1159874,0,0,0,1069785,0,0,0,1013227,0,0,0,1025809,0,0,0,1074738,0,0,0,1036234,0,0,0,1169822,0,0,0,1036439,0,0,0,1059264,0,0,0,1052678,0,0,0,1067493,0,0,0,970020,0,0,0,1047972,0,0,0,1048722,0,0,0,1041952,46,0,0,1217914,0,0,0,1149545,64,0x7f1d333e8ec0,2278,4096,2278,6374,2307,4096,2307,6403,2220,4096,2220,6316,2288,4096,2288,6384,2318,4096,2318,6414,2265,4096,2265,6361,2276,4096,2276,6372,2309,4096,2309,6405,2312,4096,2312,6408,2282,4096,2282,6378,2304,4096,2304,6400,2217,4096,2217,6313,2288,4096,2288,6384,2318,4096,2318,6414,2268,4096,2268,6364,2281,4098,2283,6379,2253,4096,2253,6349,2278,4096,2278,6374,2292,4097,2293,6389,2287,4096,2287,6383,2370,4097,2371,6467,2275,4096,2275,6371,2262,4096,2262,6358,2447,4098,2449,6545,2280,4096,2280,6376,2253,4096,2253,6349,2278,4096,2278,6374,2296,4096,2296,6392,2285,4096,2285,6381,2315,4096,2315,6411,2270,4096,2270,6366,2261,4096,2261,6357,64,0x7f9d86b3cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41959520.0,35169861.0,0.0,64,0x7f593fb84ec0,230704,128479,16384,0,16384,16384,32768,49152,28837,28837,1947964.0,1347970.0,3594.0,169822.0,1056685.0,0.0,1340330.0,1041593.0,228993,136622,28837,0,28837,0,922784.0,488635.0,0.0,0.0,64,0x7fd2e13d4ec0,10634719,9719648,571007,344064,1629318,0,0,163840,832.0,515136.0,0.0,524288.0,271923.0,32768.0,438720,0,0,10880,131072.0,131072.0,0.0,131072.0,64,0x7f08042a8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,965696.0,64,0x7f44d6ac8ec0,4100,0,0,0,4096,0,0,0,4096,0,15,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,44,0,4096,0,40,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,25,0,4097,0,369,0,4096,0,0,0,4099,0,41,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f9b671d0ec0,0,393216,163840,0,0,0,0,0,18304,0.0,0.0,0.0,32768.0,0.0,0.0,384.0,32768.0,4096,16384,352,28478,1930,0,56.0,10.0,0.0,204259.0,64,0x7f21ee0dcec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10357,0,814,27948,0,73468.0,131072.0,0.0,65568.0,198274458325591,198274458345911 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc7904dcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30552,27524,9616,2391,0,38508,200318.0,0.0,69236.0,131082.0,64,0x7faff393cec0,0,0,0,56,0,65536,65536,0,64,0x7f223ef64ec0,0,187903,0,0,65536,63800,56,1680,64,0x7f19107b0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7feea913cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,96946.0,45623.0,0.0,64,0x7f9ffc0b4ec0,6245,0,4096,6263,0,4096,6252,0,4096,6229,0,4096,6259,0,4096,6266,0,4096,6258,0,4096,6301,0,4096,6296,0,4096,6242,0,4096,6268,0,4096,6256,0,4096,6230,0,4096,6262,0,4096,6268,0,4096,6259,0,4096,6287,0,4096,6300,0,4096,6299,0,4096,6284,0,4096,6276,0,4096,6254,0,4096,6268,0,4096,6247,0,4096,6244,0,4096,6289,0,4096,6304,0,4096,6304,0,4096,6290,0,4096,6278,0,4096,6251,0,4096,6274,0,4096,64,0x7f67db69cec0,32768,32768,0,64,0x7f049309cec0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,0,41751,0,0,64,0x7fc6c1854ec0,114688,0,32768,32768,16384,16384,65536,49152,58698711.0,195304384.0,50451452.0,131072.0,0.0,466162.0,0,0,23491,8909.0,131075.0,0.0,4.0,64,0x7fe9e6918ec0,0,2881157,2828,2828,0,3745023,2856,2856,0,2739060,2872,2872,0,5238866,2880,2880,0,3755192,2880,2880,0,4952010,2856,2856,0,3114359,2856,2856,0,4224218,2796,2796,0,3223435,2796,2796,0,3529313,2828,2828,0,4109685,2856,2856,0,3392227,2882,2882,0,3544484,2880,2880,0,3728617,2884,2884,0,4695870,2856,2856,0,3189513,2856,2856,0,3192664,2808,2808,0,5010406,2826,2826,0,2791750,2864,2864,0,3472889,2880,2880,0,2935072,2848,2848,0,3539950,2900,2900,0,3298391,2828,2828,0,3487321,2832,2832,0,4840777,2832,2832,0,2895087,2808,2808,0,2906623,2836,2836,0,4249521,2864,2864,0,3905343,2878,2878,0,3175579,2846,2846,0,3128286,2900,2900,0,3998597,2828,2828,64,0x7f199c754ec0,0,0,0,1643563,127,0,0,2125780,55,0,0,2172061,447,0,0,2132887,0,0,0,1493116,414,0,0,2044416,13,0,0,1599927,0,0,0,1885384,0,0,0,1792428,0,0,0,1818619,0,0,0,1674757,0,0,0,1642989,0,0,0,1679671,0,0,0,1524889,267,0,0,2107507,0,0,0,1690633,0,0,0,1821482,0,0,0,1913169,0,0,0,1752794,0,0,0,2089516,65,0,0,1787600,278,0,0,2075529,0,0,0,1735512,207,0,0,1962830,111,0,0,2000643,0,0,0,1633525,450,0,0,2168429,0,0,0,1828094,70,0,0,2079901,0,0,0,1571734,247,0,0,2138705,0,0,0,1649740,64,0x7f1d333e8ec0,2151,4096,2151,6247,2194,4096,2194,6290,2157,4096,2157,6253,2162,4096,2162,6258,2150,4096,2150,6246,2164,4096,2164,6260,2180,4096,2180,6276,2180,4096,2180,6276,2184,4096,2184,6280,2154,4096,2154,6250,2197,4096,2197,6293,2159,4097,2160,6256,2169,4097,2170,6266,2151,4096,2151,6247,2168,4096,2168,6264,2186,4098,2188,6284,2172,4096,2172,6268,2167,4096,2167,6263,2179,4097,2180,6276,2191,4096,2191,6287,2261,4097,2262,6358,2177,4096,2177,6273,2181,4096,2181,6277,2190,4096,2190,6286,2191,4096,2191,6287,2169,4096,2169,6265,2172,4096,2172,6268,2181,4096,2181,6277,2190,4096,2190,6286,2209,4096,2209,6305,2184,4098,2186,6282,2183,4096,2183,6279,64,0x7f9d86b3cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,117590644.0,61488183.0,0.0,64,0x7f593fb84ec0,348752,236962,16384,0,16384,16384,32768,49152,43593,43593,3356834.0,2551636.0,4303.0,412372.0,1766757.0,0.0,2540480.0,2233898.0,348744,246019,43593,0,43593,0,1394976.0,800157.0,0.0,0.0,64,0x7fd2e13d4ec0,18659369,17583236,732069,344064,2688784,0,0,163840,832.0,515136.0,0.0,524288.0,583967.0,32768.0,873113,0,0,13746,91358.0,91358.0,0.0,91358.0,64,0x7f08042a8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2086319.0,64,0x7f44d6ac8ec0,4099,0,32,0,4096,0,351,0,4096,0,377,0,4096,0,479,0,4096,0,580,0,4096,0,923,0,4096,0,593,0,4096,0,1158,0,4096,0,381,0,4096,0,769,0,4097,0,570,0,4096,0,112,0,4096,0,29,0,4096,0,218,0,4096,0,145,0,4096,0,799,0,4096,0,455,0,4096,0,1376,0,4098,0,404,0,4099,0,447,0,4096,0,656,0,4097,0,364,0,4096,0,716,0,4096,0,1693,0,4096,0,1162,0,4096,0,236,0,4096,0,266,0,4096,0,391,0,4096,0,458,0,4096,0,239,0,4096,0,262,0,4096,0,1285,0,64,0x7f9b671d0ec0,0,393216,163840,0,0,0,0,0,28042,0.0,0.0,0.0,32768.0,0.0,0.0,265.0,32768.0,4096,16384,302,37155,2067,0,56.0,0.0,0.0,200137.0,64,0x7f21ee0dcec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21254,0,2679,38933,0,68994.0,131072.0,0.0,45739.0,198274458365591,198274458381111 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc7904dcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29573,26124,9671,3081,0,39425,200697.0,0.0,69616.0,131081.0,64,0x7faff393cec0,0,0,0,56,0,65536,65536,0,64,0x7f223ef64ec0,0,187181,0,0,65536,63800,56,1680,64,0x7f19107b0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7feea913cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,79654.0,45543.0,0.0,64,0x7f9ffc0b4ec0,6298,0,4096,6309,0,4096,6286,0,4096,6264,0,4096,6284,0,4096,6294,0,4096,6241,0,4096,6284,0,4096,6283,0,4096,6299,0,4096,6316,0,4096,6291,0,4096,6264,0,4096,6289,0,4096,6292,0,4096,6240,0,4096,6250,0,4096,6292,0,4096,6290,0,4096,6301,0,4096,6277,0,4096,6271,0,4096,6284,0,4096,6302,0,4096,6301,0,4096,6253,0,4096,6295,0,4096,6290,0,4096,6305,0,4096,6275,0,4096,6272,0,4096,6285,0,4096,64,0x7f67db69cec0,32768,32768,0,64,0x7f049309cec0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,0,41574,0,0,64,0x7fc6c1854ec0,114688,0,32768,32768,16384,16384,65536,49152,58212958.0,197519865.0,49132344.0,131072.0,0.0,533879.0,0,0,24937,5851.0,131085.0,0.0,24.0,64,0x7fe9e6918ec0,0,4356472,2828,2828,0,3288185,2884,2884,0,3816220,2870,2870,0,3605685,2878,2878,0,4402901,2840,2840,0,4215553,2804,2804,0,3078132,2868,2868,0,5340439,2828,2828,0,4019367,2828,2828,0,3343309,2832,2832,0,3769122,2880,2880,0,3647927,2876,2876,0,3273461,2876,2876,0,2952778,2840,2840,0,3434794,2800,2800,0,3142437,2868,2868,0,3618008,2832,2832,0,4261142,2882,2882,0,2772119,2860,2860,0,3881202,2862,2862,0,2959369,2864,2864,0,3880458,2900,2900,0,3372624,2800,2800,0,4267076,2800,2800,0,3074208,2808,2808,0,4323476,2832,2832,0,4159107,2882,2882,0,3376068,2860,2860,0,3354840,2860,2860,0,3243808,2864,2864,0,2743939,2900,2900,0,3744213,2800,2800,64,0x7f199c754ec0,330,0,0,2015523,329,0,0,1934009,0,0,0,1698775,0,0,0,1830600,0,0,0,1570437,0,0,0,1723781,0,0,0,1628088,0,0,0,1803509,196,0,0,1835850,0,0,0,1838590,72,0,0,1820132,0,0,0,1512457,0,0,0,1700082,0,0,0,1718959,773,0,0,2246371,0,0,0,1921622,0,0,0,1441712,0,0,0,1743923,0,0,0,1557593,367,0,0,2014000,0,0,0,1655504,0,0,0,1973003,0,0,0,1898184,2418,0,0,2858471,0,0,0,1826583,0,0,0,1646209,0,0,0,1554784,0,0,0,1762517,10,0,0,1971514,0,0,0,1522047,803,0,0,2397542,0,0,0,1839256,64,0x7f1d333e8ec0,2205,4096,2205,6301,2197,4096,2197,6293,2139,4096,2139,6235,2167,4096,2167,6263,2156,4096,2156,6252,2183,4096,2183,6279,2180,4096,2180,6276,2185,4096,2185,6281,2190,4096,2190,6286,2209,4096,2209,6305,2199,4096,2199,6295,2139,4097,2140,6236,2168,4097,2169,6265,2159,4096,2159,6255,2187,4096,2187,6283,2182,4098,2184,6280,2186,4096,2186,6282,2170,4096,2170,6266,2179,4097,2180,6276,2181,4096,2181,6277,2231,4097,2232,6328,2167,4096,2167,6263,2176,4096,2176,6272,2170,4096,2170,6266,2174,4096,2174,6270,2189,4096,2189,6285,2174,4096,2174,6270,2182,4096,2182,6278,2182,4096,2182,6278,2185,4096,2185,6281,2171,4098,2173,6269,2174,4096,2174,6270,64,0x7f9d86b3cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,124672508.0,68439286.0,0.0,64,0x7f593fb84ec0,327280,217804,16384,0,16384,16384,32768,49152,40909,40909,3108602.0,2423817.0,4712.0,332028.0,1803004.0,0.0,2412312.0,2101451.0,327272,227089,40909,0,40909,0,1309088.0,774275.0,0.0,0.0,64,0x7fd2e13d4ec0,18667839,17597573,726202,344064,2674403,0,0,163840,830.0,515158.0,0.0,524288.0,686997.0,32768.0,893984,0,0,14181,90870.0,90870.0,0.0,90870.0,64,0x7f08042a8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2048412.0,64,0x7f44d6ac8ec0,4100,0,474,0,4096,0,469,0,4096,0,806,0,4096,0,2529,0,4096,0,525,0,4096,0,1198,0,4096,0,1121,0,4096,0,973,0,4096,0,1198,0,4096,0,683,0,4097,0,410,0,4096,0,153,0,4096,0,335,0,4096,0,1511,0,4096,0,0,0,4096,0,1533,0,4096,0,1828,0,4096,0,1185,0,4098,0,1938,0,4099,0,387,0,4096,0,1060,0,4097,0,708,0,4096,0,1694,0,4096,0,1100,0,4096,0,618,0,4096,0,778,0,4096,0,741,0,4096,0,2023,0,4096,0,1887,0,4096,0,293,0,4096,0,832,0,4096,0,822,0,64,0x7f9b671d0ec0,0,393216,163840,0,0,0,0,0,30732,0.0,0.0,0.0,32768.0,0.0,0.0,224.0,32768.0,4096,16384,302,42229,1958,0,56.0,11.0,0.0,201241.0,64,0x7f21ee0dcec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21087,0,2674,38799,0,69906.0,131072.0,0.0,45562.0,198274458443671,198274458459991 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_1,obj_1,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_3,obj_3,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_4,obj_4,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_5,obj_5,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_8,obj_8,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_9,obj_9,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_12,obj_12,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_13,obj_13,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_14,obj_14,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_15,obj_15,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_16,obj_16,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_17,obj_17,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_18,obj_18,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa387b74ec0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,0,27884,0,0,64,0x7f54b78e0ec0,0,393216,163840,0,0,0,0,0,17971,0.0,0.0,0.0,32768.0,0.0,0.0,416.0,32768.0,4096,16384,352,29101,1965,0,56.0,6.0,0.0,204403.0,64,0x7f7d8ede8ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,1003962.0,64,0x7f8095564ec0,11185972,9981917,859991,344064,1661275,0,0,163840,832.0,515146.0,0.0,524288.0,293405.0,32768.0,497155,0,0,10948,131072.0,131072.0,0.0,131072.0,64,0x7fbc828fcec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,117,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,381,0,4096,0,0,0,4097,0,34,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,138,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7ff82552cec0,0,0,0,1062798,0,0,0,1059246,0,0,0,1112400,53,0,0,1223818,69,0,0,1101026,0,0,0,1069842,0,0,0,1006223,0,0,0,1111959,0,0,0,990686,0,0,0,992135,0,0,0,987870,0,0,0,1109034,0,0,0,1071775,0,0,0,1149760,0,0,0,988282,0,0,0,1089005,0,0,0,982225,0,0,0,1067988,0,0,0,1036861,0,0,0,1054471,0,0,0,1067959,82,0,0,1221970,0,0,0,1057528,0,0,0,1113779,0,0,0,1049121,0,0,0,1068427,0,0,0,1059770,0,0,0,1153900,0,0,0,1013444,0,0,0,1119367,30,0,0,1169392,313,0,0,1370247,64,0x7f2030324ec0,32768,32768,0,64,0x7ff214b3cec0,2257,4097,2258,6354,2252,4096,2252,6348,2307,4096,2307,6403,2274,4096,2274,6370,2242,4096,2242,6338,2269,4096,2269,6365,2279,4096,2279,6375,2321,4096,2321,6417,2323,4096,2323,6419,2261,4096,2261,6357,2252,4096,2252,6348,2306,4096,2306,6402,2277,4096,2277,6373,2299,4097,2300,6396,2266,4096,2266,6362,2279,4096,2279,6375,2321,4096,2321,6417,2295,4096,2295,6391,2257,4098,2259,6355,2307,4096,2307,6403,2284,4096,2284,6380,2334,4096,2334,6430,2296,4097,2297,6393,2427,4098,2429,6525,2264,4096,2264,6360,2321,4096,2321,6417,2297,4096,2297,6393,2261,4096,2261,6357,2308,4096,2308,6404,2285,4096,2285,6381,2335,4096,2335,6431,2298,4096,2298,6394,64,0x7f5a489b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,35027.0,46276.0,19260.0,64,0x7f011e368ec0,6356,0,4096,6381,0,4096,6380,0,4096,6399,0,4096,6370,0,4096,6381,0,4096,6325,0,4096,6398,0,4096,6400,0,4096,6360,0,4096,6381,0,4096,6377,0,4096,6401,0,4096,6371,0,4096,6385,0,4096,6327,0,4096,6427,0,4096,6377,0,4096,6371,0,4096,6367,0,4096,6360,0,4096,6431,0,4096,6386,0,4096,6538,0,4096,6371,0,4096,6424,0,4096,6380,0,4096,6373,0,4096,6370,0,4096,6365,0,4096,6433,0,4096,6388,0,4096,64,0x7f0a90424ec0,0,0,0,224,0,65536,64223,56,64,0x7f283b5e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40966616.0,36255179.0,0.0,64,0x7f2b372f8ec0,226864,126044,16384,0,16384,16384,32768,49152,28357,28357,1916621.0,1338826.0,3525.0,167602.0,1046422.0,0.0,1331068.0,1032820.0,225153,134184,28357,0,28357,0,907424.0,484563.0,0.0,0.0,64,0x7fddade1cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,8533,0,814,27227,0,73359.0,131072.0,0.0,65568.0,64,0x7f0a74eb0ec0,1300,118167,0,0,65536,63800,56,1680,64,0x7f4e7c1d0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f85f4dc4ec0,0,1093745,4096,4096,0,1251104,4096,4096,0,1288744,4096,4096,0,1310429,4096,4096,0,1290744,4096,4096,0,1318136,4096,4096,0,1171220,4096,4096,0,1247014,4096,4096,0,1079936,4096,4096,0,1158315,4096,4096,0,1140659,4096,4096,0,1279034,4096,4096,0,1158932,4096,4096,0,1272684,4096,4096,0,1388216,4096,4096,0,1314701,4096,4096,0,1220541,4096,4096,0,1466894,4096,4096,0,1266563,4096,4096,0,1337318,4096,4096,0,1238506,4096,4096,0,1215606,4096,4096,0,1291890,4096,4096,0,1347449,4096,4096,0,1328336,4096,4096,0,1273784,4096,4096,0,1171913,4096,4096,0,1356530,4096,4096,0,1243249,4096,4096,0,1211903,4096,4096,0,1196401,4096,4096,0,1499509,4096,4096,64,0x7f2586cc8ec0,114688,0,32768,32768,16384,16384,65536,49152,28303340.0,88283046.0,39728054.0,131072.0,0.0,251942.0,0,0,15747,1198.0,131082.0,0.0,12.0,64,0x7f593b40cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14374,18631,8102,545,0,27884,204302.0,0.0,73221.0,131081.0,1411760919537410,1411760919557090 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa387b74ec0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,0,41379,0,0,64,0x7f54b78e0ec0,0,393216,163840,0,0,0,0,0,31630,0.0,0.0,0.0,32768.0,0.0,0.0,237.0,32768.0,4096,16384,302,43214,2072,0,56.0,10.0,0.0,200672.0,64,0x7f7d8ede8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2085482.0,64,0x7f8095564ec0,19242572,18285029,613479,344064,2749491,0,0,163840,832.0,515136.0,0.0,524288.0,682707.0,32768.0,920373,0,0,14236,91384.0,91384.0,0.0,91384.0,64,0x7fbc828fcec0,4096,0,303,0,4097,0,720,0,4096,0,440,0,4096,0,314,0,4096,0,710,0,4097,0,142,0,4096,0,0,0,4096,0,105,0,4096,0,562,0,4097,0,0,0,4096,0,0,0,4096,0,274,0,4099,0,0,0,4096,0,0,0,4096,0,482,0,4096,0,0,0,4096,0,0,0,4096,0,240,0,4097,0,31,0,4096,0,1451,0,4096,0,863,0,4097,0,1098,0,4096,0,452,0,4096,0,140,0,4096,0,246,0,4096,0,0,0,4096,0,42,0,4100,0,56,0,4096,0,2437,0,4096,0,473,0,4096,0,89,0,4096,0,72,0,64,0x7ff82552cec0,90,0,0,1986257,260,0,0,2217681,0,0,0,1792470,0,0,0,2246888,1553,0,0,2150941,3,0,0,1944963,0,0,0,1549532,320,0,0,1979142,112,0,0,1916928,0,0,0,1735014,336,0,0,2204131,493,0,0,2107215,0,0,0,1813351,262,0,0,1927217,274,0,0,2019372,144,0,0,1994436,183,0,0,1999871,596,0,0,2004264,0,0,0,1890470,251,0,0,2166528,294,0,0,2390613,85,0,0,1960689,367,0,0,2159308,0,0,0,1959002,259,0,0,2134097,322,0,0,2028339,446,0,0,1840744,0,0,0,1814423,669,0,0,2364701,100,0,0,1915831,0,0,0,1794283,450,0,0,1993418,64,0x7f2030324ec0,32768,32768,0,64,0x7ff214b3cec0,2165,4097,2166,6262,2168,4096,2168,6264,2137,4096,2137,6233,2145,4096,2145,6241,2156,4096,2156,6252,2149,4096,2149,6245,2203,4096,2203,6299,2175,4096,2175,6271,2179,4096,2179,6275,2166,4096,2166,6262,2170,4096,2170,6266,2140,4096,2140,6236,2145,4096,2145,6241,2209,4097,2210,6306,2151,4096,2151,6247,2203,4096,2203,6299,2193,4097,2194,6290,2168,4096,2168,6264,2192,4098,2194,6290,2177,4099,2180,6276,2135,4096,2135,6231,2168,4096,2168,6264,2163,4097,2164,6260,2177,4096,2177,6273,2177,4096,2177,6273,2197,4096,2197,6293,2168,4096,2168,6264,2194,4096,2194,6290,2180,4097,2181,6277,2128,4096,2128,6224,2169,4096,2169,6265,2168,4096,2168,6264,64,0x7f5a489b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,84425.0,45632.0,0.0,64,0x7f011e368ec0,6303,0,4096,6318,0,4096,6278,0,4096,6237,0,4096,6298,0,4096,6303,0,4096,6260,0,4096,6285,0,4096,6284,0,4096,6310,0,4096,6323,0,4096,6280,0,4096,6238,0,4096,6297,0,4096,6307,0,4096,6259,0,4096,6269,0,4096,6277,0,4096,6329,0,4096,6326,0,4096,6272,0,4096,6278,0,4096,6284,0,4096,6276,0,4096,6277,0,4096,6269,0,4096,6278,0,4096,6334,0,4096,6331,0,4096,6270,0,4096,6277,0,4096,6283,0,4096,64,0x7f0a90424ec0,0,0,0,56,0,65536,65536,0,64,0x7f283b5e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,117150863.0,57306991.0,0.0,64,0x7f2b372f8ec0,323000,219636,16384,0,16384,16384,32768,49152,40374,40374,3132285.0,2436643.0,4731.0,366033.0,1713075.0,0.0,2425574.0,2116343.0,322992,229045,40374,0,40374,0,1291968.0,775627.0,0.0,0.0,64,0x7fddade1cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20300,0,2720,38382,0,69827.0,131072.0,0.0,45684.0,64,0x7f0a74eb0ec0,0,188431,0,0,65536,63800,56,1680,64,0x7f4e7c1d0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f85f4dc4ec0,0,3206307,2844,2844,0,3702823,2876,2876,0,3663523,2868,2868,0,4197934,2860,2860,0,3673270,2888,2888,0,3875209,2836,2836,0,3056106,2864,2864,0,4135076,2824,2824,0,3368853,2824,2824,0,3695938,2848,2848,0,4286737,2868,2868,0,3373112,2868,2868,0,3155972,2860,2860,0,4208013,2888,2888,0,3980722,2832,2832,0,3910564,2872,2872,0,4172805,2848,2848,0,4029374,2866,2866,0,3541176,2860,2860,0,3537193,2844,2844,0,3374025,2820,2820,0,3629067,2848,2848,0,3792033,2808,2808,0,4579099,2828,2828,0,4198390,2824,2824,0,3790812,2848,2848,0,3859781,2868,2868,0,4054043,2856,2856,0,3818289,2844,2844,0,3458601,2820,2820,0,3241395,2852,2852,0,3546292,2808,2808,64,0x7f2586cc8ec0,114688,0,32768,32768,16384,16384,65536,49152,58559423.0,190652554.0,48972504.0,131072.0,0.0,547118.0,0,0,25381,9900.0,131084.0,0.0,22.0,64,0x7f593b40cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30779,26723,9388,2436,0,39211,200428.0,0.0,69346.0,131082.0,1411760919576130,1411760919591970 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa387b74ec0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,0,41545,0,0,64,0x7f54b78e0ec0,0,393216,163840,0,0,0,0,0,31508,0.0,0.0,0.0,32768.0,0.0,0.0,189.0,32768.0,4096,16384,302,43123,2029,0,56.0,10.0,0.0,201029.0,64,0x7f7d8ede8ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2034579.0,64,0x7f8095564ec0,18342047,17397316,600667,344064,2672135,0,0,163840,832.0,515148.0,0.0,524288.0,644953.0,32768.0,899246,0,0,13470,91314.0,91314.0,0.0,91314.0,64,0x7fbc828fcec0,4096,0,930,0,4097,0,1053,0,4096,0,7,0,4096,0,1378,0,4096,0,448,0,4097,0,1114,0,4096,0,165,0,4096,0,2419,0,4096,0,442,0,4097,0,260,0,4096,0,1407,0,4096,0,1038,0,4098,0,380,0,4096,0,1309,0,4096,0,586,0,4096,0,103,0,4096,0,1312,0,4096,0,190,0,4097,0,205,0,4096,0,487,0,4096,0,1218,0,4097,0,142,0,4096,0,704,0,4096,0,786,0,4096,0,418,0,4096,0,578,0,4096,0,205,0,4100,0,233,0,4096,0,1060,0,4096,0,301,0,4096,0,579,0,4096,0,1333,0,64,0x7ff82552cec0,0,0,0,1603448,91,0,0,1663063,85,0,0,2120631,20,0,0,2027098,0,0,0,1588432,516,0,0,2253389,0,0,0,1546995,0,0,0,1701224,35,0,0,1736075,0,0,0,1689081,230,0,0,1800334,0,0,0,1662207,0,0,0,1681029,0,0,0,1548458,594,0,0,2180573,34,0,0,1795275,1040,0,0,2277922,259,0,0,2178418,0,0,0,1695691,156,0,0,1661538,1127,0,0,2652509,583,0,0,2346027,776,0,0,1990516,0,0,0,1921022,21,0,0,1879914,0,0,0,1498954,0,0,0,1725023,0,0,0,1521961,0,0,0,1809316,192,0,0,2292077,47,0,0,2115288,197,0,0,2125471,64,0x7f2030324ec0,32768,32768,0,64,0x7ff214b3cec0,2198,4097,2199,6295,2195,4096,2195,6291,2143,4096,2143,6239,2169,4096,2169,6265,2170,4096,2170,6266,2194,4096,2194,6290,2188,4096,2188,6284,2166,4096,2166,6262,2167,4096,2167,6263,2197,4096,2197,6293,2197,4096,2197,6293,2144,4096,2144,6240,2174,4096,2174,6270,2225,4097,2226,6322,2195,4096,2195,6291,2191,4096,2191,6287,2163,4097,2164,6260,2179,4096,2179,6275,2211,4098,2213,6309,2168,4099,2171,6267,2195,4096,2195,6291,2194,4096,2194,6290,2164,4097,2165,6261,2182,4096,2182,6278,2182,4096,2182,6278,2166,4096,2166,6262,2177,4096,2177,6273,2212,4096,2212,6308,2171,4097,2172,6268,2195,4096,2195,6291,2194,4096,2194,6290,2166,4096,2166,6262,64,0x7f5a489b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,97497.0,45660.0,0.0,64,0x7f011e368ec0,6275,0,4096,6308,0,4096,6268,0,4096,6260,0,4096,6301,0,4096,6307,0,4096,6276,0,4096,6260,0,4096,6265,0,4096,6280,0,4096,6308,0,4096,6269,0,4096,6259,0,4096,6306,0,4096,6308,0,4096,6282,0,4096,6240,0,4096,6291,0,4096,6300,0,4096,6309,0,4096,6260,0,4096,6278,0,4096,6279,0,4096,6314,0,4096,6312,0,4096,6244,0,4096,6295,0,4096,6301,0,4096,6315,0,4096,6260,0,4096,6281,0,4096,6281,0,4096,64,0x7f0a90424ec0,0,0,0,56,0,65536,65536,0,64,0x7f283b5e8ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119364316.0,56716847.0,0.0,64,0x7f2b372f8ec0,322240,216113,16384,0,16384,16384,32768,49152,40279,40279,3086368.0,2408166.0,4485.0,348358.0,1779695.0,0.0,2395569.0,2085153.0,322232,225271,40279,0,40279,0,1288928.0,768495.0,0.0,0.0,64,0x7fddade1cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,18496,0,2691,37992,0,69659.0,131072.0,0.0,45503.0,64,0x7f0a74eb0ec0,0,184394,0,0,65536,63800,56,1680,64,0x7f4e7c1d0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f85f4dc4ec0,0,3768011,2828,2828,0,3928499,2860,2860,0,3705985,2828,2828,0,4610854,2804,2804,0,3947737,2890,2890,0,3766042,2856,2856,0,3000389,2884,2884,0,4097806,2848,2848,0,3359530,2844,2844,0,3853419,2828,2828,0,5778330,2852,2852,0,3219598,2836,2836,0,3292412,2804,2804,0,3957802,2892,2892,0,3396864,2856,2856,0,3371648,2884,2884,0,3394097,2812,2812,0,3928701,2864,2864,0,3622092,2872,2872,0,4434528,2864,2864,0,3672508,2800,2800,0,3146039,2844,2844,0,4238381,2856,2856,0,3432688,2840,2840,0,3654475,2840,2840,0,2882593,2812,2812,0,3279511,2864,2864,0,3652491,2868,2868,0,5218286,2864,2864,0,3250472,2800,2800,0,3350342,2844,2844,0,3897740,2856,2856,64,0x7f2586cc8ec0,114688,0,32768,32768,16384,16384,65536,49152,57173005.0,202702773.0,49307206.0,131072.0,0.0,613042.0,0,0,25692,40693.0,131084.0,0.0,22.0,64,0x7f593b40cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,33652,28203,9529,2433,0,39780,200813.0,0.0,69730.0,131083.0,1411760919648450,1411760919664930 diff --git a/tests/workloads/kernel_substr/MI200/roofline.csv b/tests/workloads/kernel_substr/MI200/roofline.csv index 5b47ca7e0f..efb81d0a75 100644 --- a/tests/workloads/kernel_substr/MI200/roofline.csv +++ b/tests/workloads/kernel_substr/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.4747,1387.9553,1388.9941,5014.9604,5012.063,5017.8579,9222.5117,9221.9268,9223.0967,18050.73,18049.891,18051.57,20930.57,20869.91,20991.23,20265.133,20264.418,20265.848,170420.36,170416.08,170424.64,164859.31,164854.41,164864.22,41417.266,41416.672,41417.859,41477.48,41476.703,41478.258,166330.06,165840.5,166819.62 -1,1389.7251,1389.1949,1390.2552,5028.3931,5026.2188,5030.5674,9234.2783,9233.5322,9235.0244,18087.188,18083.588,18090.787,20971.094,20904.305,21037.883,20291.975,20291.318,20292.631,170824.14,170818.92,170829.36,165082.02,165078.61,165085.42,41468.77,41467.949,41469.59,41525.664,41524.758,41526.57,166822.78,166819.69,166825.88 -2,1388.7198,1388.2028,1389.2369,5036.1206,5033.917,5038.3242,9261.9297,9261.1611,9262.6982,18106.574,18105.59,18107.559,21049.045,21048.621,21049.469,20356.066,20355.422,20356.711,171138.38,171134.81,171141.94,165494.95,165491.14,165498.77,41581.402,41580.301,41582.504,41641.324,41640.227,41642.422,166971.16,166374.72,167567.59 -3,1388.6997,1388.0704,1389.329,5030.8838,5029.3442,5032.4233,9239.749,9239.2314,9240.2666,18025.273,18022.016,18028.531,21030.592,21030.15,21031.033,20311.781,20311.162,20312.4,171031.81,171027.84,171035.78,165235.41,165231.41,165239.41,41440.09,41286.125,41594.055,41580.582,41580.031,41581.133,167008.56,167006.89,167010.23 +0,1388.9658,1388.3842,1389.5475,5015.9883,5012.938,5019.0386,9225.1172,9224.5098,9225.7246,17715.531,17712.326,17718.736,20938.605,20878.021,20999.189,20270.34,20269.768,20270.912,170471.98,170468.02,170475.95,164910.77,164906.02,164915.52,41434.18,41433.711,41434.648,41492.617,41491.949,41493.285,166394.14,165902.47,166885.81 +1,1389.0469,1388.5142,1389.5796,5028.8301,5026.8472,5030.813,9236.9521,9236.207,9237.6973,18239.07,18236.047,18242.094,20985.062,20918.174,21051.951,20304.107,20303.527,20304.688,170946.45,170942.11,170950.8,165186.3,165182.33,165190.27,41504.238,41503.312,41505.164,41562.047,41561.035,41563.059,166949,166945.52,166952.48 +2,1388.8693,1388.3575,1389.381,5035.5464,5033.2891,5037.8037,9260.1914,9259.3496,9261.0332,18218.021,18217.1,18218.943,21053.375,21052.932,21053.818,20353.885,20353.205,20354.564,171154.2,171149.33,171159.08,165526.98,165523.47,165530.5,41583.637,41582.98,41584.293,41644.199,41643.281,41645.117,166959.98,166367,167552.97 +3,1389.0635,1388.4847,1389.6422,5033.917,5032.3442,5035.4897,9239.7314,9239.0586,9240.4043,18333.445,18332.5,18334.391,21036.664,21036.422,21036.906,20312.801,20312.271,20313.33,171053,171047.16,171058.84,165173.69,165169.31,165178.06,41435.715,41282.48,41588.949,41581.074,41579.879,41582.27,166969.88,166965.3,166974.45 diff --git a/tests/workloads/kernel_substr/MI200/sysinfo.csv b/tests/workloads/kernel_substr/MI200/sysinfo.csv index 8015b33c74..0b43aab07b 100644 --- a/tests/workloads/kernel_substr/MI200/sysinfo.csv +++ b/tests/workloads/kernel_substr/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_substr,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:15:28 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +kernel_substr,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:20:15 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_substr/MI200/timestamps.csv b/tests/workloads/kernel_substr/MI200/timestamps.csv index 010b4e7495..76a7d0e35c 100644 --- a/tests/workloads/kernel_substr/MI200/timestamps.csv +++ b/tests/workloads/kernel_substr/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458301241,198274458325591,198274458345911,198274458362076 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458356796,198274458365591,198274458381111,198274458440294 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,295872,295872,1048576,256,0,0,8,0,16,64,0x0,0x7f38a4160ec0,198274458391411,198274458443671,198274458459991,198274458461033 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4119394,4119394,1048576,256,0,0,8,0,16,64,0x0,0x7fac132a4ec0,1411760919510468,1411760919537410,1411760919557090,1411760919572024 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4119394,4119394,1048576,256,0,0,8,0,16,64,0x0,0x7fac132a4ec0,1411760919567997,1411760919576130,1411760919591970,1411760919645724 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4119394,4119394,1048576,256,0,0,8,0,16,64,0x0,0x7fac132a4ec0,1411760919602192,1411760919648450,1411760919664930,1411760919666122 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_summaries/MI100/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 2b541b8403..0000000000 --- a/tests/workloads/kernel_summaries/MI100/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,215990,215990,1048576,256,0,0,8,8,16,64,0x0,0x7faa16204e80,48096,48096,16384,65536,14355,1831748,194416751403173,194428972583416,194428972607736,194416759267063 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,215990,215990,1048576,256,0,0,8,8,16,64,0x0,0x7faa16204e80,43657,43657,16384,65536,8199,1048580,194416759288023,194428972707576,194428972726776,194416759622877 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,215990,215990,1048576,256,0,0,8,8,16,64,0x0,0x7faa16204e80,41833,41833,16384,65536,8226,1048580,194416759655488,194428972748536,194428972767576,194416759834237 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 0dbf0c6197..0000000000 --- a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,216173,216173,1048576,256,0,0,8,8,16,64,0x0,0x7fa816e2ce80,0,0,0,194417244983698,194428972583416,194428972607736,194417252760674 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,216173,216173,1048576,256,0,0,8,8,16,64,0x0,0x7fa816e2ce80,0,0,0,194417252781453,194428972707576,194428972726776,194417253062866 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,216173,216173,1048576,256,0,0,8,8,16,64,0x0,0x7fa816e2ce80,0,0,0,194417253091119,194428972748536,194428972767576,194417253271030 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index 9191db990b..0000000000 --- a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,216356,216356,1048576,256,0,0,8,8,16,64,0x0,0x7f9e5d034e80,65536,198380,25401768,194417733358146,194428972583416,194428972607736,194417741014643 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,216356,216356,1048576,256,0,0,8,8,16,64,0x0,0x7f9e5d034e80,65536,168952,21660192,194417741033098,194428972707576,194428972726776,194417741359927 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,216356,216356,1048576,256,0,0,8,8,16,64,0x0,0x7f9e5d034e80,65536,168730,21630264,194417741388111,194428972748536,194428972767576,194417741559796 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index 035466fbd8..0000000000 --- a/tests/workloads/kernel_summaries/MI100/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,216539,216539,1048576,256,0,0,8,8,16,64,0x0,0x7f022c520e80,32768,669548,85698544,194418219490729,194428972583416,194428972607736,194418227310776 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,216539,216539,1048576,256,0,0,8,8,16,64,0x0,0x7f022c520e80,32768,673709,86240076,194418227329812,194428972707576,194428972726776,194418227630281 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,216539,216539,1048576,256,0,0,8,8,16,64,0x0,0x7f022c520e80,32768,661351,84660532,194418227658024,194428972748536,194428972767576,194418227830230 diff --git a/tests/workloads/kernel_summaries/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_summaries/MI100/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 82606048b6..0000000000 --- a/tests/workloads/kernel_summaries/MI100/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,216722,216722,1048576,256,0,0,8,8,16,64,0x0,0x7f26d9ffae80,48339,48339,16433,386720,16384,25179289,237134,0,101213380,194418712048118,194428972583416,194428972607736,194418719919130 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,216722,216722,1048576,256,0,0,8,8,16,64,0x0,0x7f26d9ffae80,42466,42466,13655,339736,16384,24728801,227275,0,99412392,194418719949498,194428972707576,194428972726776,194418720265226 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,216722,216722,1048576,256,0,0,8,8,16,64,0x0,0x7f26d9ffae80,42418,42418,13366,339352,16384,24564212,229221,0,98746920,194418720303188,194428972748536,194428972767576,194418720487567 diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index 202141726e..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6f289aa046..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_10.txt deleted file mode 100644 index a00555d953..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_11.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_12.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_13.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_14.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_15.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_16.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 2180ee3f63..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_3.txt deleted file mode 100644 index 8f1ba90d04..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_4.txt deleted file mode 100644 index 9a82481329..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_5.txt deleted file mode 100644 index bbc1f21123..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_6.txt deleted file mode 100644 index b6368182b4..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_7.txt deleted file mode 100644 index 3f7673fd23..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_8.txt deleted file mode 100644 index facba6bd95..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_9.txt deleted file mode 100644 index d458645ea4..0000000000 --- a/tests/workloads/kernel_summaries/MI100/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_summaries/MI100/pmc_dispatch_info.csv deleted file mode 100644 index 17300ae9af..0000000000 --- a/tests/workloads/kernel_summaries/MI100/pmc_dispatch_info.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_summaries/MI100/pmc_perf.csv b/tests/workloads/kernel_summaries/MI100/pmc_perf.csv deleted file mode 100644 index a1f4beda8f..0000000000 --- a/tests/workloads/kernel_summaries/MI100/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_2,obj_2,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_3,obj_3,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_4,obj_4,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_5,obj_5,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_6,obj_6,TCC_EA_ATOMIC_LEVEL_sum,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_12,obj_12,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_13,obj_13,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_14,obj_14,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_15,obj_15,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_16,obj_16,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8f33d5ae80,227103,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11234,27618,9940,550,0,47416,262635.0,0.0,188.0,262447.0,64,0x7f361ebb6e80,2146,0,0,1808402,2097,0,0,1821650,4088,0,0,2131814,2646,0,0,1804199,2374,0,0,1879783,4209,0,0,1966661,2784,0,0,1906887,2573,0,0,1981464,3467,0,0,2099779,2884,0,0,1917234,4670,0,0,2009231,2168,0,0,1804542,1675,0,0,1755146,3936,0,0,1931652,4647,0,0,2038922,4788,0,0,2152189,3261,0,0,1999103,2376,0,0,1863769,3260,0,0,1908826,2578,0,0,1937213,3457,0,0,1876113,2866,0,0,1870040,4246,0,0,1978765,1960,0,0,1803352,4711,0,0,2075358,2054,0,0,1709292,3629,0,0,1990811,2856,0,0,1817385,5279,0,0,2199211,1177,0,0,1582758,5374,0,0,2070196,2227,0,0,1807925,64,0x7f175e00ee80,0,0,192,0,65536,64413,48,1353,31457,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47589,1700,0,48.0,297.0,0.0,262288.0,64,0x7f5e77b24e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86278.0,44794.0,131111.0,0.0,64,0x7fe574ab8e80,2080266,360448,163840,0,0,180224,114688,0,69187372.0,191887911.0,75981985.0,131072.0,0.0,586995.0,0,0,27123,79738.0,0.0,0.0,79738.0,64,0x7f90004bce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70744.0,134054.0,64,0x7f11a7a0ee80,0.0,64,0x7f9f92604e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47446,0,131606.0,131072.0,0.0,131104.0,64,0x7f7ad2b34e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131342.0,0.0,532.0,131341.0,64,0x7f5a02362e80,4096,0,6870,0,4096,0,0,0,4099,0,0,0,4096,0,218,0,4096,0,69,0,4144,0,0,0,4096,0,0,0,4096,0,1263,0,4096,0,832,0,4279,0,7617,0,4096,0,4272,0,4144,0,277,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,345,0,4096,0,2269,0,4096,0,914,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,72,0,4096,0,510,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,286,0,64,0x7f995aa2ce80,389768,238747,3503367,16384,25774112,144,48,0,48720,48720,3933806.0,3110584.0,5413.0,953200.0,2146723.0,0.0,3100100.0,2789501.0,388055,248670,48720,0,48720,0,1559040.0,979443.0,0.0,0.0,64,0x7fbd89c80e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8369,4273,8369,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,64,0x7f5856196e80,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,0,48052,0,0,64,0x7fece9b6ce80,131072.0,131072.0,0.0,2587371.0,0.0,0.0,126476725.0,59826737.0,64,0x7f09c32aae80,0,4127573,4096,4096,0,3032811,4096,4096,0,2887574,4096,4096,0,2883533,4096,4096,0,3072917,4096,4096,0,3128750,4096,4096,0,3807876,4096,4096,0,3092432,4096,4096,0,4714417,4096,4096,0,3296230,4096,4096,0,4704445,4096,4096,0,3158300,4096,4096,0,3027247,4096,4096,0,2909968,4096,4096,0,2820318,4096,4096,0,2675544,4096,4096,0,5503921,4096,4096,0,3342055,4096,4096,0,3439995,4096,4096,0,2290420,4096,4096,0,2995275,4096,4096,0,2826112,4096,4096,0,3310670,4096,4096,0,2997572,4096,4096,0,3106011,4096,4096,0,3038899,4096,4096,0,3110998,4096,4096,0,3129811,4096,4096,0,3015764,4096,4096,0,4064076,4096,4096,0,3267338,4096,4096,0,2891996,4096,4096,64,0x7feb195a4e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f4178150e80,32768,0,0,0,16384,16384,393216,21620542,960.0,513873.0,0.0,524288.0,1135474.0,32768.0,0,0,0,16561,131072.0,131072.0,0.0,131072.0,194428972583416,194428972607736 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8f33d5ae80,186788,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13116,29500,8523,3037,0,41701,262528.0,0.0,47.0,262481.0,64,0x7f361ebb6e80,1163,0,0,1360327,3375,0,0,1513861,5672,0,0,1780543,3356,0,0,1640753,4308,0,0,1670873,2351,0,0,1553395,5650,0,0,1681734,2514,0,0,1525301,2497,0,0,1567802,1990,0,0,1481875,5536,0,0,1685328,2033,0,0,1499998,4098,0,0,1638739,1731,0,0,1502036,4802,0,0,1727667,4148,0,0,1749367,1255,0,0,1352659,3266,0,0,1582524,4463,0,0,1681027,2898,0,0,1510856,2336,0,0,1476567,3205,0,0,1628110,4934,0,0,1715010,1968,0,0,1467369,4558,0,0,1623526,1540,0,0,1424142,5726,0,0,1689428,5183,0,0,1699838,5870,0,0,1741910,2497,0,0,1442370,4417,0,0,1671023,1282,0,0,1421149,64,0x7f175e00ee80,0,0,48,0,65536,65536,0,0,30776,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42101,1740,0,48.0,268.0,0.0,262144.0,64,0x7f5e77b24e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86864.0,0.0,131110.0,0.0,64,0x7fe574ab8e80,1794650,360448,163840,0,0,180224,114688,0,71876897.0,199760619.0,77775106.0,131072.0,0.0,611118.0,0,0,26432,62322.0,0.0,0.0,62322.0,64,0x7f90004bce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,66658.0,134718.0,64,0x7f11a7a0ee80,0.0,64,0x7f9f92604e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,4540,47638,1086,131557.0,131072.0,0.0,131103.0,64,0x7f7ad2b34e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131235.0,0.0,324.0,131234.0,64,0x7f5a02362e80,4096,0,5,0,4096,0,1360,0,4096,0,713,0,4096,0,1639,0,4096,0,0,0,4145,0,2036,0,4096,0,1733,0,4096,0,2308,0,4096,0,0,0,4262,0,3082,0,4096,0,377,0,4144,0,6983,0,4096,0,280,0,4096,0,591,0,4096,0,1600,0,4096,0,177,0,4096,0,0,0,4096,0,1242,0,4096,0,1206,0,4096,0,176,0,4096,0,0,0,4096,0,1418,0,4096,0,693,0,4097,0,0,0,4096,0,0,0,4097,0,1873,0,4096,0,74,0,4096,0,1570,0,4096,0,615,0,4096,0,559,0,4096,0,2405,0,4098,0,454,0,64,0x7f995aa2ce80,347840,236056,3428358,16384,24709920,0,48,0,43479,43479,3830906.0,3116003.0,7087.0,1274157.0,2192707.0,0.0,3106082.0,2794446.0,347832,245843,43479,0,43479,0,1391328.0,830777.0,0.0,0.0,64,0x7fbd89c80e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8324,4228,8324,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,64,0x7f5856196e80,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,0,42447,0,0,64,0x7fece9b6ce80,131072.0,131072.0,0.0,2541167.0,0.0,0.0,89178084.0,31665435.0,64,0x7f09c32aae80,0,4116291,2732,2732,0,3252725,2708,2708,0,3849005,2691,2691,0,3627731,2688,2688,0,3910497,2684,2684,0,3631585,2703,2703,0,3278098,2694,2694,0,3814972,2690,2690,0,5352424,2732,2732,0,4067071,2680,2680,0,3722341,2700,2700,0,3887840,2698,2698,0,3811211,2746,2746,0,3853787,2680,2680,0,4058700,2696,2696,0,3257937,2676,2676,0,4640786,2702,2702,0,4718048,2692,2692,0,3752690,2679,2679,0,3705766,2700,2700,0,3795072,2696,2696,0,4233340,2717,2717,0,3619676,2680,2680,0,3118514,2678,2678,0,4079647,2682,2682,0,3850344,2719,2719,0,3330379,2732,2732,0,3140054,2691,2691,0,3417002,2686,2686,0,3802025,2708,2708,0,3388474,2700,2700,0,4085759,2709,2709,64,0x7feb195a4e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f4178150e80,32768,0,0,0,16384,16384,393216,22088765,960.0,513801.0,0.0,524288.0,1081150.0,32768.0,0,0,0,20561,131072.0,131072.0,0.0,131072.0,194428972707576,194428972726776 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f8f33d5ae80,189308,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12192,28576,8591,2892,0,41359,262510.0,0.0,47.0,262463.0,64,0x7f361ebb6e80,2200,0,0,1558656,1625,0,0,1428661,775,0,0,1198382,4987,0,0,1646295,2347,0,0,1487446,2383,0,0,1488255,5143,0,0,1755371,4941,0,0,1714648,1791,0,0,1477395,1368,0,0,1357791,867,0,0,1267605,4188,0,0,1660009,4527,0,0,1743705,2073,0,0,1476549,1795,0,0,1437860,5834,0,0,1771618,2238,0,0,1518407,1992,0,0,1501434,357,0,0,1230896,2555,0,0,1505969,1297,0,0,1387408,4429,0,0,1740819,1088,0,0,1356738,2497,0,0,1554961,2666,0,0,1570082,1905,0,0,1540741,1375,0,0,1400125,5801,0,0,1686132,4301,0,0,1695396,1378,0,0,1464804,6403,0,0,1840368,3949,0,0,1617117,64,0x7f175e00ee80,0,0,48,0,65536,65536,0,0,30524,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,41801,1734,0,48.0,248.0,0.0,262144.0,64,0x7f5e77b24e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86628.0,0.0,131112.0,0.0,64,0x7fe574ab8e80,1571814,360448,163840,0,0,180224,114688,0,71130386.0,198922639.0,76388082.0,131072.0,0.0,574386.0,0,0,25633,59310.0,0.0,0.0,59310.0,64,0x7f90004bce80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,56875.0,126786.0,64,0x7f11a7a0ee80,0.0,64,0x7f9f92604e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2817,39064,0,131478.0,131072.0,0.0,86480.0,64,0x7f7ad2b34e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131295.0,0.0,444.0,131294.0,64,0x7f5a02362e80,4096,0,0,0,4096,0,27,0,4096,0,1517,0,4096,0,0,0,4096,0,0,0,4145,0,83,0,4096,0,0,0,4096,0,40,0,4096,0,0,0,4313,0,1857,0,4096,0,0,0,4144,0,6050,0,4096,0,0,0,4096,0,0,0,4096,0,40,0,4096,0,0,0,4096,0,0,0,4096,0,189,0,4096,0,170,0,4096,0,49,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,7600,0,4096,0,0,0,4096,0,0,0,4096,0,47,0,4096,0,0,0,4098,0,4615,0,64,0x7f995aa2ce80,339560,230588,3367343,16384,24823366,0,48,0,42444,42444,3748721.0,3021150.0,6105.0,1024913.0,2098265.0,0.0,3012141.0,2700847.0,339552,240363,42444,0,42444,0,1358208.0,804988.0,0.0,0.0,64,0x7fbd89c80e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8323,4227,8323,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,64,0x7f5856196e80,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,0,41683,0,0,64,0x7fece9b6ce80,131072.0,131072.0,0.0,2593715.0,0.0,0.0,124711205.0,46829716.0,64,0x7f09c32aae80,0,3613810,2722,2722,0,3600345,2716,2716,0,3872972,2722,2722,0,3465453,2692,2692,0,4052686,2692,2692,0,3918874,2720,2720,0,3370372,2738,2738,0,3773864,2694,2694,0,4830770,2730,2730,0,3832483,2707,2707,0,3699633,2752,2752,0,3210547,2694,2694,0,3794410,2764,2764,0,3559899,2690,2690,0,3874334,2728,2728,0,3251099,2710,2710,0,3787803,2724,2724,0,4392611,2736,2736,0,3852238,2721,2721,0,3721220,2724,2724,0,3479881,2712,2712,0,3595018,2734,2734,0,3811545,2726,2726,0,3112084,2680,2680,0,3492028,2703,2703,0,3666391,2718,2718,0,3661520,2746,2746,0,3537302,2704,2704,0,3646969,2718,2718,0,3739465,2726,2726,0,3287047,2728,2728,0,3119468,2695,2695,64,0x7feb195a4e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f4178150e80,32768,0,0,0,16384,16384,393216,22223735,960.0,513847.0,0.0,524288.0,1101968.0,32768.0,0,0,0,14853,86426.0,86426.0,0.0,86426.0,194428972748536,194428972767576 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_summaries/MI200/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index a95e012907..0000000000 --- a/tests/workloads/kernel_summaries/MI200/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388043,388043,1048576,256,0,0,8,0,16,64,0x0,0x7f44da594ec0,27706,27706,16384,65536,13955,1561732,200774954022403,200787787628212,200787787648052,200774969747581 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388043,388043,1048576,256,0,0,8,0,16,64,0x0,0x7f44da594ec0,43615,43615,16384,65536,9579,1048696,200774969768270,200787787740532,200787787757172,200774970075581 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388043,388043,1048576,256,0,0,8,0,16,64,0x0,0x7f44da594ec0,41391,41391,16384,65536,9373,1048716,200774970104546,200787787778292,200787787794132,200774970287072 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index dedff7ad47..0000000000 --- a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388244,388244,1048576,256,0,0,8,0,16,64,0x0,0x7f6f6dcfcec0,0,0,0,200775440849287,200787787628212,200787787648052,200775457043843 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388244,388244,1048576,256,0,0,8,0,16,64,0x0,0x7f6f6dcfcec0,0,0,0,200775457064502,200787787740532,200787787757172,200775457366523 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388244,388244,1048576,256,0,0,8,0,16,64,0x0,0x7f6f6dcfcec0,0,0,0,200775457392963,200787787778292,200787787794132,200775457550962 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index e9dc2f421c..0000000000 --- a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388445,388445,1048576,256,0,0,8,0,16,64,0x0,0x7f873d2c8ec0,65536,174940,19568128,200775923006598,200787787628212,200787787648052,200775938896186 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388445,388445,1048576,256,0,0,8,0,16,64,0x0,0x7f873d2c8ec0,65536,230260,25754984,200775938915122,200787787740532,200787787757172,200775939338744 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388445,388445,1048576,256,0,0,8,0,16,64,0x0,0x7f873d2c8ec0,65536,231676,25918432,200775939364603,200787787778292,200787787794132,200775939527411 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index 5e45abb3dd..0000000000 --- a/tests/workloads/kernel_summaries/MI200/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388642,388642,1048576,256,0,0,8,0,16,64,0x0,0x7f12be2e4ec0,32768,285164,31937516,200776399169028,200787787628212,200787787648052,200776414972784 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388642,388642,1048576,256,0,0,8,0,16,64,0x0,0x7f12be2e4ec0,32768,594483,66577344,200776414990778,200787787740532,200787787757172,200776415312347 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388642,388642,1048576,256,0,0,8,0,16,64,0x0,0x7f12be2e4ec0,32768,575084,64410468,200776415338215,200787787778292,200787787794132,200776415496445 diff --git a/tests/workloads/kernel_summaries/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_summaries/MI200/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 8bbe3dd834..0000000000 --- a/tests/workloads/kernel_summaries/MI200/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,388843,388843,1048576,256,0,0,8,0,16,64,0x0,0x7f97cce0cec0,27576,27576,11203,220616,16384,10747459,127575,0,43502216,200776883476275,200787787628212,200787787648052,200776899925873 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,388843,388843,1048576,256,0,0,8,0,16,64,0x0,0x7f97cce0cec0,41396,41396,13324,331176,16384,19796869,227124,0,79670720,200776899952965,200787787740532,200787787757172,200776900260296 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,388843,388843,1048576,256,0,0,8,0,16,64,0x0,0x7f97cce0cec0,40594,40594,12845,324760,16384,19530583,223102,0,78594672,200776900295272,200787787778292,200787787794132,200776900472668 diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_summaries/MI200/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_summaries/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_summaries/MI200/pmc_perf.csv b/tests/workloads/kernel_summaries/MI200/pmc_perf.csv deleted file mode 100644 index d97416aabb..0000000000 --- a/tests/workloads/kernel_summaries/MI200/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_6,obj_6,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_7,obj_7,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_8,obj_8,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_11,obj_11,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_12,obj_12,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_13,obj_13,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_14,obj_14,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_15,obj_15,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_16,obj_16,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_17,obj_17,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_18,obj_18,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8cb5680ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,9941,0,815,28305,0,72771.0,131072.0,0.0,65568.0,64,0x7f4dc6f04ec0,4096,0,50,0,4096,0,0,0,4096,0,0,0,4100,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,83,0,4096,0,77,0,4096,0,91,0,4096,0,96,0,4096,0,0,0,4096,0,128,0,4096,0,7,0,4097,0,0,0,4097,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,96,0,4096,0,0,0,4096,0,0,0,4096,0,66,0,4099,0,28,0,4096,0,88,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,71,0,4096,0,0,0,4096,0,0,0,4096,0,10,0,64,0x7f12d755cec0,32768,32768,0,64,0x7fc427340ec0,1280,120072,0,0,65536,63800,56,1680,64,0x7f0ede0a8ec0,10792683,9709413,739206,344064,1634345,0,0,163840,832.0,515146.0,0.0,524288.0,283214.0,32768.0,470483,0,0,10679,131072.0,131072.0,0.0,131072.0,64,0x7fd053b44ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,952369.0,64,0x7ff1c88bcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,40067951.0,35212390.0,0.0,64,0x7f27f1d84ec0,114688,0,32768,32768,16384,16384,65536,49152,28005946.0,84730216.0,39691226.0,131072.0,0.0,231750.0,0,0,15405,326.0,131082.0,0.0,12.0,64,0x7f02bc090ec0,0,0,0,224,0,65536,64201,56,64,0x7f71fb6c4ec0,0,0,0,1062890,0,0,0,1161710,0,0,0,1005251,0,0,0,1146937,126,0,0,1173208,155,0,0,1181359,0,0,0,1083314,0,0,0,1141285,0,0,0,1024216,0,0,0,1008006,51,0,0,1068883,0,0,0,1139113,0,0,0,1143369,0,0,0,967772,0,0,0,1059054,0,0,0,1225094,0,0,0,1073672,172,0,0,1151115,0,0,0,975037,0,0,0,1106246,0,0,0,1048663,0,0,0,1127460,19,0,0,1010370,0,0,0,1042960,0,0,0,982746,209,0,0,1382108,0,0,0,972810,0,0,0,1045236,103,0,0,1319196,0,0,0,1105676,0,0,0,1105274,0,0,0,1179278,64,0x7f5c86b64ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,34601.0,46044.0,19492.0,64,0x7fe59bab8ec0,6377,0,4096,6325,0,4096,6367,0,4096,6400,0,4096,6329,0,4096,6346,0,4096,6386,0,4096,6414,0,4096,6417,0,4096,6378,0,4096,6329,0,4096,6369,0,4096,6399,0,4096,6325,0,4096,6347,0,4096,6386,0,4096,6433,0,4096,6385,0,4096,6391,0,4096,6387,0,4096,6412,0,4096,6414,0,4096,6384,0,4096,6529,0,4096,6361,0,4096,6434,0,4096,6388,0,4096,6393,0,4096,6390,0,4096,6414,0,4096,6414,0,4096,6387,0,4096,64,0x7f00e0898ec0,2223,4096,2223,6319,2278,4096,2278,6374,2268,4096,2268,6364,2300,4096,2300,6396,2227,4096,2227,6323,2267,4096,2267,6363,2303,4096,2303,6399,2311,4097,2312,6408,2309,4096,2309,6405,2225,4096,2225,6321,2278,4096,2278,6374,2270,4096,2270,6366,2296,4096,2296,6392,2229,4096,2229,6325,2269,4096,2269,6365,2298,4096,2298,6394,2251,4096,2251,6347,2291,4096,2291,6387,2279,4097,2280,6376,2278,4100,2282,6378,2280,4096,2280,6376,2317,4096,2317,6413,2299,4096,2299,6395,2424,4098,2426,6522,2254,4096,2254,6350,2305,4097,2306,6402,2291,4096,2291,6387,2287,4096,2287,6383,2281,4096,2281,6377,2281,4096,2281,6377,2315,4096,2315,6411,2303,4096,2303,6399,64,0x7f34907d8ec0,227904,126692,16384,0,16384,16384,32768,49152,28487,28487,1924642.0,1335880.0,3355.0,166343.0,1034129.0,0.0,1327872.0,1029460.0,226193,134828,28487,0,28487,0,911584.0,485326.0,0.0,0.0,64,0x7f9df37d0ec0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,0,27818,0,0,64,0x7fb93c8acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12880,19043,8143,546,0,26860,204615.0,0.0,73534.0,131081.0,64,0x7f6090dc4ec0,0,393216,163840,0,0,0,0,0,17856,0.0,0.0,0.0,32768.0,0.0,0.0,409.0,32768.0,4096,16384,352,27100,1303,0,56.0,7.0,0.0,204738.0,64,0x7f0809060ec0,0,1186912,4096,4096,0,1223532,4096,4096,0,1219258,4096,4096,0,1658359,4096,4096,0,1251900,4096,4096,0,1347923,4096,4096,0,1019107,4096,4096,0,1325625,4096,4096,0,1163495,4096,4096,0,1111185,4096,4096,0,1268906,4096,4096,0,1205246,4096,4096,0,1109719,4096,4096,0,1234891,4096,4096,0,1379125,4096,4096,0,1279839,4096,4096,0,1088528,4096,4096,0,1462495,4096,4096,0,1204649,4096,4096,0,1343330,4096,4096,0,1555603,4096,4096,0,1315112,4096,4096,0,1486839,4096,4096,0,1133925,4096,4096,0,1285809,4096,4096,0,1027697,4096,4096,0,1075842,4096,4096,0,1319145,4096,4096,0,1231380,4096,4096,0,1161654,4096,4096,0,1105658,4096,4096,0,1555341,4096,4096,64,0x7fc4fdbbcec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,200787787628212,200787787648052 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8cb5680ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,19790,0,2696,38352,0,69472.0,131072.0,0.0,45644.0,64,0x7f4dc6f04ec0,4096,0,206,0,4096,0,777,0,4096,0,102,0,4100,0,562,0,4096,0,464,0,4096,0,2656,0,4096,0,491,0,4096,0,631,0,4096,0,322,0,4097,0,44,0,4096,0,282,0,4096,0,264,0,4096,0,525,0,4096,0,503,0,4096,0,536,0,4097,0,414,0,4097,0,227,0,4096,0,1186,0,4100,0,885,0,4096,0,720,0,4096,0,0,0,4096,0,12,0,4096,0,1515,0,4096,0,324,0,4096,0,268,0,4096,0,428,0,4096,0,0,0,4096,0,1081,0,4096,0,0,0,4097,0,16,0,4096,0,1100,0,4096,0,629,0,64,0x7f12d755cec0,32768,32768,0,64,0x7fc427340ec0,0,194575,0,0,65536,63800,56,1680,64,0x7f0ede0a8ec0,19029679,18003150,682465,344064,2744016,0,0,163840,832.0,515140.0,0.0,524288.0,633468.0,32768.0,892489,0,0,13912,91218.0,91218.0,0.0,91218.0,64,0x7fd053b44ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2058821.0,64,0x7ff1c88bcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,125741030.0,60350525.0,0.0,64,0x7f27f1d84ec0,114688,0,32768,32768,16384,16384,65536,49152,58716240.0,197706597.0,48130227.0,131072.0,0.0,479796.0,0,0,23433,4016.0,131073.0,0.0,0.0,64,0x7f02bc090ec0,0,0,0,56,0,65536,65536,0,64,0x7f71fb6c4ec0,0,0,0,1384594,69,0,0,2255638,83,0,0,1702593,0,0,0,2066209,0,0,0,1653195,0,0,0,2054875,279,0,0,1781753,0,0,0,1804358,0,0,0,1454844,0,0,0,1687793,0,0,0,1875678,0,0,0,1555374,0,0,0,1574007,0,0,0,1709013,396,0,0,1978961,12,0,0,1939986,0,0,0,1505907,90,0,0,1885483,0,0,0,1666838,0,0,0,1925293,0,0,0,1920417,1335,0,0,2479208,0,0,0,1395676,0,0,0,1834744,0,0,0,1650194,0,0,0,1775081,0,0,0,1501214,27,0,0,1727673,230,0,0,2102609,0,0,0,1705891,0,0,0,1899545,0,0,0,1854229,64,0x7f5c86b64ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,93345.0,45562.0,0.0,64,0x7fe59bab8ec0,6254,0,4096,6261,0,4096,6268,0,4096,6290,0,4096,6258,0,4096,6321,0,4096,6261,0,4096,6277,0,4096,6276,0,4096,6258,0,4096,6266,0,4096,6270,0,4096,6290,0,4096,6263,0,4096,6323,0,4096,6266,0,4096,6254,0,4096,6263,0,4096,6283,0,4096,6276,0,4096,6270,0,4096,6307,0,4096,6266,0,4096,6299,0,4096,6298,0,4096,6255,0,4096,6264,0,4096,6288,0,4096,6281,0,4096,6271,0,4096,6310,0,4096,6265,0,4096,64,0x7f00e0898ec0,2155,4096,2155,6251,2146,4096,2146,6242,2177,4096,2177,6273,2172,4097,2173,6269,2181,4096,2181,6277,2174,4096,2174,6270,2180,4096,2180,6276,2178,4097,2179,6275,2178,4096,2178,6274,2155,4096,2155,6251,2146,4096,2146,6242,2182,4096,2182,6278,2175,4096,2175,6271,2184,4096,2184,6280,2174,4096,2174,6270,2183,4096,2183,6279,2206,4096,2206,6302,2197,4096,2197,6293,2176,4097,2177,6273,2160,4099,2163,6259,2180,4096,2180,6276,2196,4096,2196,6292,2157,4096,2157,6253,2127,4096,2127,6223,2130,4096,2130,6226,2258,4097,2259,6355,2198,4096,2198,6294,2178,4096,2178,6274,2161,4097,2162,6258,2180,4098,2182,6278,2199,4096,2199,6295,2157,4096,2157,6253,64,0x7f34907d8ec0,332152,222737,16384,0,16384,16384,32768,49152,41518,41518,3172936.0,2484232.0,5314.0,338169.0,1704683.0,0.0,2471654.0,2163784.0,332144,232463,41518,0,41518,0,1328576.0,771607.0,0.0,0.0,64,0x7f9df37d0ec0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,0,42176,0,0,64,0x7fb93c8acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30907,27235,9652,2476,0,39335,201008.0,0.0,69925.0,131083.0,64,0x7f6090dc4ec0,0,393216,163840,0,0,0,0,0,30057,0.0,0.0,0.0,32768.0,0.0,0.0,209.0,32768.0,4096,16384,302,41040,1954,0,56.0,12.0,0.0,200750.0,64,0x7f0809060ec0,0,3159295,2840,2840,0,4074954,2860,2860,0,3442000,2860,2860,0,4663990,2858,2858,0,3821061,2900,2900,0,4015918,2852,2852,0,2863952,2884,2884,0,3690902,2816,2816,0,3351559,2816,2816,0,3271066,2840,2840,0,3218057,2864,2864,0,3910547,2860,2860,0,3194412,2846,2846,0,3424184,2900,2900,0,4028667,2848,2848,0,4020056,2884,2884,0,3931060,2812,2812,0,3076775,2852,2852,0,3577935,2852,2852,0,3691164,2832,2832,0,4011722,2844,2844,0,3902622,2892,2892,0,4221938,2840,2840,0,4603345,2832,2832,0,4021856,2832,2832,0,3345800,2806,2806,0,4412748,2854,2854,0,3985792,2852,2852,0,3464193,2832,2832,0,3753271,2844,2844,0,3840056,2888,2888,0,3976717,2840,2840,64,0x7fc4fdbbcec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,200787787740532,200787787757172 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f8cb5680ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20724,0,2747,38187,0,69831.0,131072.0,0.0,45541.0,64,0x7f4dc6f04ec0,4096,0,311,0,4096,0,615,0,4096,0,1391,0,4100,0,43,0,4096,0,275,0,4096,0,2396,0,4096,0,16,0,4096,0,410,0,4096,0,1204,0,4097,0,230,0,4096,0,597,0,4096,0,934,0,4096,0,100,0,4096,0,357,0,4096,0,0,0,4097,0,809,0,4097,0,31,0,4096,0,449,0,4100,0,6,0,4096,0,774,0,4096,0,875,0,4096,0,255,0,4096,0,899,0,4096,0,1262,0,4096,0,323,0,4096,0,112,0,4096,0,1126,0,4096,0,26,0,4096,0,304,0,4097,0,1390,0,4096,0,232,0,4096,0,801,0,64,0x7f12d755cec0,32768,32768,0,64,0x7fc427340ec0,0,189365,0,0,65536,63800,56,1680,64,0x7f0ede0a8ec0,18947510,17743741,859705,344064,2733105,0,0,163840,832.0,515146.0,0.0,524288.0,763947.0,32768.0,915724,0,0,13414,91226.0,91226.0,0.0,91226.0,64,0x7fd053b44ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2059084.0,64,0x7ff1c88bcec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,121626219.0,58024359.0,0.0,64,0x7f27f1d84ec0,114688,0,32768,32768,16384,16384,65536,49152,58310809.0,202035406.0,51471400.0,131072.0,0.0,463313.0,0,0,24953,7663.0,131082.0,0.0,18.0,64,0x7f02bc090ec0,0,0,0,56,0,65536,65536,0,64,0x7f71fb6c4ec0,580,0,0,2384547,573,0,0,2076195,0,0,0,1707563,257,0,0,2027051,0,0,0,1778158,175,0,0,2022828,129,0,0,1861580,0,0,0,1651189,76,0,0,1688029,0,0,0,1818496,766,0,0,2405585,227,0,0,1964580,125,0,0,1555538,0,0,0,1940908,194,0,0,1980412,0,0,0,1704595,0,0,0,1626585,0,0,0,1753379,583,0,0,2180781,123,0,0,1770314,0,0,0,1794918,191,0,0,2197482,0,0,0,1513569,0,0,0,1936410,0,0,0,1748736,277,0,0,1856561,0,0,0,1361974,568,0,0,2334526,1027,0,0,2735105,0,0,0,1756245,0,0,0,1697920,0,0,0,2054955,64,0x7f5c86b64ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,89139.0,45580.0,0.0,64,0x7fe59bab8ec0,6285,0,4096,6280,0,4096,6270,0,4096,6284,0,4096,6260,0,4096,6268,0,4096,6292,0,4096,6318,0,4096,6326,0,4096,6288,0,4096,6285,0,4096,6275,0,4096,6291,0,4096,6268,0,4096,6271,0,4096,6290,0,4096,6293,0,4096,6329,0,4096,6279,0,4096,6305,0,4096,6270,0,4096,6301,0,4096,6313,0,4096,6258,0,4096,6263,0,4096,6297,0,4096,6334,0,4096,6284,0,4096,6306,0,4096,6271,0,4096,6305,0,4096,6313,0,4096,64,0x7f00e0898ec0,2158,4096,2158,6254,2170,4096,2170,6266,2158,4096,2158,6254,2157,4097,2158,6254,2176,4096,2176,6272,2182,4096,2182,6278,2170,4096,2170,6266,2152,4097,2153,6249,2154,4096,2154,6250,2157,4096,2157,6253,2173,4096,2173,6269,2158,4096,2158,6254,2162,4096,2162,6258,2185,4096,2185,6281,2180,4096,2180,6276,2163,4096,2163,6259,2150,4096,2150,6246,2174,4096,2174,6270,2158,4097,2159,6255,2154,4100,2158,6254,2168,4096,2168,6264,2173,4096,2173,6269,2174,4096,2174,6270,2157,4096,2157,6253,2165,4096,2165,6261,2206,4097,2207,6303,2177,4096,2177,6273,2158,4096,2158,6254,2158,4097,2159,6255,2167,4098,2169,6265,2172,4096,2172,6268,2181,4096,2181,6277,64,0x7f34907d8ec0,333192,218989,16384,0,16384,16384,32768,49152,41648,41648,3124107.0,2462013.0,4550.0,384500.0,1781440.0,0.0,2450479.0,2141151.0,333184,228267,41648,0,41648,0,1332736.0,776559.0,0.0,0.0,64,0x7f9df37d0ec0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,0,41435,0,0,64,0x7fb93c8acec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30738,27293,9514,2578,0,39521,200737.0,0.0,69654.0,131083.0,64,0x7f6090dc4ec0,0,393216,163840,0,0,0,0,0,30390,0.0,0.0,0.0,32768.0,0.0,0.0,242.0,32768.0,4096,16384,302,41321,1977,0,56.0,11.0,0.0,200900.0,64,0x7f0809060ec0,0,3296459,2832,2832,0,3372524,2860,2860,0,4222254,2848,2848,0,3878328,2856,2856,0,3774522,2880,2880,0,3831094,2844,2844,0,3260405,2876,2876,0,4057262,2830,2830,0,4273330,2836,2836,0,2725887,2832,2832,0,3234063,2860,2860,0,3333475,2852,2852,0,3604070,2852,2852,0,3326805,2876,2876,0,3142407,2840,2840,0,3714948,2876,2876,0,2930790,2804,2804,0,3635042,2868,2868,0,3668097,2840,2840,0,5045459,2848,2848,0,4655237,2812,2812,0,3073880,2868,2868,0,2615458,2808,2808,0,4182335,2816,2816,0,3381199,2816,2816,0,3942930,2810,2810,0,4447030,2868,2868,0,4492459,2842,2842,0,3600791,2852,2852,0,3522880,2808,2808,0,3130714,2868,2868,0,4177317,2808,2808,64,0x7fc4fdbbcec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,200787787778292,200787787794132 diff --git a/tests/workloads/kernel_summaries/MI200/roofline.csv b/tests/workloads/kernel_summaries/MI200/roofline.csv deleted file mode 100644 index e69de29bb2..0000000000 diff --git a/tests/workloads/kernel_summaries/MI200/sysinfo.csv b/tests/workloads/kernel_summaries/MI200/sysinfo.csv deleted file mode 100644 index 6b1421bb87..0000000000 --- a/tests/workloads/kernel_summaries/MI200/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_summaries,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:57:22 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_0/MI100/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 48b3eb80b7..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,193490,193490,1048576,256,0,0,8,8,16,64,0x0,0x7fb2f1f4ae80,48621,48621,16384,65536,14647,1866684,194341379773374,194353571654480,194353571678800,194341387566400 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,193490,193490,1048576,256,0,0,8,8,16,64,0x0,0x7fb2f1f4ae80,43436,43436,16384,65536,8195,1048580,194341387591237,194353571699280,194353571718320,194341387859034 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,193490,193490,1048576,256,0,0,8,8,16,64,0x0,0x7fb2f1f4ae80,42100,42100,16384,65536,8187,1048596,194341387891245,194353571787600,194353571806320,194341388042942 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 8f20936a8a..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,193674,193674,1048576,256,0,0,8,8,16,64,0x0,0x7fae69f00e80,0,0,0,194341874444885,194353571654480,194353571678800,194341883176307 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,193674,193674,1048576,256,0,0,8,8,16,64,0x0,0x7fae69f00e80,0,0,0,194341883193961,194353571699280,194353571718320,194341883612814 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,193674,193674,1048576,256,0,0,8,8,16,64,0x0,0x7fae69f00e80,0,0,0,194341883642380,194353571787600,194353571806320,194341883808895 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_0/MI100/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 732ae2294b..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,194231,194231,1048576,256,0,0,8,8,16,64,0x0,0x7fef30a7ce80,48338,48338,16316,386712,16384,26132632,237677,0,105025452,194343342503857,194353571654480,194353571678800,194343350941192 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,194231,194231,1048576,256,0,0,8,8,16,64,0x0,0x7fef30a7ce80,42449,42449,13321,339600,16384,24522860,230609,0,98588116,194343350972872,194353571699280,194353571718320,194343351286887 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,194231,194231,1048576,256,0,0,8,8,16,64,0x0,0x7fef30a7ce80,42737,42737,13550,341904,16384,25012620,230778,0,100534524,194343351324829,194353571787600,194353571806320,194343351496614 diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index 202141726e..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6f289aa046..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_10.txt deleted file mode 100644 index a00555d953..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_11.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_12.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_13.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_14.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_15.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_16.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 2180ee3f63..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_3.txt deleted file mode 100644 index 8f1ba90d04..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_4.txt deleted file mode 100644 index 9a82481329..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_5.txt deleted file mode 100644 index bbc1f21123..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_6.txt deleted file mode 100644 index b6368182b4..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_7.txt deleted file mode 100644 index 3f7673fd23..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_8.txt deleted file mode 100644 index facba6bd95..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_9.txt deleted file mode 100644 index d458645ea4..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_0/MI100/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_0/MI100/pmc_perf.csv deleted file mode 100644 index 7f60854eda..0000000000 --- a/tests/workloads/kernel_verbose_0/MI100/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_1,obj_1,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_2,obj_2,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_4,obj_4,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_6,obj_6,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_7,obj_7,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_11,obj_11,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_14,obj_14,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_15,obj_15,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_16,obj_16,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fd385a04e80,2006833,360448,163840,0,0,180224,114688,0,68715404.0,172990277.0,68125891.0,131072.0,0.0,625896.0,0,0,26767,113863.0,0.0,0.0,113863.0,64,0x7f9e98b4ae80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb7a9a86e80,194132,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13587,29971,9968,550,0,46178,262586.0,0.0,188.0,262398.0,64,0x7f6a2f3ece80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8313,4264,8360,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3713cfce80,32768,0,0,0,16384,16384,393216,23243666,960.0,513920.0,0.0,524288.0,905506.0,32768.0,0,0,0,16088,131072.0,131072.0,0.0,131072.0,64,0x7f0c1e818e80,0,0,192,0,65536,64467,48,1381,31324,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,47160,1670,0,48.0,263.0,0.0,262288.0,64,0x7f3250ba2e80,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,0,48631,0,0,64,0x7fed10890e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47696,0,131584.0,131072.0,0.0,131104.0,64,0x7f5553c0ce80,0.0,64,0x7f16ce836e80,387368,239224,3490962,16384,25872794,144,48,0,48420,48420,3941246.0,3118196.0,5739.0,953182.0,2123489.0,0.0,3109146.0,2800453.0,385655,249166,48420,0,48420,0,1549440.0,993517.0,0.0,0.0,64,0x7fb3e5fa0e80,4096,0,4462,0,4096,0,409,0,4099,0,4376,0,4096,0,226,0,4096,0,3731,0,4096,0,1797,0,4096,0,2805,0,4096,0,1669,0,4096,0,1739,0,4096,0,4257,0,4096,0,3622,0,4310,0,3660,0,4096,0,109,0,4096,0,1494,0,4096,0,5047,0,4144,0,3070,0,4096,0,1670,0,4096,0,1445,0,4096,0,4884,0,4096,0,2740,0,4096,0,1035,0,4096,0,3302,0,4096,0,3960,0,4096,0,529,0,4096,0,3569,0,4096,0,1691,0,4096,0,3186,0,4096,0,1192,0,4096,0,119,0,4097,0,533,0,4096,0,1668,0,4096,0,3003,0,64,0x7f209d1cee80,683,0,0,1681084,5739,0,0,2192455,1326,0,0,1749948,4875,0,0,2106330,3977,0,0,1986884,2440,0,0,1876324,1614,0,0,1814035,824,0,0,1861178,2548,0,0,1798354,2070,0,0,1845346,2259,0,0,1856629,1037,0,0,1660772,3060,0,0,1931718,2301,0,0,1793728,2724,0,0,1943004,6640,0,0,2198193,3152,0,0,1888080,1849,0,0,1811706,2712,0,0,1981406,5295,0,0,2037812,2893,0,0,1929244,2281,0,0,1948298,3962,0,0,2025022,4303,0,0,2065531,4729,0,0,2047026,1984,0,0,1835190,551,0,0,1645298,6476,0,0,2171387,3957,0,0,2033716,2261,0,0,1891349,4993,0,0,2156620,4404,0,0,1972354,64,0x7fe28285ce80,0,3730368,4096,4096,0,3655095,4096,4096,0,3163009,4096,4096,0,3948395,4096,4096,0,3286143,4096,4096,0,5034301,4096,4096,0,3571898,4096,4096,0,4076582,4096,4096,0,4932830,4096,4096,0,3783152,4096,4096,0,4546871,4096,4096,0,3752739,4096,4096,0,3223245,4096,4096,0,4381348,4096,4096,0,3702046,4096,4096,0,4420403,4096,4096,0,3786309,4096,4096,0,4054829,4096,4096,0,3082527,4096,4096,0,3126263,4096,4096,0,4153912,4096,4096,0,3204802,4096,4096,0,4239022,4096,4096,0,2843960,4096,4096,0,3922575,4096,4096,0,3560485,4096,4096,0,3311424,4096,4096,0,3735645,4096,4096,0,3893362,4096,4096,0,4405362,4096,4096,0,3139392,4096,4096,0,4193590,4096,4096,64,0x7f5352440e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86386.0,44686.0,131111.0,0.0,64,0x7f8185804e80,131072.0,131072.0,0.0,2336661.0,0.0,0.0,137127129.0,60488149.0,64,0x7f750354ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,64647.0,130388.0,64,0x7fcd8cecee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131376.0,0.0,600.0,131375.0,194353571654480,194353571678800 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fd385a04e80,1346773,360448,163840,0,0,180224,114688,0,72054641.0,203418176.0,74077908.0,131072.0,0.0,657109.0,0,0,26308,64781.0,0.0,0.0,64781.0,64,0x7f9e98b4ae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb7a9a86e80,190604,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14139,30523,8420,2397,0,40405,262426.0,0.0,47.0,262379.0,64,0x7f6a2f3ece80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8232,4136,8232,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8314,4265,8361,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3713cfce80,32768,0,0,0,16384,16384,393216,23247664,960.0,513946.0,0.0,524288.0,1013134.0,32768.0,0,0,0,14099,86383.0,86383.0,0.0,86383.0,64,0x7f0c1e818e80,0,0,48,0,65536,65536,0,0,30401,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42131,1751,0,48.0,245.0,0.0,262144.0,64,0x7f3250ba2e80,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,0,43087,0,0,64,0x7fed10890e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5707,47024,1080,131866.0,131072.0,0.0,115949.0,64,0x7f5553c0ce80,0.0,64,0x7f16ce836e80,345248,229414,3369784,16384,24865119,0,48,0,43155,43155,3731153.0,3088880.0,5937.0,907196.0,2054685.0,0.0,3079687.0,2770511.0,345240,238889,43155,0,43155,0,1380960.0,821879.0,0.0,0.0,64,0x7fb3e5fa0e80,4096,0,906,0,4096,0,744,0,4096,0,2991,0,4096,0,2057,0,4096,0,1432,0,4096,0,6560,0,4096,0,1091,0,4096,0,4975,0,4096,0,34,0,4096,0,1294,0,4096,0,306,0,4270,0,3078,0,4096,0,764,0,4096,0,19,0,4096,0,361,0,4144,0,145,0,4096,0,1995,0,4096,0,2156,0,4096,0,1427,0,4096,0,1794,0,4097,0,0,0,4096,0,1099,0,4096,0,750,0,4096,0,28,0,4096,0,2330,0,4096,0,2719,0,4096,0,608,0,4097,0,719,0,4096,0,213,0,4100,0,7519,0,4096,0,2179,0,4096,0,2965,0,64,0x7f209d1cee80,2149,0,0,1529798,4769,0,0,1775466,809,0,0,1293469,3323,0,0,1581991,1355,0,0,1437536,2507,0,0,1525460,955,0,0,1290002,2763,0,0,1544569,1542,0,0,1383729,2377,0,0,1558005,3026,0,0,1626699,1429,0,0,1451597,2715,0,0,1567633,3543,0,0,1679118,1966,0,0,1480065,4848,0,0,1755619,1319,0,0,1440911,1117,0,0,1365875,1677,0,0,1476115,2531,0,0,1475491,3166,0,0,1515185,1306,0,0,1414787,2218,0,0,1556401,6554,0,0,1857795,1715,0,0,1476033,3349,0,0,1698064,1038,0,0,1358600,5224,0,0,1739257,1471,0,0,1421995,5136,0,0,1753385,1510,0,0,1449180,1596,0,0,1382884,64,0x7fe28285ce80,0,4425069,2700,2700,0,4036778,2708,2708,0,4504980,2680,2680,0,3666830,2712,2712,0,3306629,2684,2684,0,2736295,2678,2678,0,5116273,2704,2704,0,3165010,2706,2706,0,2787842,2711,2711,0,4286214,2685,2685,0,3722374,2714,2714,0,5103837,2741,2741,0,3026756,2708,2708,0,3022760,2680,2680,0,4737002,2692,2692,0,2928740,2704,2704,0,3401400,2686,2686,0,3970324,2688,2688,0,3395899,2704,2704,0,5058727,2714,2714,0,3203562,2703,2703,0,4337607,2749,2749,0,4320317,2680,2680,0,3082350,2692,2692,0,2932808,2676,2676,0,4111799,2706,2706,0,4412749,2730,2730,0,4819919,2718,2718,0,3413705,2706,2706,0,3689644,2691,2691,0,4642279,2704,2704,0,4839472,2710,2710,64,0x7f5352440e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86484.0,0.0,131112.0,0.0,64,0x7f8185804e80,131072.0,131072.0,0.0,2680005.0,0.0,0.0,105353275.0,37782076.0,64,0x7f750354ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,71485.0,140507.0,64,0x7fcd8cecee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131451.0,0.0,756.0,131450.0,194353571699280,194353571718320 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7fd385a04e80,1436338,360448,163840,0,0,180224,114688,0,69699642.0,187307657.0,69545746.0,131072.0,0.0,665131.0,0,0,25460,50890.0,0.0,0.0,50890.0,64,0x7f9e98b4ae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb7a9a86e80,193254,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11286,27670,8593,2405,0,41864,262459.0,0.0,47.0,262412.0,64,0x7f6a2f3ece80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8198,4102,8198,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8314,4265,8361,0,8192,4096,8192,0,8192,4096,8192,64,0x7f3713cfce80,32768,0,0,0,16384,16384,393216,22808406,960.0,513845.0,0.0,524288.0,1058785.0,32768.0,0,0,0,13916,86647.0,86647.0,0.0,86647.0,64,0x7f0c1e818e80,0,0,48,0,65536,65536,0,0,31544,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42897,1726,0,48.0,276.0,0.0,262144.0,64,0x7f3250ba2e80,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,0,42151,0,0,64,0x7fed10890e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2896,40667,0,131461.0,131072.0,0.0,86668.0,64,0x7f5553c0ce80,0.0,64,0x7f16ce836e80,343696,227035,3332340,16384,24268612,0,48,0,42961,42961,3695291.0,3049265.0,5055.0,919004.0,2067958.0,0.0,3040489.0,2731456.0,343688,236801,42961,0,42961,0,1374752.0,809016.0,0.0,0.0,64,0x7fb3e5fa0e80,4096,0,2920,0,4096,0,153,0,4096,0,2717,0,4096,0,1261,0,4096,0,6504,0,4096,0,4404,0,4096,0,2970,0,4096,0,325,0,4096,0,3404,0,4096,0,1411,0,4096,0,4443,0,4323,0,2573,0,4096,0,572,0,4096,0,1241,0,4096,0,4975,0,4144,0,244,0,4096,0,3326,0,4096,0,2453,0,4096,0,4944,0,4096,0,2365,0,4097,0,637,0,4096,0,699,0,4096,0,1917,0,4096,0,3516,0,4096,0,308,0,4096,0,1241,0,4096,0,4157,0,4097,0,2653,0,4096,0,88,0,4100,0,272,0,4096,0,1774,0,4096,0,0,0,64,0x7f209d1cee80,1105,0,0,1389999,2196,0,0,1478769,1978,0,0,1420854,3005,0,0,1572715,1708,0,0,1429400,1416,0,0,1389753,1490,0,0,1395001,2225,0,0,1499468,1655,0,0,1445943,2945,0,0,1591288,3047,0,0,1561401,930,0,0,1394091,4036,0,0,1744397,5554,0,0,1702932,1961,0,0,1442125,3798,0,0,1623435,5558,0,0,1760973,1059,0,0,1432582,3124,0,0,1584883,1381,0,0,1379178,2362,0,0,1515193,1650,0,0,1507077,3266,0,0,1561604,2699,0,0,1523282,1951,0,0,1468214,2466,0,0,1507468,2150,0,0,1474605,3618,0,0,1624888,2796,0,0,1576234,3507,0,0,1590909,5663,0,0,1810246,1636,0,0,1461062,64,0x7fe28285ce80,0,3578293,2712,2712,0,4907688,2728,2728,0,3596146,2685,2685,0,4201515,2702,2702,0,3951803,2660,2660,0,4265151,2714,2714,0,4503718,2699,2699,0,5018693,2692,2692,0,3935995,2716,2716,0,4686136,2683,2683,0,4362814,2700,2700,0,4666937,2710,2710,0,5053364,2706,2706,0,3697139,2696,2696,0,3992805,2698,2698,0,4189689,2684,2684,0,3711908,2667,2667,0,5088538,2702,2702,0,4014027,2696,2696,0,4757445,2702,2702,0,3557373,2691,2691,0,3491927,2739,2739,0,3533736,2694,2694,0,3713251,2690,2690,0,3517338,2668,2668,0,3889139,2692,2692,0,4315516,2730,2730,0,3731959,2694,2694,0,3050714,2690,2690,0,3954401,2705,2705,0,3036695,2698,2698,0,4778210,2693,2693,64,0x7f5352440e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86496.0,0.0,131112.0,0.0,64,0x7f8185804e80,131072.0,131072.0,0.0,2408704.0,0.0,0.0,130898481.0,47722039.0,64,0x7f750354ae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,75460.0,143313.0,64,0x7fcd8cecee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131370.0,0.0,594.0,131369.0,194353571787600,194353571806320 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_0/MI200/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 1305a9cec1..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,358385,358385,1048576,256,0,0,8,0,16,64,0x0,0x7f4c05fb0ec0,27667,27667,16384,65536,13532,1531332,199948894773455,199961732754864,199961732775184,199948910717487 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,358385,358385,1048576,256,0,0,8,0,16,64,0x0,0x7f4c05fb0ec0,40465,40465,16384,65536,9379,1048736,199948910739288,199961732860464,199961732876784,199948911142290 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,358385,358385,1048576,256,0,0,8,0,16,64,0x0,0x7f4c05fb0ec0,41265,41265,16384,65536,8936,1048696,199948911163951,199961732897264,199961732913104,199948911336488 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index edb7528078..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,358986,358986,1048576,256,0,0,8,0,16,64,0x0,0x7fdb72218ec0,32768,298276,33407688,199950343316353,199961732754864,199961732775184,199950359262619 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,358986,358986,1048576,256,0,0,8,0,16,64,0x0,0x7fdb72218ec0,32768,596987,66845280,199950359277127,199961732860464,199961732876784,199950359582544 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,358986,358986,1048576,256,0,0,8,0,16,64,0x0,0x7fdb72218ec0,32768,597482,66917436,199950359609075,199961732897264,199961732913104,199950359763046 diff --git a/tests/workloads/kernel_verbose_0/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_0/MI200/SQ_LEVEL_WAVES.csv deleted file mode 100644 index b8641b7245..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,359171,359171,1048576,256,0,0,8,0,16,64,0x0,0x7f5d6a584ec0,28053,28053,11278,224432,16384,11062997,129980,0,44746892,199950845453276,199961732754864,199961732775184,199950861414300 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,359171,359171,1048576,256,0,0,8,0,16,64,0x0,0x7f5d6a584ec0,40430,40430,12754,323448,16384,19776698,224617,0,79579868,199950861440600,199961732860464,199961732876784,199950861744164 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,359171,359171,1048576,256,0,0,8,0,16,64,0x0,0x7f5d6a584ec0,40804,40804,12443,326440,16384,19963790,227939,0,80332968,199950861779430,199961732897264,199961732913104,199950861943731 diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_0.txt deleted file mode 100644 index 4ffdc32149..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6c277f4a37..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_10.txt deleted file mode 100644 index 7053d4dce6..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_11.txt deleted file mode 100644 index 77ae8b461f..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_12.txt deleted file mode 100644 index dfb2cf65e5..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_13.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_14.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_15.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_16.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_17.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_17.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_18.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_18.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_2.txt deleted file mode 100644 index 70b69f8928..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_3.txt deleted file mode 100644 index e47f8e33c9..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_4.txt deleted file mode 100644 index 2d96f365a9..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_5.txt deleted file mode 100644 index e50beed390..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_6.txt deleted file mode 100644 index 15a2277c1b..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_7.txt deleted file mode 100644 index b42ce91618..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_8.txt deleted file mode 100644 index 21d4c7a998..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_9.txt deleted file mode 100644 index 9ffe5778c3..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_0/MI200/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_0/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_0/MI200/pmc_perf.csv deleted file mode 100644 index 4a4a70b1d3..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_1,obj_1,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_2,obj_2,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_5,obj_5,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_6,obj_6,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_7,obj_7,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_12,obj_12,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_13,obj_13,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_14,obj_14,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_15,obj_15,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_16,obj_16,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_17,obj_17,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_18,obj_18,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f8012a88ec0,114688,0,32768,32768,16384,16384,65536,49152,27615177.0,87807843.0,40484884.0,131072.0,0.0,196518.0,0,0,14809,38.0,131083.0,0.0,14.0,64,0x7f7fece10ec0,2262,4096,2262,6358,2310,4096,2310,6406,2254,4096,2254,6350,2299,4096,2299,6395,2305,4097,2306,6402,2306,4099,2309,6405,2309,4096,2309,6405,2281,4096,2281,6377,2285,4096,2285,6381,2262,4096,2262,6358,2309,4096,2309,6405,2254,4096,2254,6350,2300,4096,2300,6396,2251,4096,2251,6347,2307,4096,2307,6403,2311,4096,2311,6407,2267,4096,2267,6363,2310,4096,2310,6406,2249,4097,2250,6346,2295,4096,2295,6391,2262,4096,2262,6358,2297,4096,2297,6393,2291,4096,2291,6387,2444,4099,2447,6543,2277,4096,2277,6373,2268,4096,2268,6364,2306,4096,2306,6402,2253,4096,2253,6349,2291,4096,2291,6387,2262,4096,2262,6358,2303,4096,2303,6399,2298,4096,2298,6394,64,0x7f8e70438ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10643,0,814,27527,0,73464.0,131072.0,0.0,65568.0,64,0x7ff35030cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11416,18608,8076,549,0,26136,204284.0,0.0,73203.0,131081.0,64,0x7f98f7dd4ec0,1293,115127,0,0,65536,63800,56,1680,64,0x7f3382d3cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fb474a04ec0,0,393216,163840,0,0,0,0,0,18528,0.0,0.0,0.0,32768.0,0.0,0.0,397.0,32768.0,4096,16384,352,29010,1938,0,56.0,6.0,0.0,204757.0,64,0x7f90a9bbcec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,120,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f65ed360ec0,229488,128849,16384,0,16384,16384,32768,49152,28685,28685,1952618.0,1308857.0,3414.0,129435.0,1034941.0,0.0,1300622.0,1002465.0,227777,136980,28685,0,28685,0,917920.0,491095.0,0.0,0.0,64,0x7fc8d388cec0,32768,32768,0,64,0x7f7bd52a0ec0,0,0,0,224,0,65536,64183,56,64,0x7fe95a08cec0,0,0,0,1032925,0,0,0,1116636,0,0,0,1077888,15,0,0,1249287,0,0,0,1057034,64,0,0,1230430,59,0,0,1083685,61,0,0,1216586,16,0,0,1069244,0,0,0,1121576,0,0,0,1008544,0,0,0,1130056,0,0,0,1095521,49,0,0,1156927,0,0,0,1083565,0,0,0,1205235,0,0,0,1056906,6,0,0,1093588,0,0,0,1049037,0,0,0,1147696,24,0,0,1121366,0,0,0,1128214,9,0,0,1194933,0,0,0,1146147,0,0,0,1041055,106,0,0,1175478,0,0,0,1106738,0,0,0,1189854,10,0,0,1089377,184,0,0,1141140,0,0,0,1096664,0,0,0,1173028,64,0x7f8da5ce4ec0,6363,0,4096,6401,0,4096,6373,0,4096,6424,0,4096,6354,0,4096,6419,0,4096,6338,0,4096,6371,0,4096,6370,0,4096,6362,0,4096,6402,0,4096,6374,0,4096,6425,0,4096,6356,0,4096,6424,0,4096,6338,0,4096,6372,0,4096,6341,0,4096,6354,0,4096,6383,0,4096,6385,0,4096,6367,0,4096,6387,0,4096,6531,0,4096,6365,0,4096,6371,0,4096,6339,0,4096,6355,0,4096,6383,0,4096,6385,0,4096,6369,0,4096,6387,0,4096,64,0x7fe9c17d0ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39045272.0,34791701.0,0.0,64,0x7fa461318ec0,0,1144758,4096,4096,0,1198859,4096,4096,0,1169355,4096,4096,0,1417969,4096,4096,0,1295789,4096,4096,0,1447915,4096,4096,0,1212133,4096,4096,0,1489792,4096,4096,0,1400337,4096,4096,0,1222110,4096,4096,0,1177960,4096,4096,0,1421251,4096,4096,0,1041792,4096,4096,0,1200010,4096,4096,0,1236139,4096,4096,0,1269052,4096,4096,0,1192839,4096,4096,0,1276429,4096,4096,0,1036663,4096,4096,0,1279176,4096,4096,0,1196150,4096,4096,0,1186095,4096,4096,0,1392935,4096,4096,0,1159360,4096,4096,0,1243849,4096,4096,0,1181254,4096,4096,0,1180725,4096,4096,0,1203109,4096,4096,0,1343890,4096,4096,0,1018493,4096,4096,0,1152072,4096,4096,0,1517163,4096,4096,64,0x7f4286e30ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131078.0,34051.0,46157.0,19379.0,64,0x7f2ad94fcec0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,0,27724,0,0,64,0x7f8a94e90ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,983917.0,64,0x7fe3d4124ec0,11180534,9957449,879021,344064,1678545,0,0,163840,832.0,515136.0,0.0,524288.0,333998.0,32768.0,503855,0,0,11694,131072.0,131072.0,0.0,131072.0,199961732754864,199961732775184 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f8012a88ec0,114688,0,32768,32768,16384,16384,65536,49152,59635919.0,204377227.0,52566171.0,131072.0,0.0,421089.0,0,0,23370,3887.0,131073.0,0.0,0.0,64,0x7f7fece10ec0,2188,4096,2188,6284,2174,4096,2174,6270,2176,4099,2179,6275,2136,4096,2136,6232,2225,4097,2226,6322,2204,4098,2206,6302,2142,4096,2142,6238,2177,4096,2177,6273,2181,4096,2181,6277,2185,4096,2185,6281,2174,4096,2174,6270,2177,4096,2177,6273,2140,4096,2140,6236,2167,4096,2167,6263,2212,4096,2212,6308,2148,4096,2148,6244,2158,4096,2158,6254,2165,4096,2165,6261,2169,4097,2170,6266,2156,4096,2156,6252,2164,4096,2164,6260,2126,4096,2126,6222,2188,4096,2188,6284,2198,4097,2199,6295,2202,4096,2202,6298,2162,4096,2162,6258,2166,4096,2166,6262,2174,4097,2175,6271,2159,4096,2159,6255,2164,4096,2164,6260,2127,4096,2127,6223,2192,4096,2192,6288,64,0x7f8e70438ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,15930,0,819,36570,0,69577.0,131072.0,0.0,45480.0,64,0x7ff35030cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32570,28382,9568,2425,0,38970,200878.0,0.0,69795.0,131083.0,64,0x7f98f7dd4ec0,0,188622,0,0,65536,63800,56,1680,64,0x7f3382d3cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fb474a04ec0,0,393216,163840,0,0,0,0,0,30838,0.0,0.0,0.0,32768.0,0.0,0.0,202.0,32768.0,4096,16384,302,41968,2083,0,56.0,11.0,0.0,200840.0,64,0x7f90a9bbcec0,4096,0,529,0,4096,0,19,0,4096,0,1248,0,4096,0,790,0,4096,0,264,0,4096,0,461,0,4096,0,758,0,4096,0,733,0,4096,0,530,0,4096,0,290,0,4097,0,179,0,4099,0,1111,0,4096,0,494,0,4096,0,423,0,4096,0,584,0,4096,0,744,0,4096,0,14,0,4097,0,234,0,4097,0,47,0,4096,0,729,0,4096,0,644,0,4096,0,615,0,4096,0,360,0,4096,0,859,0,4096,0,2255,0,4097,0,265,0,4096,0,216,0,4096,0,25,0,4097,0,22,0,4098,0,293,0,4096,0,785,0,4096,0,2172,0,64,0x7f65ed360ec0,328344,221036,16384,0,16384,16384,32768,49152,41042,41042,3150055.0,2415775.0,4039.0,278343.0,1633554.0,0.0,2403693.0,2095396.0,328336,230159,41042,0,41042,0,1313344.0,778018.0,0.0,0.0,64,0x7fc8d388cec0,32768,32768,0,64,0x7f7bd52a0ec0,0,0,0,56,0,65536,65536,0,64,0x7fe95a08cec0,787,0,0,2133833,553,0,0,2069105,262,0,0,1852036,307,0,0,1953299,1010,0,0,2438948,1550,0,0,2234417,0,0,0,1692453,181,0,0,1899948,105,0,0,1933065,625,0,0,1988865,257,0,0,1629841,292,0,0,1721025,268,0,0,1726583,816,0,0,1928842,754,0,0,2100554,84,0,0,1894588,36,0,0,1589513,84,0,0,1577650,586,0,0,1806706,1386,0,0,2120762,316,0,0,2136687,418,0,0,2011421,1311,0,0,2146658,572,0,0,2040442,216,0,0,1927918,578,0,0,1802792,155,0,0,2078166,1263,0,0,1796692,764,0,0,1726683,282,0,0,1708020,446,0,0,2000506,1001,0,0,1927813,64,0x7f8da5ce4ec0,6284,0,4096,6279,0,4096,6273,0,4096,6257,0,4096,6263,0,4096,6292,0,4096,6298,0,4096,6280,0,4096,6284,0,4096,6281,0,4096,6284,0,4096,6278,0,4096,6256,0,4096,6262,0,4096,6293,0,4096,6296,0,4096,6303,0,4096,6282,0,4096,6282,0,4096,6260,0,4096,6291,0,4096,6272,0,4096,6256,0,4096,6259,0,4096,6262,0,4096,6303,0,4096,6287,0,4096,6288,0,4096,6261,0,4096,6293,0,4096,6273,0,4096,6260,0,4096,64,0x7fe9c17d0ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,117684210.0,60329209.0,0.0,64,0x7fa461318ec0,0,3178627,2832,2832,0,3739317,2872,2872,0,3441328,2860,2860,0,4901048,2848,2848,0,4023958,2892,2892,0,3722092,2840,2840,0,2962120,2872,2872,0,4583360,2832,2832,0,3103569,2836,2836,0,4358587,2824,2824,0,3624303,2872,2872,0,3147139,2856,2856,0,3851139,2848,2848,0,3651378,2894,2894,0,4128605,2840,2840,0,3375854,2864,2864,0,3725421,2820,2820,0,4082832,2856,2856,0,3796158,2848,2848,0,3407282,2844,2844,0,4215144,2848,2848,0,3900469,2868,2868,0,3493863,2828,2828,0,3897504,2824,2824,0,3428842,2828,2828,0,3416021,2820,2820,0,3973811,2860,2860,0,3639781,2848,2848,0,4238154,2848,2848,0,3746299,2848,2848,0,3582366,2864,2864,0,4382424,2830,2830,64,0x7f4286e30ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,107751.0,45571.0,0.0,64,0x7f2ad94fcec0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,0,40721,0,0,64,0x7f8a94e90ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2074694.0,64,0x7fe3d4124ec0,19929676,18414865,1170747,344064,2869779,0,0,163840,832.0,515150.0,0.0,524288.0,678901.0,32768.0,1079587,0,0,13692,90874.0,90874.0,0.0,90874.0,199961732860464,199961732876784 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f8012a88ec0,114688,0,32768,32768,16384,16384,65536,49152,57632606.0,194401316.0,47256923.0,131072.0,0.0,495511.0,0,0,25157,6922.0,131084.0,0.0,22.0,64,0x7f7fece10ec0,2170,4096,2170,6266,2196,4096,2196,6292,2177,4099,2180,6276,2172,4096,2172,6268,2254,4097,2255,6351,2198,4099,2201,6297,2153,4096,2153,6249,2174,4096,2174,6270,2170,4096,2170,6266,2174,4096,2174,6270,2200,4096,2200,6296,2177,4096,2177,6273,2176,4096,2176,6272,2202,4096,2202,6298,2198,4096,2198,6294,2156,4096,2156,6252,2173,4096,2173,6269,2167,4096,2167,6263,2158,4097,2159,6255,2154,4096,2154,6250,2181,4096,2181,6277,2165,4096,2165,6261,2175,4096,2175,6271,2194,4097,2195,6291,2189,4096,2189,6285,2173,4096,2173,6269,2174,4096,2174,6270,2159,4097,2160,6256,2157,4096,2157,6253,2183,4096,2183,6279,2166,4096,2166,6262,2177,4096,2177,6273,64,0x7f8e70438ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,23205,0,2664,39565,0,69837.0,131072.0,0.0,45573.0,64,0x7ff35030cec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30520,26936,9680,2389,0,38821,200332.0,0.0,69250.0,131082.0,64,0x7f98f7dd4ec0,0,188959,0,0,65536,63800,56,1680,64,0x7f3382d3cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fb474a04ec0,0,393216,163840,0,0,0,0,0,30062,0.0,0.0,0.0,32768.0,0.0,0.0,197.0,32768.0,4096,16384,302,41498,2031,0,56.0,10.0,0.0,200301.0,64,0x7f90a9bbcec0,4096,0,388,0,4096,0,28,0,4096,0,740,0,4096,0,187,0,4096,0,0,0,4096,0,278,0,4096,0,311,0,4096,0,42,0,4096,0,56,0,4096,0,936,0,4098,0,1,0,4099,0,636,0,4096,0,131,0,4096,0,1277,0,4096,0,381,0,4096,0,3,0,4096,0,107,0,4097,0,478,0,4097,0,148,0,4096,0,1099,0,4096,0,858,0,4096,0,505,0,4096,0,368,0,4096,0,2281,0,4096,0,82,0,4097,0,1,0,4096,0,1,0,4096,0,151,0,4097,0,247,0,4098,0,335,0,4096,0,498,0,4096,0,0,0,64,0x7f65ed360ec0,323336,216717,16384,0,16384,16384,32768,49152,40416,40416,3093355.0,2372241.0,3631.0,304293.0,1757267.0,0.0,2360052.0,2051749.0,323328,225731,40416,0,40416,0,1293312.0,766992.0,0.0,0.0,64,0x7fc8d388cec0,32768,32768,0,64,0x7f7bd52a0ec0,0,0,0,56,0,65536,65536,0,64,0x7fe95a08cec0,731,0,0,1945323,1560,0,0,2438847,133,0,0,2120827,3498,0,0,2635765,0,0,0,1936784,1748,0,0,2566494,314,0,0,1787260,59,0,0,2046095,0,0,0,1820194,281,0,0,1771976,27,0,0,1753515,0,0,0,1844134,1028,0,0,2331648,818,0,0,2104644,1005,0,0,2078374,668,0,0,2133213,34,0,0,1942244,138,0,0,1944518,249,0,0,1986452,1513,0,0,2296875,1265,0,0,2302691,1025,0,0,2475075,2049,0,0,2565441,212,0,0,2260746,803,0,0,2335438,0,0,0,1711706,649,0,0,2031873,1070,0,0,2115952,1283,0,0,2029529,1407,0,0,2134321,473,0,0,2089453,800,0,0,2150600,64,0x7f8da5ce4ec0,6285,0,4096,6273,0,4096,6243,0,4096,6275,0,4096,6283,0,4096,6251,0,4096,6270,0,4096,6314,0,4096,6309,0,4096,6289,0,4096,6275,0,4096,6242,0,4096,6277,0,4096,6283,0,4096,6256,0,4096,6275,0,4096,6319,0,4096,6318,0,4096,6276,0,4096,6283,0,4096,6261,0,4096,6281,0,4096,6283,0,4096,6259,0,4096,6262,0,4096,6326,0,4096,6317,0,4096,6276,0,4096,6283,0,4096,6264,0,4096,6279,0,4096,6284,0,4096,64,0x7fe9c17d0ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120659866.0,59415420.0,0.0,64,0x7fa461318ec0,0,3248042,2840,2840,0,4491416,2876,2876,0,3529715,2852,2852,0,3365992,2872,2872,0,4157333,2872,2872,0,4344622,2828,2828,0,3326338,2860,2860,0,4526060,2824,2824,0,4197751,2824,2824,0,3396200,2840,2840,0,3667208,2876,2876,0,3541353,2852,2852,0,2942008,2868,2868,0,3693904,2882,2882,0,3878014,2828,2828,0,3703272,2860,2860,0,4026373,2800,2800,0,4312805,2844,2844,0,3339296,2872,2872,0,4300410,2864,2864,0,3773833,2840,2840,0,3680806,2880,2880,0,3721011,2820,2820,0,4519666,2812,2812,0,3389306,2808,2808,0,4268449,2796,2796,0,4590185,2848,2848,0,3665564,2876,2876,0,3600059,2868,2868,0,3340209,2844,2844,0,2859877,2876,2876,0,4227424,2824,2824,64,0x7f4286e30ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,90911.0,45585.0,0.0,64,0x7f2ad94fcec0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,0,40816,0,0,64,0x7f8a94e90ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2093024.0,64,0x7fe3d4124ec0,19352365,18025139,983162,344064,2774252,0,0,163840,832.0,515136.0,0.0,524288.0,725062.0,32768.0,999100,0,0,13869,91032.0,91032.0,0.0,91032.0,199961732897264,199961732913104 diff --git a/tests/workloads/kernel_verbose_0/MI200/roofline.csv b/tests/workloads/kernel_verbose_0/MI200/roofline.csv deleted file mode 100644 index f4cc3e612c..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/roofline.csv +++ /dev/null @@ -1,5 +0,0 @@ -device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.5713,1387.9775,1389.165,5015.2139,5012.1392,5018.2886,9224.082,9223.3262,9224.8379,18052.5,18051.562,18053.438,20937.758,20877.43,20998.086,20264.014,20263.346,20264.682,170404.42,170401.03,170407.81,164866.61,164862.56,164870.66,41418.559,41418.07,41419.047,41474.844,41474.246,41475.441,166332.06,165839.12,166825 -1,1389.4777,1388.9285,1390.0269,5028.5171,5026.5938,5030.4404,9235.2178,9234.4756,9235.96,18097.75,18092.523,18102.977,20976.178,20909.389,21042.967,20293.092,20292.469,20293.715,170832.12,170828.16,170836.09,165102.62,165099.02,165106.23,41483.664,41483.043,41484.285,41542.723,41541.859,41543.586,166911.92,166908.61,166915.23 -2,1389.0422,1388.4388,1389.6456,5034.1714,5031.7939,5036.5488,9256.9932,9256.2656,9257.7207,18100.01,18099.045,18100.975,21039.893,21039.441,21040.344,20342.699,20342.092,20343.307,171059.3,171055.52,171063.08,165431.02,165426.25,165435.78,41559.031,41558.309,41559.754,41618.191,41617.215,41619.168,166881.56,166290.81,167472.31 -3,1388.8164,1388.1942,1389.4386,5033.0767,5031.8364,5034.3169,9240.877,9240.2109,9241.543,18023.621,18020.01,18027.232,21032.256,21031.824,21032.688,20313.984,20313.314,20314.654,171042.12,171037.98,171046.27,165238.38,165233.67,165243.08,41444.531,41290.031,41599.031,41588.297,41587.699,41588.895,167035.66,167033.28,167038.03 diff --git a/tests/workloads/kernel_verbose_0/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_0/MI200/sysinfo.csv deleted file mode 100644 index 5fbbbd2a6a..0000000000 --- a/tests/workloads/kernel_verbose_0/MI200/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_0,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:43:35 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 701edf9ff4..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,197832,197832,1048576,256,0,0,8,8,16,64,0x0,0x7fe221dcce80,47387,47387,16384,65536,14667,1878708,194355159737813,194367370722111,194367370746271,194355167424447 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,197832,197832,1048576,256,0,0,8,8,16,64,0x0,0x7fe221dcce80,43050,43050,16384,65536,8225,1048584,194355167445587,194367370933951,194367370952671,194355167769981 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,197832,197832,1048576,256,0,0,8,8,16,64,0x0,0x7fe221dcce80,42530,42530,16384,65536,8263,1048580,194355167801541,194367370974911,194367370993791,194355167976562 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 6521ebdfb3..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,198017,198017,1048576,256,0,0,8,8,16,64,0x0,0x7f27260e2e80,0,0,0,194355644721069,194367370722111,194367370746271,194355652895216 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,198017,198017,1048576,256,0,0,8,8,16,64,0x0,0x7f27260e2e80,0,0,0,194355652913661,194367370933951,194367370952671,194355653353063 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,198017,198017,1048576,256,0,0,8,8,16,64,0x0,0x7f27260e2e80,0,0,0,194355653382178,194367370974911,194367370993791,194355653572268 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index b18aea553b..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,198204,198204,1048576,256,0,0,8,8,16,64,0x0,0x7f60d7434e80,65536,167008,21396328,194356143449181,194367370722111,194367370746271,194356151035335 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,198204,198204,1048576,256,0,0,8,8,16,64,0x0,0x7f60d7434e80,65536,167780,21442488,194356151053830,194367370933951,194367370952671,194356151409473 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,198204,198204,1048576,256,0,0,8,8,16,64,0x0,0x7f60d7434e80,65536,167906,21472200,194356151438879,194367370974911,194367370993791,194356151626464 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index 84a1dec816..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,198390,198390,1048576,256,0,0,8,8,16,64,0x0,0x7f4338698e80,32768,658286,84234268,194356645433769,194367370722111,194367370746271,194356653334939 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,198390,198390,1048576,256,0,0,8,8,16,64,0x0,0x7f4338698e80,32768,673258,86177260,194356653355528,194367370933951,194367370952671,194356653661497 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,198390,198390,1048576,256,0,0,8,8,16,64,0x0,0x7f4338698e80,32768,688731,88155632,194356653689400,194367370974911,194367370993791,194356653860985 diff --git a/tests/workloads/kernel_verbose_1/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_1/MI100/SQ_LEVEL_WAVES.csv deleted file mode 100644 index ed76dacbe9..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,198575,198575,1048576,256,0,0,8,8,16,64,0x0,0x7f12a29a0e80,48960,48960,17780,391688,16384,25009693,239385,0,100519984,194357137744279,194367370722111,194367370746271,194357145390777 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,198575,198575,1048576,256,0,0,8,8,16,64,0x0,0x7f12a29a0e80,42895,42895,13804,343168,16384,24582159,231597,0,98810844,194357145421986,194367370933951,194367370952671,194357145708218 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,198575,198575,1048576,256,0,0,8,8,16,64,0x0,0x7f12a29a0e80,42679,42679,14357,341440,16384,24332023,228433,0,97816732,194357145746270,194367370974911,194367370993791,194357145934717 diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index 202141726e..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6f289aa046..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_10.txt deleted file mode 100644 index a00555d953..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_11.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_12.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_13.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_14.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_15.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_16.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 2180ee3f63..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_3.txt deleted file mode 100644 index 8f1ba90d04..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_4.txt deleted file mode 100644 index 9a82481329..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_5.txt deleted file mode 100644 index bbc1f21123..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_6.txt deleted file mode 100644 index b6368182b4..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_7.txt deleted file mode 100644 index 3f7673fd23..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_8.txt deleted file mode 100644 index facba6bd95..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_9.txt deleted file mode 100644 index d458645ea4..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_1/MI100/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_1/MI100/pmc_dispatch_info.csv deleted file mode 100644 index 17300ae9af..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/pmc_dispatch_info.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_verbose_1/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_1/MI100/pmc_perf.csv deleted file mode 100644 index 77b20a63ca..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_2,obj_2,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_3,obj_3,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_4,obj_4,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_5,obj_5,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_8,obj_8,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_9,obj_9,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_10,obj_10,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_11,obj_11,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_15,obj_15,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_16,obj_16,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7413ddce80,0.0,64,0x7f04b75cce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86375.0,44697.0,131111.0,0.0,64,0x7f456805ce80,0,4192108,4096,4096,0,3817704,4096,4096,0,4759466,4096,4096,0,4107810,4096,4096,0,4790901,4096,4096,0,3195663,4096,4096,0,4439894,4096,4096,0,3392732,4096,4096,0,4218702,4096,4096,0,3296409,4096,4096,0,4509910,4096,4096,0,4058330,4096,4096,0,3380081,4096,4096,0,3311906,4096,4096,0,4910040,4096,4096,0,5162718,4096,4096,0,4789162,4096,4096,0,5164560,4096,4096,0,4770121,4096,4096,0,4754320,4096,4096,0,4026595,4096,4096,0,3446956,4096,4096,0,4606073,4096,4096,0,2978295,4096,4096,0,4365011,4096,4096,0,3293260,4096,4096,0,4472168,4096,4096,0,2455749,4096,4096,0,4345395,4096,4096,0,2915389,4096,4096,0,4204587,4096,4096,0,4056589,4096,4096,64,0x7f64d8c44e80,2263271,360448,163840,0,0,180224,114688,0,69526984.0,194355108.0,76807015.0,131072.0,0.0,596818.0,0,0,26073,76677.0,0.0,0.0,76677.0,64,0x7f79ddbace80,32768,0,0,0,16384,16384,393216,22869483,960.0,513946.0,0.0,524288.0,911169.0,32768.0,0,0,0,17344,131072.0,131072.0,0.0,131072.0,64,0x7f358e54ee80,0,0,192,0,65536,64522,48,1351,32220,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,539,48268,1668,0,48.0,303.0,0.0,262288.0,64,0x7fda121dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47706,0,131488.0,131072.0,0.0,131104.0,64,0x7f8aa888ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,52045.0,127706.0,64,0x7fc4e07dce80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fd199caee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131318.0,0.0,484.0,131317.0,64,0x7f1d50fa2e80,4096,0,1673,0,4097,0,21,0,4099,0,1012,0,4096,0,1493,0,4096,0,174,0,4096,0,777,0,4096,0,2456,0,4096,0,6414,0,4096,0,3136,0,4096,0,95,0,4144,0,3210,0,4096,0,204,0,4096,0,219,0,4096,0,995,0,4096,0,2513,0,4096,0,205,0,4144,0,544,0,4096,0,397,0,4096,0,2663,0,4096,0,299,0,4096,0,501,0,4096,0,241,0,4096,0,1098,0,4096,0,101,0,4096,0,1030,0,4096,0,430,0,4096,0,74,0,4096,0,106,0,4096,0,69,0,4096,0,53,0,4265,0,2772,0,4096,0,3479,0,64,0x7f23ec544e80,131072.0,131072.0,0.0,2540068.0,0.0,0.0,126437381.0,61078005.0,64,0x7f785810ae80,1764,0,0,1895876,1569,0,0,1804049,1362,0,0,1829121,1900,0,0,1752756,2775,0,0,1964520,842,0,0,1575968,1863,0,0,1774296,1077,0,0,1660955,679,0,0,1588916,1304,0,0,1791103,4201,0,0,2117997,404,0,0,1520859,999,0,0,1709730,866,0,0,1613585,931,0,0,1680020,5637,0,0,2179901,3462,0,0,2031318,582,0,0,1625413,1568,0,0,1741736,371,0,0,1575750,1970,0,0,1744447,835,0,0,1670421,1850,0,0,1873930,902,0,0,1551335,692,0,0,1659834,619,0,0,1510890,2123,0,0,1815210,1486,0,0,1674237,916,0,0,1604129,1135,0,0,1680935,2334,0,0,1953579,680,0,0,1567243,64,0x7fd731586e80,186379,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14010,30394,9854,550,0,47013,262624.0,0.0,188.0,262436.0,64,0x7f3a59806e80,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,0,48735,0,0,64,0x7fb08e9c8e80,0,8192,4096,8192,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8315,4219,8315,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fbbb9930e80,384168,233587,3418191,16384,25170789,144,48,0,48020,48020,3856166.0,3031473.0,6288.0,877839.0,2052891.0,0.0,3022741.0,2712888.0,382847,243520,48020,0,48020,0,1536640.0,969767.0,0.0,0.0,194367370722111,194367370746271 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7413ddce80,0.0,64,0x7f04b75cce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,85883.0,43666.0,129642.0,0.0,64,0x7f456805ce80,0,4216950,2692,2692,0,4206195,2724,2724,0,3588452,2684,2684,0,3845148,2716,2716,0,4168997,2696,2696,0,3352134,2718,2718,0,4371773,2736,2736,0,5281250,2708,2708,0,3459629,2699,2699,0,3820986,2673,2673,0,4141290,2718,2718,0,4881147,2724,2724,0,5037167,2702,2702,0,3102761,2685,2685,0,5181847,2714,2714,0,3285064,2704,2704,0,3833234,2676,2676,0,4253007,2706,2706,0,4152958,2708,2708,0,4995761,2708,2708,0,4401476,2696,2696,0,3819813,2730,2730,0,4286935,2720,2720,0,3787683,2688,2688,0,3397335,2666,2666,0,3873191,2682,2682,0,3142739,2752,2752,0,4554698,2696,2696,0,3945155,2704,2704,0,3818305,2706,2706,0,4285789,2716,2716,0,3694683,2705,2705,64,0x7f64d8c44e80,2101626,360448,163840,0,0,180224,114688,0,69886382.0,200025255.0,79222327.0,131072.0,0.0,592328.0,0,0,25822,68552.0,0.0,0.0,68552.0,64,0x7f79ddbace80,32768,0,0,0,16384,16384,393216,22318518,0.0,524288.0,0.0,524288.0,774010.0,32768.0,0,0,0,12098,86514.0,86514.0,0.0,86514.0,64,0x7f358e54ee80,0,0,48,0,65536,65536,0,0,30395,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,481,45124,3914,0,48.0,294.0,0.0,262144.0,64,0x7fda121dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2792,39547,0,131359.0,131072.0,0.0,86688.0,64,0x7f8aa888ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,27849.0,111017.0,64,0x7fc4e07dce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fd199caee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131378.0,0.0,610.0,131377.0,64,0x7f1d50fa2e80,4096,0,3731,0,4097,0,2282,0,4096,0,1624,0,4096,0,1348,0,4096,0,1918,0,4096,0,2408,0,4096,0,811,0,4096,0,4156,0,4096,0,373,0,4096,0,978,0,4144,0,1371,0,4096,0,2643,0,4096,0,6733,0,4096,0,442,0,4096,0,1751,0,4096,0,425,0,4144,0,5050,0,4096,0,5406,0,4096,0,559,0,4096,0,346,0,4097,0,819,0,4096,0,3904,0,4096,0,642,0,4099,0,131,0,4096,0,666,0,4096,0,1059,0,4096,0,161,0,4097,0,4238,0,4096,0,447,0,4096,0,252,0,4263,0,1769,0,4096,0,363,0,64,0x7f23ec544e80,131072.0,131072.0,0.0,2685982.0,0.0,0.0,118623100.0,48409523.0,64,0x7f785810ae80,2773,0,0,1497824,3187,0,0,1588319,4089,0,0,1710491,3475,0,0,1650544,1968,0,0,1419914,2031,0,0,1463899,1673,0,0,1456764,3489,0,0,1682358,1154,0,0,1331657,1421,0,0,1391184,1119,0,0,1453064,1556,0,0,1467704,1324,0,0,1365971,2780,0,0,1555220,915,0,0,1350863,6037,0,0,1795936,2640,0,0,1481325,483,0,0,1255589,1145,0,0,1347347,2195,0,0,1555327,1418,0,0,1415848,3584,0,0,1629478,2265,0,0,1576474,4100,0,0,1703274,3017,0,0,1569810,872,0,0,1328952,1207,0,0,1360828,4425,0,0,1664706,2120,0,0,1414380,4190,0,0,1688824,2335,0,0,1483704,1956,0,0,1503244,64,0x7fd731586e80,184762,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13305,29689,8566,2357,0,41715,262483.0,0.0,47.0,262436.0,64,0x7f3a59806e80,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,0,43704,0,0,64,0x7fb08e9c8e80,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8317,4221,8317,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fbbb9930e80,351848,243417,3516962,16384,25880136,0,48,0,43980,43980,3940726.0,3170074.0,5255.0,1208458.0,2347503.0,0.0,3159784.0,2847676.0,351840,252679,43980,0,43980,0,1407360.0,855829.0,0.0,0.0,194367370933951,194367370952671 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f7413ddce80,0.0,64,0x7f04b75cce80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86753.0,0.0,131112.0,0.0,64,0x7f456805ce80,0,2451006,2682,2682,0,3387605,2738,2738,0,3548623,2662,2662,0,5319404,2720,2720,0,3217638,2636,2636,0,3168710,2760,2760,0,3421453,2712,2712,0,5429104,2732,2732,0,3881526,2674,2674,0,3120021,2695,2695,0,3343738,2710,2710,0,3570785,2746,2746,0,2901259,2680,2680,0,3543947,2715,2715,0,3756849,2704,2704,0,3430709,2704,2704,0,3193338,2666,2666,0,4440514,2724,2724,0,3381381,2684,2684,0,3653592,2719,2719,0,3610677,2703,2703,0,3645702,2785,2785,0,2610785,2698,2698,0,2329664,2680,2680,0,2726438,2656,2656,0,3630648,2748,2748,0,2851579,2732,2732,0,2992685,2700,2700,0,2694386,2668,2668,0,3347992,2720,2720,0,4324088,2734,2734,0,4465578,2690,2690,64,0x7f64d8c44e80,1992543,360448,163840,0,0,180224,114688,0,68926929.0,192250366.0,78109110.0,131072.0,0.0,570329.0,0,0,25394,51597.0,0.0,0.0,51597.0,64,0x7f79ddbace80,32768,0,0,0,16384,16384,393216,22662855,960.0,513954.0,0.0,524288.0,984036.0,32768.0,0,0,0,15337,86466.0,86466.0,0.0,86466.0,64,0x7f358e54ee80,0,0,48,0,65536,65536,0,0,30776,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42053,1700,0,48.0,312.0,0.0,262144.0,64,0x7fda121dce80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2771,39262,0,131356.0,131072.0,0.0,86473.0,64,0x7f8aa888ee80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,70894.0,139631.0,64,0x7fc4e07dce80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fd199caee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131331.0,0.0,516.0,131330.0,64,0x7f1d50fa2e80,4096,0,1101,0,4097,0,3653,0,4096,0,1121,0,4096,0,727,0,4096,0,91,0,4096,0,4912,0,4096,0,3204,0,4096,0,1781,0,4096,0,2125,0,4096,0,0,0,4144,0,3678,0,4096,0,5951,0,4096,0,3209,0,4096,0,614,0,4096,0,6105,0,4096,0,215,0,4144,0,561,0,4096,0,1575,0,4096,0,2240,0,4096,0,685,0,4097,0,1941,0,4096,0,0,0,4096,0,5466,0,4099,0,1263,0,4096,0,5330,0,4096,0,1033,0,4096,0,1242,0,4097,0,922,0,4096,0,1359,0,4096,0,0,0,4249,0,2522,0,4096,0,1290,0,64,0x7f23ec544e80,131072.0,131072.0,0.0,2556858.0,0.0,0.0,121470381.0,48575777.0,64,0x7f785810ae80,1595,0,0,1374521,4687,0,0,1738220,1796,0,0,1388251,1881,0,0,1408386,1600,0,0,1411979,2396,0,0,1572015,721,0,0,1266501,1397,0,0,1423876,636,0,0,1312876,3380,0,0,1679604,379,0,0,1366359,1193,0,0,1404105,434,0,0,1272968,804,0,0,1339086,311,0,0,1246690,5414,0,0,1840197,1559,0,0,1340295,1210,0,0,1372430,1359,0,0,1406959,1159,0,0,1402329,770,0,0,1289463,4008,0,0,1663495,800,0,0,1320403,3753,0,0,1674779,1296,0,0,1366792,1433,0,0,1487244,355,0,0,1189678,3686,0,0,1645120,612,0,0,1240993,1469,0,0,1494455,555,0,0,1275442,2954,0,0,1541587,64,0x7fd731586e80,103057,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13054,29438,8438,2816,0,41461,262572.0,0.0,47.0,262525.0,64,0x7f3a59806e80,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,0,42323,0,0,64,0x7fb08e9c8e80,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8312,4216,8312,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8317,4221,8317,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fbbb9930e80,339352,230354,3340348,16384,24150798,0,48,0,42418,42418,3744972.0,3060409.0,5587.0,1010398.0,2102076.0,0.0,3050755.0,2740530.0,339344,239875,42418,0,42418,0,1357376.0,817781.0,0.0,0.0,194367370974911,194367370993791 diff --git a/tests/workloads/kernel_verbose_1/MI100/timestamps.csv b/tests/workloads/kernel_verbose_1/MI100/timestamps.csv deleted file mode 100644 index 3e6798f8fe..0000000000 --- a/tests/workloads/kernel_verbose_1/MI100/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,201908,201908,1048576,256,0,0,8,8,16,64,0x0,0x7f0fe9074e80,194367370695532,194367370722111,194367370746271,194367370760986 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,201908,201908,1048576,256,0,0,8,8,16,64,0x0,0x7f0fe9074e80,194367370758892,194367370933951,194367370952671,194367370953881 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,201908,201908,1048576,256,0,0,8,8,16,64,0x0,0x7f0fe9074e80,194367370964872,194367370974911,194367370993791,194367370994929 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index bd6503d226..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,363460,363460,1048576,256,0,0,8,0,16,64,0x0,0x7ff22c994ec0,27703,27703,16384,65536,13404,1537372,200055078848242,200067979162338,200067979182178,200055094559183 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,363460,363460,1048576,256,0,0,8,0,16,64,0x0,0x7ff22c994ec0,40119,40119,16384,65536,9550,1048624,200055094579321,200067979273538,200067979290178,200055094882795 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,363460,363460,1048576,256,0,0,8,0,16,64,0x0,0x7ff22c994ec0,42479,42479,16384,65536,9234,1048768,200055094912260,200067979310018,200067979325698,200055095070179 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 6be79d2404..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,363661,363661,1048576,256,0,0,8,0,16,64,0x0,0x7f3124730ec0,0,0,0,200055561500194,200067979162338,200067979182178,200055577369855 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,363661,363661,1048576,256,0,0,8,0,16,64,0x0,0x7f3124730ec0,0,0,0,200055577387589,200067979273538,200067979290178,200055577688568 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,363661,363661,1048576,256,0,0,8,0,16,64,0x0,0x7f3124730ec0,0,0,0,200055577714908,200067979310018,200067979325698,200055577867657 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index 260b14abf4..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,363848,363848,1048576,256,0,0,8,0,16,64,0x0,0x7f2fbd3c8ec0,65536,169366,19139736,200056043039793,200067979162338,200067979182178,200056058877453 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,363848,363848,1048576,256,0,0,8,0,16,64,0x0,0x7f2fbd3c8ec0,65536,225964,25370840,200056058896139,200067979273538,200067979290178,200056059202949 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,363848,363848,1048576,256,0,0,8,0,16,64,0x0,0x7f2fbd3c8ec0,65536,292244,32717160,200056059229198,200067979310018,200067979325698,200056059383340 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index d1d30cf4f2..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,364036,364036,1048576,256,0,0,8,0,16,64,0x0,0x7f9afaf64ec0,32768,296309,33183028,200056531297830,200067979162338,200067979182178,200056547311183 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,364036,364036,1048576,256,0,0,8,0,16,64,0x0,0x7f9afaf64ec0,32768,573512,64241388,200056547331662,200067979273538,200067979290178,200056547590842 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,364036,364036,1048576,256,0,0,8,0,16,64,0x0,0x7f9afaf64ec0,32768,580962,65069524,200056547616591,200067979310018,200067979325698,200056547773858 diff --git a/tests/workloads/kernel_verbose_1/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_1/MI200/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 37bc72388c..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,364221,364221,1048576,256,0,0,8,0,16,64,0x0,0x7fcf1d938ec0,28004,28004,11221,224040,16384,10685818,128439,0,43260548,200057011816670,200067979162338,200067979182178,200057027542399 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,364221,364221,1048576,256,0,0,8,0,16,64,0x0,0x7fcf1d938ec0,40208,40208,12845,321672,16384,18938324,218514,0,76234636,200057027570592,200067979273538,200067979290178,200057027850292 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,364221,364221,1048576,256,0,0,8,0,16,64,0x0,0x7fcf1d938ec0,40263,40263,12057,322112,16384,19286850,220562,0,77628096,200057027885588,200067979310018,200067979325698,200057028049158 diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_0.txt deleted file mode 100644 index 4ffdc32149..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6c277f4a37..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_10.txt deleted file mode 100644 index 7053d4dce6..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_11.txt deleted file mode 100644 index 77ae8b461f..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_12.txt deleted file mode 100644 index dfb2cf65e5..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_13.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_14.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_15.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_16.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_17.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_17.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_18.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_18.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_2.txt deleted file mode 100644 index 70b69f8928..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_3.txt deleted file mode 100644 index e47f8e33c9..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_4.txt deleted file mode 100644 index 2d96f365a9..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_5.txt deleted file mode 100644 index e50beed390..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_6.txt deleted file mode 100644 index 15a2277c1b..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_7.txt deleted file mode 100644 index b42ce91618..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_8.txt deleted file mode 100644 index 21d4c7a998..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_9.txt deleted file mode 100644 index 9ffe5778c3..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_1/MI200/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_1/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_1/MI200/pmc_perf.csv deleted file mode 100644 index 170881be1a..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_3,obj_3,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_6,obj_6,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_7,obj_7,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_8,obj_8,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_9,obj_9,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_10,obj_10,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_11,obj_11,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_12,obj_12,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_13,obj_13,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_14,obj_14,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_15,obj_15,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_16,obj_16,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_17,obj_17,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_18,obj_18,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f30d60ec0,0,393216,163840,0,0,0,0,0,17747,0.0,0.0,0.0,32768.0,0.0,0.0,421.0,32768.0,4096,16384,352,28468,2266,0,56.0,7.0,0.0,204466.0,64,0x7fb5e5294ec0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,0,27664,0,0,64,0x7f32c606cec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,1027000.0,64,0x7f095d840ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10201,0,816,27563,0,73358.0,131072.0,0.0,65568.0,64,0x7f18088e4ec0,2261,4096,2261,6357,2290,4096,2290,6386,2316,4096,2316,6412,2293,4096,2293,6389,2230,4096,2230,6326,2271,4096,2271,6367,2282,4096,2282,6378,2310,4096,2310,6406,2311,4100,2315,6411,2264,4096,2264,6360,2288,4096,2288,6384,2318,4096,2318,6414,2292,4096,2292,6388,2232,4098,2234,6330,2270,4096,2270,6366,2286,4096,2286,6382,2291,4096,2291,6387,2270,4096,2270,6366,2368,4098,2370,6466,2313,4096,2313,6409,2275,4096,2275,6371,2280,4096,2280,6376,2287,4096,2287,6383,2447,4098,2449,6545,2279,4096,2279,6375,2290,4096,2290,6386,2269,4096,2269,6365,2316,4097,2317,6413,2315,4096,2315,6411,2279,4096,2279,6375,2280,4096,2280,6376,2290,4096,2290,6386,64,0x7f4fb5fd8ec0,0,0,0,224,0,65536,64182,56,64,0x7f42a6b3cec0,114688,0,32768,32768,16384,16384,65536,49152,27649860.0,87502975.0,39274438.0,131072.0,0.0,215108.0,0,0,14754,521.0,131081.0,0.0,10.0,64,0x7fb6d6754ec0,234048,132225,16384,0,16384,16384,32768,49152,29255,29255,1996337.0,1334650.0,3387.0,170996.0,1046881.0,0.0,1326318.0,1027943.0,232337,140340,29255,0,29255,0,936160.0,486100.0,0.0,0.0,64,0x7f4ccb2e8ec0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,301,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,100,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f707852cec0,0,1168245,4096,4096,0,1374737,4096,4096,0,1374113,4096,4096,0,1251333,4096,4096,0,1323182,4096,4096,0,1480557,4096,4096,0,1282383,4096,4096,0,1503021,4096,4096,0,1367890,4096,4096,0,1185330,4096,4096,0,1031338,4096,4096,0,1287324,4096,4096,0,1101961,4096,4096,0,1542256,4096,4096,0,1135142,4096,4096,0,1105766,4096,4096,0,1224038,4096,4096,0,1191336,4096,4096,0,1105875,4096,4096,0,1421596,4096,4096,0,1220864,4096,4096,0,1345222,4096,4096,0,1238044,4096,4096,0,1282389,4096,4096,0,1629687,4096,4096,0,1132579,4096,4096,0,1275299,4096,4096,0,1039849,4096,4096,0,1123301,4096,4096,0,1173075,4096,4096,0,1143817,4096,4096,0,1262905,4096,4096,64,0x7f8bc7a80ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fb5d5860ec0,32768,32768,0,64,0x7fa6a5348ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12040,19189,8199,547,0,26241,204509.0,0.0,73429.0,131080.0,64,0x7fcd72e38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131078.0,34952.0,46045.0,19491.0,64,0x7f12b11a8ec0,1315,116949,0,0,65536,63800,56,1680,64,0x7f16ec274ec0,11246562,9885575,1016923,344064,1685778,0,0,163840,832.0,515146.0,0.0,524288.0,313367.0,32768.0,532433,0,0,11249,131072.0,131072.0,0.0,131072.0,64,0x7f0fa95e8ec0,0,0,0,960793,0,0,0,1046335,0,0,0,1007179,0,0,0,1069013,11,0,0,1185365,131,0,0,1263233,0,0,0,1121946,0,0,0,1081571,0,0,0,1011187,0,0,0,1006260,0,0,0,1027593,0,0,0,1072598,0,0,0,1003114,0,0,0,1118865,95,0,0,1169897,111,0,0,1270909,0,0,0,1077659,0,0,0,1062317,0,0,0,1038773,437,0,0,1336872,0,0,0,1051285,0,0,0,1086019,0,0,0,1116459,0,0,0,1184759,0,0,0,1107126,0,0,0,1091346,0,0,0,1054377,0,0,0,1115638,65,0,0,1174159,0,0,0,1063579,0,0,0,1010761,0,0,0,1238908,64,0x7fb3dee04ec0,6360,0,4096,6398,0,4096,6407,0,4096,6397,0,4096,6344,0,4096,6385,0,4096,6341,0,4096,6375,0,4096,6380,0,4096,6364,0,4096,6398,0,4096,6409,0,4096,6399,0,4096,6341,0,4096,6389,0,4096,6345,0,4096,6363,0,4096,6412,0,4096,6384,0,4096,6375,0,4096,6364,0,4096,6372,0,4096,6385,0,4096,6531,0,4096,6363,0,4096,6359,0,4096,6419,0,4096,6387,0,4096,6379,0,4096,6364,0,4096,6374,0,4096,6388,0,4096,64,0x7f8ab4290ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41246558.0,35325626.0,0.0,200067979162338,200067979182178 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f30d60ec0,0,393216,163840,0,0,0,0,0,28486,0.0,0.0,0.0,32768.0,0.0,0.0,220.0,32768.0,4096,16384,302,37723,1950,0,56.0,2.0,0.0,200260.0,64,0x7fb5e5294ec0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,0,40783,0,0,64,0x7f32c606cec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2106996.0,64,0x7f095d840ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,18950,0,2726,38120,0,69389.0,131072.0,0.0,45663.0,64,0x7f18088e4ec0,2212,4096,2212,6308,2218,4096,2218,6314,2159,4096,2159,6255,2202,4096,2202,6298,2204,4096,2204,6300,2202,4097,2203,6299,2170,4096,2170,6266,2196,4096,2196,6292,2191,4098,2193,6289,2218,4099,2221,6317,2221,4096,2221,6317,2159,4096,2159,6255,2206,4096,2206,6302,2201,4097,2202,6298,2204,4096,2204,6300,2171,4096,2171,6267,2163,4096,2163,6259,2185,4096,2185,6281,2209,4099,2212,6308,2200,4096,2200,6296,2186,4096,2186,6282,2228,4096,2228,6324,2163,4096,2163,6259,2193,4096,2193,6289,2195,4096,2195,6291,2163,4096,2163,6259,2184,4096,2184,6280,2155,4097,2156,6252,2203,4096,2203,6299,2187,4096,2187,6283,2230,4096,2230,6326,2165,4096,2165,6261,64,0x7f4fb5fd8ec0,0,0,0,56,0,65536,65536,0,64,0x7f42a6b3cec0,114688,0,32768,32768,16384,16384,65536,49152,57390856.0,203960685.0,49843780.0,131072.0,0.0,431717.0,0,0,22700,4524.0,131075.0,0.0,4.0,64,0x7fb6d6754ec0,331432,223438,16384,0,16384,16384,32768,49152,41428,41428,3181987.0,2495637.0,4300.0,423158.0,1692058.0,0.0,2485217.0,2178896.0,331424,232703,41428,0,41428,0,1325696.0,781224.0,0.0,0.0,64,0x7f4ccb2e8ec0,4096,0,1653,0,4096,0,459,0,4097,0,912,0,4096,0,125,0,4096,0,573,0,4097,0,390,0,4096,0,448,0,4096,0,300,0,4096,0,31,0,4099,0,257,0,4096,0,159,0,4096,0,189,0,4096,0,336,0,4096,0,56,0,4096,0,166,0,4096,0,224,0,4096,0,9,0,4096,0,135,0,4097,0,520,0,4096,0,1802,0,4096,0,276,0,4096,0,1464,0,4096,0,823,0,4096,0,1003,0,4096,0,527,0,4096,0,36,0,4096,0,13,0,4098,0,287,0,4096,0,200,0,4096,0,10,0,4096,0,1289,0,4096,0,797,0,64,0x7f707852cec0,0,3622600,2804,2804,0,3628991,2854,2854,0,4031469,2846,2846,0,3480464,2854,2854,0,3057363,2876,2876,0,4283274,2832,2832,0,3048608,2868,2868,0,3743924,2828,2828,0,2992924,2828,2828,0,3222388,2808,2808,0,3243665,2852,2852,0,3245835,2840,2840,0,4202768,2852,2852,0,3406709,2872,2872,0,3907380,2832,2832,0,3164228,2868,2868,0,4223629,2816,2816,0,3747189,2860,2860,0,3804412,2818,2818,0,3605594,2804,2804,0,4814152,2840,2840,0,3897375,2860,2860,0,3522879,2812,2812,0,3923642,2812,2812,0,3892628,2812,2812,0,3517951,2824,2824,0,4275879,2860,2860,0,3508292,2824,2824,0,4193072,2800,2800,0,3321261,2840,2840,0,3287207,2864,2864,0,3327450,2812,2812,64,0x7f8bc7a80ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fb5d5860ec0,32768,32768,0,64,0x7fa6a5348ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27685,25349,9618,2805,0,39619,200989.0,0.0,69903.0,131086.0,64,0x7fcd72e38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131074.0,94908.0,45649.0,0.0,64,0x7f12b11a8ec0,0,185211,0,0,65536,63800,56,1680,64,0x7f16ec274ec0,18850381,17530827,975490,344064,2738187,0,0,163840,832.0,515136.0,0.0,524288.0,618227.0,32768.0,963178,0,0,13140,91094.0,91094.0,0.0,91094.0,64,0x7f0fa95e8ec0,276,0,0,2078425,718,0,0,2283622,128,0,0,1857323,30,0,0,1917834,65,0,0,1851409,127,0,0,2017291,0,0,0,1586952,0,0,0,1845882,39,0,0,1812700,68,0,0,1662973,506,0,0,2211686,0,0,0,1799130,0,0,0,1659931,89,0,0,2008008,1172,0,0,2195573,0,0,0,1802041,714,0,0,2323621,0,0,0,1850067,1600,0,0,2540949,14,0,0,2025056,0,0,0,1700205,58,0,0,1970555,580,0,0,2131441,0,0,0,1845730,36,0,0,1711716,0,0,0,1699576,0,0,0,1762701,344,0,0,2084798,268,0,0,2144912,0,0,0,1524111,15,0,0,1959758,68,0,0,1791707,64,0x7fb3dee04ec0,6286,0,4096,6327,0,4096,6293,0,4096,6289,0,4096,6316,0,4096,6277,0,4096,6253,0,4096,6294,0,4096,6289,0,4096,6290,0,4096,6328,0,4096,6291,0,4096,6293,0,4096,6321,0,4096,6277,0,4096,6254,0,4096,6267,0,4096,6284,0,4096,6305,0,4096,6330,0,4096,6276,0,4096,6281,0,4096,6271,0,4096,6258,0,4096,6256,0,4096,6265,0,4096,6289,0,4096,6307,0,4096,6328,0,4096,6285,0,4096,6283,0,4096,6268,0,4096,64,0x7f8ab4290ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119329188.0,56654754.0,0.0,200067979273538,200067979290178 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f30d60ec0,0,393216,163840,0,0,0,0,0,28940,0.0,0.0,0.0,32768.0,0.0,0.0,207.0,32768.0,4096,16384,302,40717,1983,0,56.0,11.0,0.0,199940.0,64,0x7fb5e5294ec0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,0,40768,0,0,64,0x7f32c606cec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2011197.0,64,0x7f095d840ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20445,0,2660,38190,0,70095.0,131072.0,0.0,45563.0,64,0x7f18088e4ec0,2150,4096,2150,6246,2177,4096,2177,6273,2167,4096,2167,6263,2148,4096,2148,6244,2189,4096,2189,6285,2191,4097,2192,6288,2166,4096,2166,6262,2172,4096,2172,6268,2175,4099,2178,6274,2153,4099,2156,6252,2185,4096,2185,6281,2170,4096,2170,6266,2153,4096,2153,6249,2187,4097,2188,6284,2193,4096,2193,6289,2177,4096,2177,6273,2165,4096,2165,6261,2151,4096,2151,6247,2224,4099,2227,6323,2171,4096,2171,6267,2141,4096,2141,6237,2178,4096,2178,6274,2179,4096,2179,6275,2194,4096,2194,6290,2198,4096,2198,6294,2170,4096,2170,6266,2151,4096,2151,6247,2167,4097,2168,6264,2176,4096,2176,6272,2144,4096,2144,6240,2179,4096,2179,6275,2180,4096,2180,6276,64,0x7f4fb5fd8ec0,0,0,0,56,0,65536,65536,0,64,0x7f42a6b3cec0,114688,0,32768,32768,16384,16384,65536,49152,57765526.0,192978845.0,50819565.0,131072.0,0.0,604455.0,0,0,25175,23721.0,131085.0,0.0,24.0,64,0x7fb6d6754ec0,333064,224258,16384,0,16384,16384,32768,49152,41632,41632,3191915.0,2493074.0,4219.0,397854.0,1717635.0,0.0,2482516.0,2176088.0,333056,233379,41632,0,41632,0,1332224.0,788337.0,0.0,0.0,64,0x7f4ccb2e8ec0,4096,0,441,0,4096,0,36,0,4097,0,801,0,4096,0,1738,0,4096,0,1182,0,4097,0,325,0,4096,0,91,0,4096,0,368,0,4096,0,330,0,4099,0,95,0,4096,0,1080,0,4096,0,198,0,4096,0,349,0,4096,0,56,0,4096,0,70,0,4096,0,104,0,4096,0,398,0,4096,0,1146,0,4097,0,484,0,4096,0,416,0,4096,0,21,0,4096,0,1052,0,4096,0,261,0,4096,0,1429,0,4096,0,305,0,4096,0,866,0,4096,0,64,0,4098,0,1044,0,4096,0,1,0,4096,0,434,0,4096,0,408,0,4096,0,1556,0,64,0x7f707852cec0,0,3019414,2840,2840,0,3805566,2868,2868,0,2893168,2844,2844,0,4394570,2838,2838,0,3719139,2908,2908,0,3646514,2840,2840,0,2821869,2868,2868,0,3990068,2836,2836,0,3130074,2836,2836,0,4047865,2840,2840,0,4304105,2864,2864,0,3279555,2836,2836,0,3458266,2832,2832,0,3684432,2908,2908,0,3405072,2840,2840,0,3811030,2868,2868,0,3269281,2842,2842,0,3373001,2868,2868,0,5091322,2848,2848,0,3554058,2864,2864,0,4766885,2800,2800,0,3706149,2840,2840,0,3600606,2844,2844,0,4547252,2840,2840,0,4987512,2840,2840,0,2811187,2844,2844,0,3459144,2868,2868,0,5074160,2856,2856,0,4714888,2868,2868,0,3573994,2792,2792,0,3265947,2840,2840,0,3313355,2844,2844,64,0x7f8bc7a80ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fb5d5860ec0,32768,32768,0,64,0x7fa6a5348ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27882,26189,9638,2476,0,38724,201429.0,0.0,70344.0,131085.0,64,0x7fcd72e38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,107629.0,45685.0,0.0,64,0x7f12b11a8ec0,0,181934,0,0,65536,63800,56,1680,64,0x7f16ec274ec0,20228511,18668289,1216158,344064,2851023,0,0,163840,832.0,515156.0,0.0,524288.0,700661.0,32768.0,1080267,0,0,14023,91210.0,91210.0,0.0,91210.0,64,0x7f0fa95e8ec0,59,0,0,1657032,0,0,0,1681772,0,0,0,2118893,408,0,0,2262814,647,0,0,2130525,170,0,0,2065416,0,0,0,1548795,204,0,0,2122947,688,0,0,2112658,0,0,0,1382101,0,0,0,1548077,0,0,0,1878627,534,0,0,2026008,898,0,0,2307419,1835,0,0,2466622,571,0,0,1847218,0,0,0,1647624,959,0,0,2335257,0,0,0,1332561,0,0,0,1672615,438,0,0,2354054,1123,0,0,2533509,55,0,0,1837177,130,0,0,1918288,194,0,0,1926745,0,0,0,1631619,171,0,0,1895566,0,0,0,1345366,22,0,0,1859148,1593,0,0,2502870,1267,0,0,2554825,509,0,0,2172337,64,0x7fb3dee04ec0,6267,0,4096,6317,0,4096,6241,0,4096,6246,0,4096,6289,0,4096,6320,0,4096,6253,0,4096,6268,0,4096,6269,0,4096,6264,0,4096,6323,0,4096,6244,0,4096,6246,0,4096,6294,0,4096,6319,0,4096,6256,0,4096,6263,0,4096,6239,0,4096,6268,0,4096,6290,0,4096,6242,0,4096,6261,0,4096,6290,0,4096,6285,0,4096,6294,0,4096,6268,0,4096,6241,0,4096,6268,0,4096,6291,0,4096,6241,0,4096,6263,0,4096,6290,0,4096,64,0x7f8ab4290ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,121672689.0,58735129.0,0.0,200067979310018,200067979325698 diff --git a/tests/workloads/kernel_verbose_1/MI200/roofline.csv b/tests/workloads/kernel_verbose_1/MI200/roofline.csv deleted file mode 100644 index 3573643cb0..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/roofline.csv +++ /dev/null @@ -1,5 +0,0 @@ -device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.9409,1388.3834,1389.4984,5015.6914,5012.4653,5018.9175,9224.9053,9224.2285,9225.582,18054.15,18053.188,18055.113,20938.648,20877.58,20999.717,20266.691,20266.037,20267.346,170416.02,170412.12,170419.91,164870.83,164865.84,164875.81,41418.922,41418.492,41419.352,41477.297,41476.762,41477.832,166331.31,165841,166821.62 -1,1389.4838,1388.9222,1390.0453,5028.2129,5026.3608,5030.0649,9233.1123,9232.4492,9233.7754,18093.682,18088.578,18098.785,20972.543,20905.521,21039.564,20293.006,20292.27,20293.742,170840.12,170836,170844.25,165095.39,165091.75,165099.03,41482.512,41481.504,41483.52,41540.258,41539.344,41541.172,166864.66,166861.39,166867.92 -2,1388.2366,1387.7125,1388.7606,5035.1167,5032.833,5037.4004,9259.4932,9258.8311,9260.1553,18100.863,18098.338,18103.389,21041.74,21041.322,21042.158,20345.758,20345.221,20346.295,171069.66,171065.45,171073.86,165449.23,165445.14,165453.33,41565.84,41564.875,41566.805,41627.988,41626.949,41629.027,166897.69,166307.59,167487.78 -3,1388.8666,1388.2894,1389.4437,5032.5542,5031.2466,5033.8618,9241.6113,9241.0742,9242.1484,18025.863,18022.361,18029.365,21034.627,21034.064,21035.189,20313.65,20312.877,20314.424,171046.27,171041.16,171051.38,165240.64,165236.17,165245.11,41444.09,41289.723,41598.457,41586.117,41585.5,41586.734,167022.28,167020.55,167024.02 diff --git a/tests/workloads/kernel_verbose_1/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_1/MI200/sysinfo.csv deleted file mode 100644 index 2fc047efde..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_1,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:45:22 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_1/MI200/timestamps.csv b/tests/workloads/kernel_verbose_1/MI200/timestamps.csv deleted file mode 100644 index 6a139a2a7b..0000000000 --- a/tests/workloads/kernel_verbose_1/MI200/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,368049,368049,1048576,256,0,0,8,0,16,64,0x0,0x7f2adce70ec0,200067979137309,200067979162338,200067979182178,200067979197333 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,368049,368049,1048576,256,0,0,8,0,16,64,0x0,0x7f2adce70ec0,200067979192984,200067979273538,200067979290178,200067979291451 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,368049,368049,1048576,256,0,0,8,0,16,64,0x0,0x7f2adce70ec0,200067979301109,200067979310018,200067979325698,200067979327008 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index f854ac49cb..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202183,202183,1048576,256,0,0,8,8,16,64,0x0,0x7fc19df06e80,48930,48930,16384,65536,17387,2236868,194368956320546,194382200379108,194382200403588,194368964074598 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202183,202183,1048576,256,0,0,8,8,16,64,0x0,0x7fc19df06e80,42369,42369,16384,65536,8129,1048576,194368964088674,194382200591908,194382200610788,194368964418298 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202183,202183,1048576,256,0,0,8,8,16,64,0x0,0x7fc19df06e80,42036,42036,16384,65536,8251,1048576,194368964450570,194382200632548,194382200651908,194368964637223 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 302b134e6f..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202368,202368,1048576,256,0,0,8,8,16,64,0x0,0x7f56a412ce80,0,0,0,194369449081429,194382200379108,194382200403588,194369456955538 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202368,202368,1048576,256,0,0,8,8,16,64,0x0,0x7f56a412ce80,0,0,0,194369456972621,194382200591908,194382200610788,194369457310971 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202368,202368,1048576,256,0,0,8,8,16,64,0x0,0x7f56a412ce80,0,0,0,194369457339004,194382200632548,194382200651908,194369457513895 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index 54604f023c..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202554,202554,1048576,256,0,0,8,8,16,64,0x0,0x7fa8b3c30e80,65536,190140,24309104,194369940413738,194382200379108,194382200403588,194369948055977 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202554,202554,1048576,256,0,0,8,8,16,64,0x0,0x7fa8b3c30e80,65536,164948,21160952,194369948078049,194382200591908,194382200610788,194369948374541 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202554,202554,1048576,256,0,0,8,8,16,64,0x0,0x7fa8b3c30e80,65536,192100,24628256,194369948402403,194382200632548,194382200651908,194369948574459 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index 49429e3eec..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202737,202737,1048576,256,0,0,8,8,16,64,0x0,0x7f36814e8e80,32768,653699,83684436,194370432681737,194382200379108,194382200403588,194370440420971 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202737,202737,1048576,256,0,0,8,8,16,64,0x0,0x7f36814e8e80,32768,669006,85644320,194370440440017,194382200591908,194382200610788,194370440743191 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202737,202737,1048576,256,0,0,8,8,16,64,0x0,0x7f36814e8e80,32768,683114,87439184,194370440771745,194382200632548,194382200651908,194370440942228 diff --git a/tests/workloads/kernel_verbose_2/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_2/MI100/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 8426db5bcb..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,202926,202926,1048576,256,0,0,8,8,16,64,0x0,0x7f934e4eee80,48771,48771,18480,390176,16384,25511502,237172,0,102544652,194370925985268,194382200379108,194382200403588,194370933763826 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,202926,202926,1048576,256,0,0,8,8,16,64,0x0,0x7f934e4eee80,41866,41866,13148,334936,16384,24344497,229388,0,97861616,194370933793472,194382200591908,194382200610788,194370934145419 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,202926,202926,1048576,256,0,0,8,8,16,64,0x0,0x7f934e4eee80,41674,41674,12445,333400,16384,24426899,230891,0,98192152,194370934183962,194382200632548,194382200651908,194370934372258 diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index 202141726e..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6f289aa046..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_10.txt deleted file mode 100644 index a00555d953..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_11.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_12.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_13.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_14.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_15.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_16.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 2180ee3f63..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_3.txt deleted file mode 100644 index 8f1ba90d04..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_4.txt deleted file mode 100644 index 9a82481329..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_5.txt deleted file mode 100644 index bbc1f21123..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_6.txt deleted file mode 100644 index b6368182b4..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_7.txt deleted file mode 100644 index 3f7673fd23..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_8.txt deleted file mode 100644 index facba6bd95..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_9.txt deleted file mode 100644 index d458645ea4..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_2/MI100/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_2/MI100/pmc_dispatch_info.csv deleted file mode 100644 index 17300ae9af..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/pmc_dispatch_info.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_verbose_2/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_2/MI100/pmc_perf.csv deleted file mode 100644 index fc9c6e019e..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_3,obj_3,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_6,obj_6,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_7,obj_7,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_8,obj_8,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_9,obj_9,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_11,obj_11,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_12,obj_12,TCC_EA_ATOMIC_LEVEL_sum,wave_size_13,obj_13,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_14,obj_14,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_15,obj_15,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_16,obj_16,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f156a44ae80,0,8192,4096,8192,0,8240,4144,8240,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8414,4318,8414,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f76e1e78e80,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,0,47639,0,0,64,0x7fb737450e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131232.0,0.0,312.0,131231.0,64,0x7f77cd934e80,4096,0,6931,0,4096,0,86,0,4099,0,4591,0,4144,0,4396,0,4096,0,2462,0,4096,0,1204,0,4096,0,240,0,4096,0,3053,0,4096,0,1650,0,4096,0,1004,0,4144,0,1807,0,4096,0,2289,0,4096,0,43,0,4096,0,0,0,4096,0,2384,0,4096,0,756,0,4096,0,830,0,4096,0,2200,0,4096,0,5759,0,4096,0,754,0,4096,0,1971,0,4096,0,975,0,4096,0,339,0,4096,0,277,0,4366,0,6200,0,4096,0,1188,0,4096,0,5341,0,4096,0,59,0,4097,0,0,0,4096,0,83,0,4096,0,31,0,4096,0,433,0,64,0x7f23fefece80,0,3973094,4096,4096,0,3575095,4096,4096,0,3090678,4096,4096,0,2557002,4096,4096,0,3684560,4096,4096,0,3032625,4096,4096,0,3145760,4096,4096,0,3469629,4096,4096,0,3888860,4096,4096,0,4837539,4096,4096,0,2450672,4096,4096,0,2740624,4096,4096,0,5153327,4096,4096,0,3254310,4096,4096,0,3042508,4096,4096,0,2569101,4096,4096,0,4718010,4096,4096,0,3977840,4096,4096,0,2877048,4096,4096,0,2531062,4096,4096,0,3926983,4096,4096,0,3297509,4096,4096,0,3423963,4096,4096,0,2482331,4096,4096,0,2530588,4096,4096,0,3609441,4096,4096,0,3337674,4096,4096,0,2641930,4096,4096,0,2908298,4096,4096,0,2965224,4096,4096,0,2802934,4096,4096,0,2879762,4096,4096,64,0x7ff447138e80,2224134,360448,163840,0,0,180224,114688,0,68011968.0,193155059.0,77936326.0,131072.0,0.0,698182.0,0,0,26674,131108.0,0.0,0.0,131108.0,64,0x7fe9eb506e80,381808,232935,3412645,16384,25113165,144,48,0,47725,47725,3846402.0,2986823.0,7299.0,1104437.0,2045534.0,0.0,2977750.0,2665854.0,380351,242860,47725,0,47725,0,1527200.0,956122.0,0.0,0.0,64,0x7fd2f5ab2e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86344.0,44728.0,131111.0,0.0,64,0x7f63c13d4e80,189379,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11954,28338,9839,550,0,46475,262706.0,0.0,188.0,262518.0,64,0x7f8f2282ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46926,0,131517.0,131072.0,0.0,131104.0,64,0x7fea86a3ee80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f3459734e80,32768,0,0,0,16384,16384,393216,22921941,960.0,513901.0,0.0,524288.0,1098033.0,32768.0,0,0,0,17873,131072.0,131072.0,0.0,131072.0,64,0x7f35166c4e80,0.0,64,0x7f4fbfe06e80,0,0,192,0,65536,64369,48,1511,31068,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47104,1767,0,48.0,219.0,0.0,262288.0,64,0x7f6057aaee80,5927,0,0,2166326,3261,0,0,1982388,6005,0,0,2255863,4438,0,0,1919764,4487,0,0,2102843,4740,0,0,2098259,6067,0,0,2136986,4192,0,0,1962012,3487,0,0,1943608,2487,0,0,1886355,5788,0,0,2053919,5772,0,0,2090662,3938,0,0,1996591,4695,0,0,2036435,5862,0,0,2145962,5951,0,0,2131657,3405,0,0,1997465,3068,0,0,1950682,4782,0,0,2166745,4975,0,0,2032355,5815,0,0,2129578,3946,0,0,2029762,6564,0,0,2212734,5237,0,0,2093705,5910,0,0,2166414,2014,0,0,1827861,5759,0,0,2055192,5235,0,0,1999912,5892,0,0,2183682,2944,0,0,1948454,5917,0,0,2141567,2711,0,0,1867756,64,0x7f70efdd8e80,131072.0,131072.0,0.0,2581687.0,0.0,0.0,121433529.0,60798872.0,64,0x7f97be568e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,48226.0,131089.0,194382200379108,194382200403588 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f156a44ae80,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,47,8193,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8429,4333,8429,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f76e1e78e80,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,0,43575,0,0,64,0x7fb737450e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131320.0,0.0,494.0,131319.0,64,0x7f77cd934e80,4096,0,1905,0,4096,0,4711,0,4096,0,3579,0,4144,0,172,0,4096,0,1310,0,4096,0,19,0,4096,0,71,0,4096,0,0,0,4097,0,1396,0,4096,0,1499,0,4144,0,780,0,4096,0,815,0,4096,0,567,0,4096,0,1944,0,4096,0,675,0,4100,0,0,0,4096,0,3990,0,4096,0,6756,0,4096,0,210,0,4096,0,1110,0,4096,0,388,0,4096,0,6753,0,4096,0,1200,0,4096,0,0,0,4382,0,4061,0,4096,0,57,0,4096,0,208,0,4096,0,0,0,4097,0,596,0,4096,0,0,0,4096,0,521,0,4096,0,52,0,64,0x7f23fefece80,0,3024263,2724,2724,0,3189694,2724,2724,0,3359847,2708,2708,0,3204889,2722,2722,0,4239198,2712,2712,0,2762119,2708,2708,0,4362490,2746,2746,0,3494543,2710,2710,0,3305691,2738,2738,0,2719735,2698,2698,0,4323178,2759,2759,0,4032834,2720,2720,0,3455208,2702,2702,0,3023765,2698,2698,0,3166339,2748,2748,0,3185943,2712,2712,0,5100369,2704,2704,0,3467488,2732,2732,0,4596794,2744,2744,0,3330846,2716,2716,0,3553629,2708,2708,0,2840479,2766,2766,0,2800857,2730,2730,0,2691871,2700,2700,0,3117780,2702,2702,0,2872134,2705,2705,0,3983009,2773,2773,0,3227016,2702,2702,0,2978795,2737,2737,0,2716404,2723,2723,0,3975822,2756,2756,0,3357948,2706,2706,64,0x7ff447138e80,1498978,360448,163840,0,0,180224,114688,0,70684587.0,172980258.0,72840260.0,131072.0,0.0,669839.0,0,0,26021,65159.0,0.0,0.0,65159.0,64,0x7fe9eb506e80,349008,236258,3458074,16384,25329802,0,48,0,43625,43625,3833472.0,3059966.0,7249.0,1092242.0,2075811.0,0.0,3051125.0,2739341.0,349000,245775,43625,0,43625,0,1396000.0,816958.0,0.0,0.0,64,0x7fd2f5ab2e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,49778.0,36901.0,30414.0,0.0,64,0x7f63c13d4e80,183800,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14772,31156,8646,2409,0,41077,262573.0,0.0,47.0,262526.0,64,0x7f8f2282ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2779,40304,0,131359.0,131072.0,0.0,86739.0,64,0x7fea86a3ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f3459734e80,32768,0,0,0,16384,16384,393216,23804899,1120.0,512122.0,0.0,524288.0,1383396.0,32768.0,0,0,0,22988,129842.0,129842.0,0.0,129842.0,64,0x7f35166c4e80,0.0,64,0x7f4fbfe06e80,0,0,96,0,65536,65559,0,0,34236,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,505,49836,6552,0,96.0,439.0,0.0,262144.0,64,0x7f6057aaee80,1342,0,0,1357706,3088,0,0,1560245,1132,0,0,1425286,1786,0,0,1492138,406,0,0,1137309,1815,0,0,1491560,1686,0,0,1417614,3704,0,0,1639531,330,0,0,1118683,2116,0,0,1446658,1342,0,0,1345317,385,0,0,1287878,1411,0,0,1388963,1533,0,0,1554974,93,0,0,1202262,1847,0,0,1468069,640,0,0,1268551,1030,0,0,1486093,2230,0,0,1568133,2554,0,0,1393206,1138,0,0,1394563,2029,0,0,1418829,4734,0,0,1700618,1901,0,0,1532860,1723,0,0,1360382,1933,0,0,1427951,666,0,0,1290575,3725,0,0,1639430,702,0,0,1230480,5272,0,0,1740161,1313,0,0,1350818,2998,0,0,1550864,64,0x7f70efdd8e80,131072.0,131072.0,0.0,2765054.0,0.0,0.0,105015707.0,39728540.0,64,0x7f97be568e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,28341.0,88900.0,194382200591908,194382200610788 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f156a44ae80,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,47,8193,4144,8240,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8473,4377,8473,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f76e1e78e80,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,0,43080,0,0,64,0x7fb737450e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131237.0,0.0,328.0,131236.0,64,0x7f77cd934e80,4096,0,3095,0,4096,0,3086,0,4096,0,2542,0,4144,0,1015,0,4096,0,3921,0,4096,0,2973,0,4096,0,3175,0,4096,0,925,0,4097,0,7725,0,4096,0,4269,0,4144,0,3359,0,4096,0,4690,0,4096,0,4468,0,4096,0,6071,0,4096,0,4591,0,4100,0,2176,0,4096,0,7363,0,4096,0,1908,0,4096,0,2715,0,4096,0,908,0,4096,0,3838,0,4096,0,3632,0,4096,0,1443,0,4096,0,510,0,4304,0,8034,0,4096,0,3350,0,4096,0,1958,0,4096,0,2337,0,4097,0,2420,0,4096,0,1224,0,4096,0,103,0,4096,0,800,0,64,0x7f23fefece80,0,3349150,2756,2756,0,3793384,2760,2760,0,3130678,2684,2684,0,3139875,2708,2708,0,4089862,2728,2728,0,3224165,2748,2748,0,2954370,2736,2736,0,3165260,2726,2726,0,4504655,2736,2736,0,3641152,2694,2694,0,3539525,2716,2716,0,3152590,2704,2704,0,3651449,2728,2728,0,3656055,2700,2700,0,3028050,2720,2720,0,3432579,2710,2710,0,4720728,2702,2702,0,4212986,2728,2728,0,3313882,2708,2708,0,3448004,2700,2700,0,3423245,2710,2710,0,3323042,2759,2759,0,3280038,2704,2704,0,2738710,2680,2680,0,2954379,2713,2713,0,3669247,2717,2717,0,2814013,2700,2700,0,3010430,2708,2708,0,3044370,2743,2743,0,4001444,2745,2745,0,3228176,2680,2680,0,3191296,2714,2714,64,0x7ff447138e80,2443266,360448,163840,0,0,180224,114688,0,64777445.0,179145628.0,71679788.0,131072.0,0.0,863837.0,0,0,25996,109718.0,0.0,0.0,109718.0,64,0x7fe9eb506e80,342280,230418,3382281,16384,24778089,0,48,0,42784,42784,3745777.0,3046045.0,6539.0,1086510.0,2113631.0,0.0,3037163.0,2725311.0,342272,239741,42784,0,42784,0,1369088.0,807240.0,0.0,0.0,64,0x7fd2f5ab2e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86383.0,0.0,131112.0,0.0,64,0x7f63c13d4e80,188456,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11101,27485,8717,2465,0,42240,262548.0,0.0,47.0,262501.0,64,0x7f8f2282ae80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2860,40281,0,131392.0,131072.0,0.0,86551.0,64,0x7fea86a3ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f3459734e80,32768,0,0,0,16384,16384,393216,23804305,960.0,513922.0,0.0,524288.0,1174041.0,32768.0,0,0,0,14263,86641.0,86641.0,0.0,86641.0,64,0x7f35166c4e80,0.0,64,0x7f4fbfe06e80,0,0,48,0,65536,65536,0,0,30145,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41433,1743,0,48.0,270.0,0.0,262144.0,64,0x7f6057aaee80,4035,0,0,1623242,2124,0,0,1501904,2205,0,0,1476320,5433,0,0,1646903,2328,0,0,1484069,3395,0,0,1534251,3545,0,0,1574752,5006,0,0,1624070,3314,0,0,1600346,4030,0,0,1695220,3079,0,0,1538954,3129,0,0,1505311,3468,0,0,1511261,3188,0,0,1462399,1180,0,0,1352653,5031,0,0,1555926,4079,0,0,1636492,2597,0,0,1468386,549,0,0,1222899,4525,0,0,1539683,4307,0,0,1585037,3242,0,0,1555900,2048,0,0,1458957,4678,0,0,1597845,4747,0,0,1594757,3341,0,0,1570089,3538,0,0,1566549,4498,0,0,1526048,6115,0,0,1688727,2321,0,0,1476960,5009,0,0,1757596,4105,0,0,1615484,64,0x7f70efdd8e80,131072.0,131072.0,0.0,2557270.0,0.0,0.0,124629672.0,47819336.0,64,0x7f97be568e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,33750.0,115087.0,194382200632548,194382200651908 diff --git a/tests/workloads/kernel_verbose_2/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_2/MI100/sysinfo.csv deleted file mode 100644 index 630f57ae2a..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:10:33 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_2/MI100/timestamps.csv b/tests/workloads/kernel_verbose_2/MI100/timestamps.csv deleted file mode 100644 index 74c2c44d45..0000000000 --- a/tests/workloads/kernel_verbose_2/MI100/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,206324,206324,1048576,256,0,0,8,8,16,64,0x0,0x7f7f525aee80,194382200353481,194382200379108,194382200403588,194382200418083 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,206324,206324,1048576,256,0,0,8,8,16,64,0x0,0x7f7f525aee80,194382200416540,194382200591908,194382200610788,194382200612441 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,206324,206324,1048576,256,0,0,8,8,16,64,0x0,0x7f7f525aee80,194382200623271,194382200632548,194382200651908,194382200653348 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 94b724a48b..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,368475,368475,1048576,256,0,0,8,0,16,64,0x0,0x7ffb08e3cec0,27564,27564,16384,65536,13515,1533580,200161368579796,200174259821413,200174259842053,200161385412590 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,368475,368475,1048576,256,0,0,8,0,16,64,0x0,0x7ffb08e3cec0,41380,41380,16384,65536,9363,1048672,200161385434030,200174259860293,200174259876453,200161385706686 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,368475,368475,1048576,256,0,0,8,0,16,64,0x0,0x7ffb08e3cec0,42124,42124,16384,65536,9450,1048648,200161385736292,200174259950853,200174259967493,200161385875185 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 4b91723d21..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,368658,368658,1048576,256,0,0,8,0,16,64,0x0,0x7f1d2a670ec0,0,0,0,200161856840122,200174259821413,200174259842053,200161872800946 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,368658,368658,1048576,256,0,0,8,0,16,64,0x0,0x7f1d2a670ec0,0,0,0,200161872820553,200174259860293,200174259876453,200161873098529 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,368658,368658,1048576,256,0,0,8,0,16,64,0x0,0x7f1d2a670ec0,0,0,0,200161873124929,200174259950853,200174259967493,200161873321250 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index ab70ba9365..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,368859,368859,1048576,256,0,0,8,0,16,64,0x0,0x7f3ec6f68ec0,65536,192258,21467752,200162338737471,200174259821413,200174259842053,200162354523133 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,368859,368859,1048576,256,0,0,8,0,16,64,0x0,0x7f3ec6f68ec0,65536,262844,29388808,200162354541568,200174259860293,200174259876453,200162354807732 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,368859,368859,1048576,256,0,0,8,0,16,64,0x0,0x7f3ec6f68ec0,65536,256738,28673856,200162354833330,200174259950853,200174259967493,200162354984777 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index fce6e99566..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,369043,369043,1048576,256,0,0,8,0,16,64,0x0,0x7f6e427c4ec0,32768,287066,32165360,200162820253779,200174259821413,200174259842053,200162835982564 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,369043,369043,1048576,256,0,0,8,0,16,64,0x0,0x7f6e427c4ec0,32768,568990,63732840,200162836000868,200174259860293,200174259876453,200162836321695 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,369043,369043,1048576,256,0,0,8,0,16,64,0x0,0x7f6e427c4ec0,32768,590916,66182320,200162836347424,200174259950853,200174259967493,200162836509170 diff --git a/tests/workloads/kernel_verbose_2/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_2/MI200/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 9cacae8857..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,369226,369226,1048576,256,0,0,8,0,16,64,0x0,0x7f982e044ec0,28181,28181,10938,225456,16384,11281842,134087,0,45624964,200163302335206,200174259821413,200174259842053,200163317930148 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,369226,369226,1048576,256,0,0,8,0,16,64,0x0,0x7f982e044ec0,41120,41120,13245,328968,16384,19597753,226880,0,78874180,200163317957940,200174259860293,200174259876453,200163318228011 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,369226,369226,1048576,256,0,0,8,0,16,64,0x0,0x7f982e044ec0,40436,40436,12974,323496,16384,19482902,222930,0,78428532,200163318263278,200174259950853,200174259967493,200163318411007 diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_0.txt deleted file mode 100644 index 4ffdc32149..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6c277f4a37..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_10.txt deleted file mode 100644 index 7053d4dce6..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_11.txt deleted file mode 100644 index 77ae8b461f..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_12.txt deleted file mode 100644 index dfb2cf65e5..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_13.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_14.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_15.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_16.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_17.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_17.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_18.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_18.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_2.txt deleted file mode 100644 index 70b69f8928..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_3.txt deleted file mode 100644 index e47f8e33c9..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_4.txt deleted file mode 100644 index 2d96f365a9..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_5.txt deleted file mode 100644 index e50beed390..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_6.txt deleted file mode 100644 index 15a2277c1b..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_7.txt deleted file mode 100644 index b42ce91618..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_8.txt deleted file mode 100644 index 21d4c7a998..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_9.txt deleted file mode 100644 index 9ffe5778c3..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_2/MI200/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_2/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_2/MI200/pmc_perf.csv deleted file mode 100644 index 6721108893..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_3,obj_3,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_4,obj_4,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_5,obj_5,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_8,obj_8,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_9,obj_9,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_12,obj_12,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_13,obj_13,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_14,obj_14,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_15,obj_15,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_16,obj_16,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_17,obj_17,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_18,obj_18,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7a5ea30ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14028,19506,7920,547,0,27221,203514.0,0.0,72430.0,131084.0,64,0x7f1ae2278ec0,10859351,9857065,658222,344064,1639415,0,0,163840,832.0,515136.0,0.0,524288.0,284003.0,32768.0,485803,0,0,10923,131072.0,131072.0,0.0,131072.0,64,0x7f15a5de8ec0,0,0,0,956056,0,0,0,1011778,0,0,0,1136179,0,0,0,1189699,0,0,0,1104475,12,0,0,1152792,12,0,0,1145845,47,0,0,1300444,65,0,0,1238716,0,0,0,983608,0,0,0,937471,0,0,0,1144009,0,0,0,1161780,0,0,0,1121077,0,0,0,1023641,0,0,0,1136005,0,0,0,1124093,5,0,0,1216583,0,0,0,1002079,12,0,0,1140318,0,0,0,1029452,196,0,0,1321454,0,0,0,1139146,0,0,0,1115911,0,0,0,1124928,0,0,0,1095036,0,0,0,1014058,0,0,0,1103718,0,0,0,1027860,0,0,0,1051087,0,0,0,1148759,0,0,0,1015853,64,0x7f05f40a0ec0,32768,32768,0,64,0x7f47183d8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fb8009f8ec0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,0,27522,0,0,64,0x7f8d37784ec0,4096,0,0,0,4096,0,0,0,4096,0,22,0,4096,0,0,0,4096,0,0,0,4096,0,4,0,4101,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,34,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4099,0,0,0,4096,0,219,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7fbc26c78ec0,0,0,0,224,0,65536,64181,56,64,0x7fed73b94ec0,114688,0,32768,32768,16384,16384,65536,49152,27830943.0,88351260.0,38720340.0,131072.0,0.0,206725.0,0,0,14875,138.0,131081.0,0.0,10.0,64,0x7f65b5028ec0,2231,4096,2231,6327,2284,4096,2284,6380,2283,4096,2283,6379,2286,4096,2286,6382,2264,4096,2264,6360,2269,4097,2270,6366,2294,4096,2294,6390,2290,4096,2290,6386,2290,4096,2290,6386,2232,4096,2232,6328,2286,4096,2286,6382,2284,4096,2284,6380,2286,4096,2286,6382,2324,4097,2325,6421,2272,4096,2272,6368,2293,4096,2293,6389,2280,4099,2283,6379,2289,4096,2289,6385,2243,4097,2244,6340,2258,4096,2258,6354,2281,4096,2281,6377,2325,4096,2325,6421,2269,4096,2269,6365,2449,4098,2451,6547,2285,4096,2285,6381,2284,4096,2284,6380,2295,4096,2295,6391,2243,4096,2243,6339,2256,4096,2256,6352,2281,4096,2281,6377,2327,4096,2327,6423,2271,4096,2271,6367,64,0x7f86b4438ec0,222024,129283,16384,0,16384,16384,32768,49152,27752,27752,1958260.0,1352086.0,3458.0,150388.0,1064219.0,0.0,1344454.0,1047013.0,220313,137414,27752,0,27752,0,888064.0,475768.0,0.0,0.0,64,0x7f0869250ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10271,0,817,27847,0,72952.0,131072.0,0.0,65568.0,64,0x7f1c3083cec0,0,1240407,4096,4096,0,1293421,4096,4096,0,1290782,4096,4096,0,1155322,4096,4096,0,1145435,4096,4096,0,1087237,4096,4096,0,1643369,4096,4096,0,1264251,4096,4096,0,1137249,4096,4096,0,1259465,4096,4096,0,1230781,4096,4096,0,1245523,4096,4096,0,1128832,4096,4096,0,1138570,4096,4096,0,1280799,4096,4096,0,1238290,4096,4096,0,1057989,4096,4096,0,1137603,4096,4096,0,1119570,4096,4096,0,1501648,4096,4096,0,1216808,4096,4096,0,1288956,4096,4096,0,1162251,4096,4096,0,1182789,4096,4096,0,1222269,4096,4096,0,1023575,4096,4096,0,1059677,4096,4096,0,1416373,4096,4096,0,1365018,4096,4096,0,1187606,4096,4096,0,1057060,4096,4096,0,1306203,4096,4096,64,0x7f2d2947cec0,0,393216,163840,0,0,0,0,0,17744,0.0,0.0,0.0,32768.0,0.0,0.0,405.0,32768.0,4096,16384,352,28253,2231,0,56.0,5.0,0.0,203801.0,64,0x7f553b0b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,35839.0,46120.0,19416.0,64,0x7effc4ae8ec0,1257,113304,0,0,65536,63800,56,1680,64,0x7f123191cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41867435.0,34832387.0,0.0,64,0x7f637f758ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,980229.0,64,0x7fb1db9c4ec0,6362,0,4096,6346,0,4096,6375,0,4096,6427,0,4096,6346,0,4096,6364,0,4096,6340,0,4096,6433,0,4096,6436,0,4096,6362,0,4096,6347,0,4096,6376,0,4096,6427,0,4096,6349,0,4096,6363,0,4096,6346,0,4096,6386,0,4096,6392,0,4096,6369,0,4096,6340,0,4096,6382,0,4096,6384,0,4096,6378,0,4096,6520,0,4096,6354,0,4096,6388,0,4096,6393,0,4096,6369,0,4096,6341,0,4096,6382,0,4096,6387,0,4096,6381,0,4096,200174259821413,200174259842053 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7a5ea30ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,27922,28136,8427,550,0,35389,200522.0,0.0,69447.0,131075.0,64,0x7f1ae2278ec0,17699656,17126682,228910,344064,2581872,0,0,163840,0.0,524288.0,0.0,524288.0,456056.0,32768.0,784400,0,0,11580,91294.0,91294.0,0.0,91294.0,64,0x7f15a5de8ec0,0,0,0,1476958,0,0,0,1484506,0,0,0,2141999,380,0,0,2107744,0,0,0,1962154,80,0,0,1850892,71,0,0,1795681,0,0,0,1786698,0,0,0,1643811,0,0,0,1334453,46,0,0,1707745,0,0,0,1866452,0,0,0,1565908,0,0,0,1861219,390,0,0,2198669,0,0,0,1676566,0,0,0,1810149,0,0,0,1423959,0,0,0,1448796,0,0,0,1825655,0,0,0,1643794,156,0,0,1991800,367,0,0,1884672,13,0,0,1780589,70,0,0,1809295,0,0,0,1474915,0,0,0,1540670,0,0,0,1403032,0,0,0,1508568,0,0,0,1743565,30,0,0,1748857,0,0,0,1733371,64,0x7f05f40a0ec0,32768,32768,0,64,0x7f47183d8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7fb8009f8ec0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,0,40608,0,0,64,0x7f8d37784ec0,4096,0,34,0,4096,0,2605,0,4096,0,11,0,4096,0,700,0,4096,0,907,0,4096,0,247,0,4101,0,30,0,4096,0,775,0,4096,0,106,0,4096,0,381,0,4096,0,550,0,4096,0,122,0,4098,0,309,0,4096,0,41,0,4097,0,18,0,4096,0,94,0,4096,0,289,0,4096,0,390,0,4097,0,274,0,4096,0,348,0,4096,0,503,0,4098,0,797,0,4097,0,55,0,4096,0,1123,0,4096,0,1662,0,4096,0,60,0,4096,0,64,0,4096,0,2765,0,4096,0,269,0,4096,0,94,0,4097,0,379,0,4096,0,1029,0,64,0x7fbc26c78ec0,0,0,0,56,0,65536,65536,0,64,0x7fed73b94ec0,114688,0,32768,32768,16384,16384,65536,49152,57504966.0,195097391.0,47200514.0,131072.0,0.0,543936.0,0,0,25010,5335.0,131083.0,0.0,20.0,64,0x7f65b5028ec0,2162,4096,2162,6258,2168,4096,2168,6264,2131,4097,2132,6228,2148,4096,2148,6244,2173,4096,2173,6269,2171,4097,2172,6268,2182,4096,2182,6278,2192,4096,2192,6288,2196,4096,2196,6292,2157,4096,2157,6253,2170,4096,2170,6266,2135,4096,2135,6231,2151,4096,2151,6247,2228,4097,2229,6325,2168,4096,2168,6264,2179,4096,2179,6275,2185,4098,2187,6283,2173,4096,2173,6269,2152,4098,2154,6250,2189,4096,2189,6285,2131,4096,2131,6227,2160,4099,2163,6259,2144,4096,2144,6240,2173,4096,2173,6269,2174,4096,2174,6270,2187,4096,2187,6283,2177,4096,2177,6273,2156,4096,2156,6252,2190,4096,2190,6286,2130,4096,2130,6226,2162,4096,2162,6258,2145,4096,2145,6241,64,0x7f86b4438ec0,303000,205571,16384,0,16384,16384,32768,49152,37874,37874,2949719.0,2367536.0,5033.0,364184.0,1639574.0,0.0,2353376.0,2042594.0,302992,214897,37874,0,37874,0,1211968.0,772115.0,0.0,0.0,64,0x7f0869250ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,19443,0,2653,38124,0,69188.0,131072.0,0.0,45562.0,64,0x7f1c3083cec0,0,3418781,2834,2834,0,3774926,2848,2848,0,4291359,2864,2864,0,4132082,2868,2868,0,3213153,2896,2896,0,3716569,2860,2860,0,3077725,2852,2852,0,3428377,2820,2820,0,3256268,2820,2820,0,3270489,2836,2836,0,3180611,2848,2848,0,4050351,2864,2864,0,3417258,2868,2868,0,3498552,2896,2896,0,4442452,2864,2864,0,3275478,2852,2852,0,3208451,2800,2800,0,4007546,2840,2840,0,3532965,2840,2840,0,3553152,2844,2844,0,3406685,2830,2830,0,3364811,2884,2884,0,5011486,2832,2832,0,4303897,2836,2836,0,3662817,2840,2840,0,4106975,2796,2796,0,3504339,2840,2840,0,3869973,2840,2840,0,4164728,2844,2844,0,4763343,2832,2832,0,3251083,2888,2888,0,4584202,2832,2832,64,0x7f2d2947cec0,0,393216,163840,0,0,0,0,0,27486,0.0,0.0,0.0,32768.0,0.0,0.0,252.0,32768.0,4096,16384,302,36563,2006,0,56.0,0.0,0.0,199961.0,64,0x7f553b0b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131086.0,81674.0,45365.0,0.0,64,0x7effc4ae8ec0,0,187688,0,0,65536,63800,56,1680,64,0x7f123191cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,115073211.0,59212179.0,0.0,64,0x7f637f758ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2025340.0,64,0x7fb1db9c4ec0,6237,0,4096,6257,0,4096,6248,0,4096,6233,0,4096,6273,0,4096,6249,0,4096,6257,0,4096,6256,0,4096,6259,0,4096,6233,0,4096,6259,0,4096,6251,0,4096,6231,0,4096,6280,0,4096,6253,0,4096,6253,0,4096,6261,0,4096,6253,0,4096,6255,0,4096,6280,0,4096,6232,0,4096,6243,0,4096,6237,0,4096,6224,0,4096,6223,0,4096,6264,0,4096,6253,0,4096,6249,0,4096,6276,0,4096,6235,0,4096,6249,0,4096,6238,0,4096,200174259860293,200174259876453 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f7a5ea30ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,28576,24605,9466,3198,0,40300,200307.0,0.0,69220.0,131087.0,64,0x7f1ae2278ec0,18686016,17546663,795289,344064,2763127,0,0,163840,832.0,515136.0,0.0,524288.0,601143.0,32768.0,918208,0,0,12897,91150.0,91150.0,0.0,91150.0,64,0x7f15a5de8ec0,0,0,0,1560267,0,0,0,1528060,0,0,0,1949569,0,0,0,1855561,0,0,0,1587193,2,0,0,1924652,536,0,0,2205049,99,0,0,1973648,0,0,0,1771732,0,0,0,1531031,388,0,0,1965343,0,0,0,1927530,0,0,0,1794828,0,0,0,2021137,0,0,0,1772140,95,0,0,2222713,0,0,0,1814298,90,0,0,1946681,0,0,0,1475727,0,0,0,1772875,163,0,0,2171346,0,0,0,1901219,183,0,0,1862241,0,0,0,2132632,0,0,0,1880290,0,0,0,1655226,5,0,0,1614818,0,0,0,1605000,183,0,0,2053629,0,0,0,1704115,0,0,0,1545112,0,0,0,1681595,64,0x7f05f40a0ec0,32768,32768,0,64,0x7f47183d8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fb8009f8ec0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,0,40732,0,0,64,0x7f8d37784ec0,4096,0,98,0,4096,0,139,0,4096,0,1398,0,4096,0,1034,0,4096,0,2111,0,4096,0,969,0,4101,0,765,0,4096,0,812,0,4096,0,381,0,4096,0,330,0,4096,0,143,0,4096,0,245,0,4098,0,883,0,4096,0,1257,0,4097,0,422,0,4096,0,590,0,4096,0,1248,0,4096,0,1616,0,4097,0,353,0,4096,0,921,0,4096,0,214,0,4098,0,759,0,4097,0,1061,0,4096,0,1494,0,4096,0,1745,0,4096,0,871,0,4096,0,567,0,4096,0,786,0,4096,0,782,0,4096,0,421,0,4097,0,856,0,4096,0,1219,0,64,0x7fbc26c78ec0,0,0,0,56,0,65536,65536,0,64,0x7fed73b94ec0,114688,0,32768,32768,16384,16384,65536,49152,56434754.0,202460986.0,49754619.0,131072.0,0.0,558592.0,0,0,24814,26394.0,131085.0,0.0,24.0,64,0x7f65b5028ec0,2208,4096,2208,6304,2220,4096,2220,6316,2173,4097,2174,6270,2168,4096,2168,6264,2157,4096,2157,6253,2176,4097,2177,6273,2179,4096,2179,6275,2173,4096,2173,6269,2173,4096,2173,6269,2210,4096,2210,6306,2215,4096,2215,6311,2178,4096,2178,6274,2169,4096,2169,6265,2215,4097,2216,6312,2177,4096,2177,6273,2183,4096,2183,6279,2177,4099,2180,6276,2205,4096,2205,6301,2157,4098,2159,6255,2223,4096,2223,6319,2183,4096,2183,6279,2168,4099,2171,6267,2156,4096,2156,6252,2183,4096,2183,6279,2181,4096,2181,6277,2180,4096,2180,6276,2207,4096,2207,6303,2161,4096,2161,6257,2225,4096,2225,6321,2182,4096,2182,6278,2166,4096,2166,6262,2152,4096,2152,6248,64,0x7f86b4438ec0,326352,219998,16384,0,16384,16384,32768,49152,40793,40793,3136125.0,2454363.0,4502.0,347779.0,1753482.0,0.0,2443293.0,2133873.0,326344,229021,40793,0,40793,0,1305376.0,762190.0,0.0,0.0,64,0x7f0869250ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20808,0,2647,39068,0,70062.0,131072.0,0.0,45782.0,64,0x7f1c3083cec0,0,4330318,2840,2840,0,3426749,2868,2868,0,3504767,2856,2856,0,3931420,2836,2836,0,3325380,2876,2876,0,4130117,2844,2844,0,3139565,2856,2856,0,4266411,2828,2828,0,3495466,2820,2820,0,4519191,2834,2834,0,3586841,2868,2868,0,3118187,2852,2852,0,3171777,2836,2836,0,4439257,2876,2876,0,4745545,2844,2844,0,3463541,2858,2858,0,3117032,2812,2812,0,3961551,2848,2848,0,4045052,2844,2844,0,3403891,2860,2860,0,3986132,2824,2824,0,3731800,2878,2878,0,4754579,2824,2824,0,4375906,2832,2832,0,4351714,2830,2830,0,2972415,2812,2812,0,3540266,2852,2852,0,3320714,2844,2844,0,4155841,2860,2860,0,3429068,2824,2824,0,3092763,2880,2880,0,3521856,2824,2824,64,0x7f2d2947cec0,0,393216,163840,0,0,0,0,0,29169,0.0,0.0,0.0,32768.0,0.0,0.0,239.0,32768.0,4096,16384,302,40080,1933,0,56.0,9.0,0.0,200220.0,64,0x7f553b0b0ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,101033.0,45525.0,0.0,64,0x7effc4ae8ec0,0,188262,0,0,65536,63800,56,1680,64,0x7f123191cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,114564364.0,55936691.0,0.0,64,0x7f637f758ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2023601.0,64,0x7fb1db9c4ec0,6275,0,4096,6249,0,4096,6241,0,4096,6246,0,4096,6240,0,4096,6242,0,4096,6254,0,4096,6230,0,4096,6233,0,4096,6277,0,4096,6254,0,4096,6243,0,4096,6252,0,4096,6241,0,4096,6244,0,4096,6254,0,4096,6241,0,4096,6238,0,4096,6274,0,4096,6283,0,4096,6229,0,4096,6242,0,4096,6236,0,4096,6229,0,4096,6228,0,4096,6243,0,4096,6238,0,4096,6275,0,4096,6283,0,4096,6228,0,4096,6243,0,4096,6238,0,4096,200174259950853,200174259967493 diff --git a/tests/workloads/kernel_verbose_2/MI200/roofline.csv b/tests/workloads/kernel_verbose_2/MI200/roofline.csv deleted file mode 100644 index 1b07b88444..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/roofline.csv +++ /dev/null @@ -1,5 +0,0 @@ -device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.1689,1387.6534,1388.6844,5014.3301,5011.2061,5017.4541,9222.6172,9222.0459,9223.1885,18050.293,18049.406,18051.18,20931.176,20870.689,20991.662,20261.637,20261.008,20262.266,170400.38,170395.67,170405.08,164850.41,164845.45,164855.36,41415.574,41415.02,41416.129,41474.078,41473.312,41474.844,166318.97,165828.61,166809.33 -1,1389.2894,1388.6531,1389.9258,5029.8667,5027.9429,5031.7905,9235.4102,9234.6797,9236.1406,18095.471,18091.338,18099.604,20976.723,20909.848,21043.598,20295.529,20294.941,20296.117,170841.22,170836.52,170845.92,165117.64,165114.41,165120.88,41486.184,41485.363,41487.004,41540.363,41539.438,41541.289,166883.98,166881.17,166886.8 -2,1388.4487,1387.9197,1388.9778,5036.0479,5033.9048,5038.1909,9256.2939,9255.5273,9257.0605,18099.859,18098.83,18100.889,21040.043,21039.582,21040.504,20344.139,20343.57,20344.707,171080.62,171076.52,171084.73,165467.66,165463.81,165471.5,41571.277,41570.355,41572.199,41623.371,41622.438,41624.305,166884.66,166292.78,167476.53 -3,1389.0746,1388.5024,1389.6467,5030.7954,5029.2437,5032.3472,9240.874,9240.2598,9241.4883,18025.227,18021.703,18028.75,21033.723,21033.025,21034.42,20312.977,20312.451,20313.502,171026.72,171023.88,171029.56,165234.98,165230.12,165239.84,41442.422,41288.453,41596.391,41581.973,41581.297,41582.648,167019.41,167017.95,167020.86 diff --git a/tests/workloads/kernel_verbose_2/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_2/MI200/sysinfo.csv deleted file mode 100644 index 1dc99903e3..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_2,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:47:08 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_2/MI200/timestamps.csv b/tests/workloads/kernel_verbose_2/MI200/timestamps.csv deleted file mode 100644 index a3b3e59c59..0000000000 --- a/tests/workloads/kernel_verbose_2/MI200/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,373046,373046,1048576,256,0,0,8,0,16,64,0x0,0x7f7786f54ec0,200174259795652,200174259821413,200174259842053,200174259872358 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,373046,373046,1048576,256,0,0,8,0,16,64,0x0,0x7f7786f54ec0,200174259852831,200174259860293,200174259876453,200174259944224 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,373046,373046,1048576,256,0,0,8,0,16,64,0x0,0x7f7786f54ec0,200174259886715,200174259950853,200174259967493,200174259968429 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 22da007d7d..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,206689,206689,1048576,256,0,0,8,8,16,64,0x0,0x7f43269ece80,48693,48693,16384,65536,14469,1865604,194384658278855,194396826197502,194396826221982,194384666142164 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,206689,206689,1048576,256,0,0,8,8,16,64,0x0,0x7f43269ece80,43316,43316,16384,65536,8204,1048580,194384666163785,194396826332862,194396826352062,194384666499089 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,206689,206689,1048576,256,0,0,8,8,16,64,0x0,0x7f43269ece80,42593,42593,16384,65536,8350,1048580,194384666531571,194396826372542,194396826391422,194384666714708 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index d50fe3815b..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,206876,206876,1048576,256,0,0,8,8,16,64,0x0,0x7f4d26388e80,0,0,0,194385153601799,194396826197502,194396826221982,194385161313521 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,206876,206876,1048576,256,0,0,8,8,16,64,0x0,0x7f4d26388e80,0,0,0,194385161331686,194396826332862,194396826352062,194385161649227 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,206876,206876,1048576,256,0,0,8,8,16,64,0x0,0x7f4d26388e80,0,0,0,194385161677080,194396826372542,194396826391422,194385161849085 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index 1dcdaa0866..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,207059,207059,1048576,256,0,0,8,8,16,64,0x0,0x7f511354ae80,65536,213020,27276184,194385643338427,194396826197502,194396826221982,194385650922807 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,207059,207059,1048576,256,0,0,8,8,16,64,0x0,0x7f511354ae80,65536,210858,27017696,194385650943867,194396826332862,194396826352062,194385651292708 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,207059,207059,1048576,256,0,0,8,8,16,64,0x0,0x7f511354ae80,65536,226888,29109624,194385651321101,194396826372542,194396826391422,194385651501673 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index 5a4ea2e87e..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,207248,207248,1048576,256,0,0,8,8,16,64,0x0,0x7f247b7bae80,32768,647852,82918112,194386133628101,194396826197502,194396826221982,194386141441194 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,207248,207248,1048576,256,0,0,8,8,16,64,0x0,0x7f247b7bae80,32768,686109,87810960,194386141462445,194396826332862,194396826352062,194386141756702 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,207248,207248,1048576,256,0,0,8,8,16,64,0x0,0x7f247b7bae80,32768,664689,85064412,194386141784915,194396826372542,194396826391422,194386141990585 diff --git a/tests/workloads/kernel_verbose_3/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_3/MI100/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 379e0427f9..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,207434,207434,1048576,256,0,0,8,8,16,64,0x0,0x7f839c740e80,48577,48577,18491,388624,16384,25209993,235570,0,101320804,194386624498284,194396826197502,194396826221982,194386632110978 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,207434,207434,1048576,256,0,0,8,8,16,64,0x0,0x7f839c740e80,43097,43097,14640,344784,16384,24236574,228131,0,97443576,194386632139723,194396826332862,194396826352062,194386632506297 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,207434,207434,1048576,256,0,0,8,8,16,64,0x0,0x7f839c740e80,42960,42960,14329,343688,16384,24452621,227388,0,98300612,194386632544118,194396826372542,194396826391422,194386632731563 diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index 202141726e..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6f289aa046..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_10.txt deleted file mode 100644 index a00555d953..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_11.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_12.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_13.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_14.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_15.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_16.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 2180ee3f63..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_3.txt deleted file mode 100644 index 8f1ba90d04..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_4.txt deleted file mode 100644 index 9a82481329..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_5.txt deleted file mode 100644 index bbc1f21123..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_6.txt deleted file mode 100644 index b6368182b4..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_7.txt deleted file mode 100644 index 3f7673fd23..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_8.txt deleted file mode 100644 index facba6bd95..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_9.txt deleted file mode 100644 index d458645ea4..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_3/MI100/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_3/MI100/pmc_dispatch_info.csv deleted file mode 100644 index 17300ae9af..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/pmc_dispatch_info.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_verbose_3/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_3/MI100/pmc_perf.csv deleted file mode 100644 index 46ed8fd8e0..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_2,obj_2,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_5,obj_5,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_7,obj_7,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_11,obj_11,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_12,obj_12,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_13,obj_13,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_14,obj_14,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5508d98e80,184843,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13902,30286,9861,550,0,46421,262634.0,0.0,188.0,262446.0,64,0x7fee2df36e80,0,0,192,0,65536,64388,48,1373,32476,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48425,1718,0,48.0,289.0,0.0,262288.0,64,0x7f0995892e80,0,8192,4096,8192,0,8192,4096,8192,0,8342,4246,8342,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8243,4288,8384,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f2ab255ae80,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,0,48564,0,0,64,0x7f6a7b45ae80,382896,228889,3349219,16384,24380469,144,48,0,47861,47861,3786114.0,2947353.0,5519.0,1093149.0,2075525.0,0.0,2938717.0,2629100.0,381247,238828,47861,0,47861,0,1531552.0,958923.0,0.0,0.0,64,0x7fa8a50a8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86606.0,44466.0,131111.0,0.0,64,0x7fa08cd16e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47392,0,131550.0,131072.0,0.0,131104.0,64,0x7fdea13e8e80,0.0,64,0x7fcbfe282e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131472.0,0.0,792.0,131471.0,64,0x7ffa6be20e80,3859,0,0,1970765,3681,0,0,1984118,635,0,0,1611375,2014,0,0,1821378,398,0,0,1584425,3624,0,0,2005190,1299,0,0,1833567,4055,0,0,2060337,665,0,0,1582695,2478,0,0,1864662,807,0,0,1667599,3815,0,0,2094149,2489,0,0,1906402,1409,0,0,1772055,1089,0,0,1701191,4564,0,0,2065336,2791,0,0,1882729,2506,0,0,1870477,1977,0,0,1823086,2831,0,0,1904967,1631,0,0,1835109,3821,0,0,2117574,1454,0,0,1839408,2889,0,0,1950532,2083,0,0,1752582,2025,0,0,1811453,862,0,0,1728671,5806,0,0,2079569,2394,0,0,1902911,2217,0,0,1867275,2716,0,0,1936833,3107,0,0,1974779,64,0x7fe7a4682e80,32768,0,0,0,16384,16384,393216,23217465,960.0,513989.0,0.0,524288.0,893109.0,32768.0,0,0,0,16632,131072.0,131072.0,0.0,131072.0,64,0x7f3ce5ea6e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdb47134e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,74795.0,141833.0,64,0x7f912f362e80,0,4913610,4096,4096,0,3440750,4096,4096,0,3451033,4096,4096,0,3012196,4096,4096,0,4179555,4096,4096,0,4184987,4096,4096,0,3449114,4096,4096,0,4180696,4096,4096,0,4473068,4096,4096,0,3697658,4096,4096,0,4624928,4096,4096,0,4341236,4096,4096,0,4524291,4096,4096,0,3774306,4096,4096,0,3834415,4096,4096,0,3054436,4096,4096,0,4849916,4096,4096,0,3854440,4096,4096,0,4273841,4096,4096,0,3044787,4096,4096,0,4315615,4096,4096,0,3094589,4096,4096,0,5124172,4096,4096,0,3359898,4096,4096,0,4669912,4096,4096,0,5241771,4096,4096,0,4064690,4096,4096,0,3095054,4096,4096,0,4829537,4096,4096,0,4142466,4096,4096,0,4488083,4096,4096,0,3337502,4096,4096,64,0x7f1809e16e80,4096,0,7400,0,4096,0,1410,0,4099,0,23,0,4096,0,0,0,4239,0,83,0,4096,0,6,0,4096,0,827,0,4096,0,46,0,4144,0,328,0,4096,0,3,0,4096,0,155,0,4144,0,22,0,4096,0,2165,0,4096,0,1222,0,4096,0,706,0,4096,0,0,0,4096,0,2845,0,4096,0,1753,0,4096,0,1452,0,4096,0,1725,0,4096,0,105,0,4097,0,4198,0,4096,0,112,0,4096,0,0,0,4096,0,16,0,4096,0,63,0,4096,0,923,0,4096,0,58,0,4096,0,248,0,4096,0,1470,0,4096,0,94,0,4096,0,282,0,64,0x7fb76b03ce80,2225524,360448,163840,0,0,180224,114688,0,70490386.0,198596091.0,76945764.0,131072.0,0.0,720519.0,0,0,26958,111489.0,0.0,0.0,111489.0,64,0x7fbc23f24e80,131072.0,131072.0,0.0,2573261.0,0.0,0.0,120200135.0,60407108.0,194396826197502,194396826221982 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5508d98e80,183073,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13917,30301,8550,2895,0,41199,262499.0,0.0,47.0,262452.0,64,0x7fee2df36e80,0,0,48,0,65536,65536,0,0,31295,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,456,42618,1751,0,48.0,289.0,0.0,262144.0,64,0x7f0995892e80,0,8192,4096,8192,0,8192,4096,8192,0,8353,4257,8353,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8242,4146,8242,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f2ab255ae80,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,0,43076,0,0,64,0x7f6a7b45ae80,398816,253525,3656449,16384,27608011,0,96,0,49851,49851,4093106.0,3142810.0,4779.0,1305387.0,2477227.0,0.0,3127820.0,2818002.0,398808,263315,49851,0,49851,1071,1595232.0,919010.0,1.0,0.0,64,0x7fa8a50a8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86992.0,0.0,131112.0,0.0,64,0x7fa08cd16e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5672,44419,1069,131878.0,131072.0,0.0,100886.0,64,0x7fdea13e8e80,0.0,64,0x7fcbfe282e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131413.0,0.0,680.0,131412.0,64,0x7ffa6be20e80,2393,0,0,1505669,1806,0,0,1382894,1480,0,0,1315597,782,0,0,1244727,905,0,0,1407983,987,0,0,1401679,1650,0,0,1416579,1957,0,0,1476147,1009,0,0,1362920,377,0,0,1216413,561,0,0,1284898,842,0,0,1358815,3596,0,0,1644906,743,0,0,1285517,460,0,0,1359592,419,0,0,1245569,3764,0,0,1641410,1376,0,0,1384620,2651,0,0,1686642,392,0,0,1280907,4974,0,0,1786735,2025,0,0,1489720,2750,0,0,1600983,702,0,0,1252677,1987,0,0,1452574,1240,0,0,1387814,541,0,0,1328206,2416,0,0,1517465,1641,0,0,1328849,5124,0,0,1757667,1966,0,0,1508761,854,0,0,1398100,64,0x7fe7a4682e80,32768,0,0,0,16384,16384,393216,23214843,960.0,513820.0,0.0,524288.0,1000532.0,32768.0,0,0,0,15843,86661.0,86661.0,0.0,86661.0,64,0x7f3ce5ea6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdb47134e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,63379.0,129485.0,64,0x7f912f362e80,0,5406074,2746,2746,0,4542210,2692,2692,0,4168543,2694,2694,0,2979635,2700,2700,0,4522300,2700,2700,0,3781123,2690,2690,0,4354132,2729,2729,0,4131338,2698,2698,0,4771312,2716,2716,0,4308948,2648,2648,0,3778388,2722,2722,0,4860900,2716,2716,0,4453289,2717,2717,0,4258046,2652,2652,0,4826419,2721,2721,0,3514255,2672,2672,0,5138906,2701,2701,0,4451913,2691,2691,0,4874714,2724,2724,0,3103815,2698,2698,0,3478356,2708,2708,0,4425368,2716,2716,0,4300990,2706,2706,0,2892985,2694,2694,0,4234505,2712,2712,0,3932490,2672,2672,0,3494117,2758,2758,0,3322920,2699,2699,0,3706708,2732,2732,0,4753931,2666,2666,0,4796012,2732,2732,0,3421325,2684,2684,64,0x7f1809e16e80,4096,0,625,0,4096,0,1196,0,4096,0,472,0,4096,0,74,0,4356,0,1728,0,4096,0,1568,0,4096,0,664,0,4096,0,1448,0,4144,0,486,0,4096,0,134,0,4096,0,1845,0,4144,0,1242,0,4096,0,364,0,4097,0,3648,0,4096,0,5968,0,4096,0,815,0,4096,0,4108,0,4096,0,1970,0,4096,0,3011,0,4098,0,3166,0,4096,0,0,0,4097,0,2829,0,4096,0,4357,0,4096,0,131,0,4096,0,0,0,4096,0,2286,0,4096,0,552,0,4096,0,56,0,4096,0,457,0,4096,0,697,0,4096,0,1411,0,4097,0,6440,0,64,0x7fb76b03ce80,1295324,360448,163840,0,0,180224,114688,0,70428307.0,199281393.0,78745788.0,131072.0,0.0,770740.0,0,0,25457,111815.0,0.0,0.0,111815.0,64,0x7fbc23f24e80,131072.0,131072.0,0.0,2595896.0,0.0,0.0,124626523.0,46691436.0,194396826332862,194396826352062 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f5508d98e80,183878,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12351,28735,8605,2881,0,41218,262475.0,0.0,47.0,262428.0,64,0x7fee2df36e80,0,0,48,0,65536,65536,0,0,31164,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42753,1756,0,48.0,300.0,0.0,262144.0,64,0x7f0995892e80,0,8192,4096,8192,0,8192,4096,8192,0,8350,4254,8350,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8242,4146,8242,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f2ab255ae80,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,0,43151,0,0,64,0x7f6a7b45ae80,344368,234389,3406775,16384,25110806,0,48,0,43045,43045,3805602.0,3051655.0,4688.0,1229012.0,2233630.0,0.0,3042247.0,2733003.0,344360,243917,43045,0,43045,0,1377440.0,836248.0,0.0,0.0,64,0x7fa8a50a8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86562.0,0.0,131112.0,0.0,64,0x7fa08cd16e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2728,39753,0,131401.0,131072.0,0.0,86539.0,64,0x7fdea13e8e80,0.0,64,0x7fcbfe282e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131403.0,0.0,660.0,131402.0,64,0x7ffa6be20e80,2698,0,0,1508527,2706,0,0,1594950,822,0,0,1253756,895,0,0,1383191,1011,0,0,1347161,1423,0,0,1436486,1020,0,0,1364229,1415,0,0,1465863,1106,0,0,1372123,3346,0,0,1630053,354,0,0,1304213,1716,0,0,1489722,757,0,0,1329802,1964,0,0,1560150,561,0,0,1310838,1843,0,0,1508879,1073,0,0,1355347,1662,0,0,1426961,1078,0,0,1409297,1997,0,0,1542878,1917,0,0,1497069,2521,0,0,1592084,1840,0,0,1479610,3168,0,0,1616809,1055,0,0,1348494,2948,0,0,1548195,955,0,0,1365520,6642,0,0,1835795,2289,0,0,1519329,4078,0,0,1764730,4556,0,0,1707012,1048,0,0,1385439,64,0x7fe7a4682e80,32768,0,0,0,16384,16384,393216,22648440,960.0,514059.0,0.0,524288.0,910739.0,32768.0,0,0,0,13564,86249.0,86249.0,0.0,86249.0,64,0x7f3ce5ea6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fdb47134e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,64357.0,131446.0,64,0x7f912f362e80,0,4265051,2690,2690,0,3724900,2696,2696,0,4508775,2666,2666,0,3672269,2708,2708,0,3602539,2674,2674,0,4585509,2730,2730,0,3151448,2721,2721,0,4269878,2722,2722,0,3625060,2672,2672,0,4042630,2700,2700,0,3316608,2720,2720,0,4887594,2756,2756,0,3687904,2699,2699,0,4909789,2674,2674,0,5105095,2695,2695,0,4227334,2735,2735,0,3486620,2688,2688,0,4915692,2679,2679,0,3211476,2674,2674,0,4602044,2720,2720,0,3119021,2704,2704,0,3942482,2732,2732,0,3486389,2690,2690,0,2989916,2723,2723,0,2423470,2668,2668,0,4494094,2708,2708,0,3270528,2736,2736,0,3977918,2724,2724,0,3392450,2690,2690,0,4695773,2689,2689,0,2931919,2696,2696,0,4837499,2718,2718,64,0x7f1809e16e80,4096,0,0,0,4096,0,1036,0,4096,0,2049,0,4096,0,653,0,4336,0,1607,0,4096,0,1463,0,4096,0,0,0,4096,0,1536,0,4144,0,992,0,4096,0,1989,0,4096,0,26,0,4144,0,1530,0,4096,0,0,0,4097,0,965,0,4096,0,60,0,4096,0,111,0,4096,0,786,0,4096,0,7893,0,4096,0,910,0,4098,0,860,0,4096,0,355,0,4097,0,253,0,4096,0,0,0,4096,0,480,0,4096,0,196,0,4096,0,503,0,4096,0,805,0,4096,0,1575,0,4096,0,1282,0,4096,0,0,0,4096,0,5637,0,4097,0,979,0,64,0x7fb76b03ce80,1391842,360448,163840,0,0,180224,114688,0,70516697.0,203434105.0,79228043.0,131072.0,0.0,748918.0,0,0,25591,130010.0,0.0,0.0,130010.0,64,0x7fbc23f24e80,131072.0,131072.0,0.0,2574918.0,0.0,0.0,119544141.0,45104787.0,194396826372542,194396826391422 diff --git a/tests/workloads/kernel_verbose_3/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_3/MI100/sysinfo.csv deleted file mode 100644 index 15114cd207..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_3,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:10:49 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_3/MI100/timestamps.csv b/tests/workloads/kernel_verbose_3/MI100/timestamps.csv deleted file mode 100644 index 43443b4bff..0000000000 --- a/tests/workloads/kernel_verbose_3/MI100/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,210790,210790,1048576,256,0,0,8,8,16,64,0x0,0x7f8894d18e80,194396826171795,194396826197502,194396826221982,194396826235726 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,210790,210790,1048576,256,0,0,8,8,16,64,0x0,0x7f8894d18e80,194396826234664,194396826332862,194396826352062,194396826353259 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,210790,210790,1048576,256,0,0,8,8,16,64,0x0,0x7f8894d18e80,194396826363709,194396826372542,194396826391422,194396826392423 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index fa09789595..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,374560,374560,1048576,256,0,0,8,0,16,64,0x0,0x7f1c198c8ec0,27304,27304,16384,65536,13690,1541648,200364037453801,200376896683431,200376896703751,200364053586099 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,374560,374560,1048576,256,0,0,8,0,16,64,0x0,0x7f1c198c8ec0,40592,40592,16384,65536,9067,1048664,200364053606127,200376896785031,200376896801511,200364053915061 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,374560,374560,1048576,256,0,0,8,0,16,64,0x0,0x7f1c198c8ec0,40381,40381,16384,65536,9390,1048628,200364053944887,200376896822791,200376896838791,200364054105652 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index cce6baf3d9..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,374762,374762,1048576,256,0,0,8,0,16,64,0x0,0x7f85d0858ec0,0,0,0,200364529244124,200376896683431,200376896703751,200364545052319 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,374762,374762,1048576,256,0,0,8,0,16,64,0x0,0x7f85d0858ec0,0,0,0,200364545078108,200376896785031,200376896801511,200364545315327 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,374762,374762,1048576,256,0,0,8,0,16,64,0x0,0x7f85d0858ec0,0,0,0,200364545342398,200376896822791,200376896838791,200364545475360 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index 058adf7b52..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,374963,374963,1048576,256,0,0,8,0,16,64,0x0,0x7f343fc74ec0,65536,173402,19359720,200365011775202,200376896683431,200376896703751,200365027932057 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,374963,374963,1048576,256,0,0,8,0,16,64,0x0,0x7f343fc74ec0,65536,233884,26199952,200365027949490,200376896785031,200376896801511,200365028257833 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,374963,374963,1048576,256,0,0,8,0,16,64,0x0,0x7f343fc74ec0,65536,226524,25416944,200365028281277,200376896822791,200376896838791,200365028549555 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index 7e25b6a6ed..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,375161,375161,1048576,256,0,0,8,0,16,64,0x0,0x7f6600634ec0,32768,293599,32874012,200365501049676,200376896683431,200376896703751,200365517396009 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,375161,375161,1048576,256,0,0,8,0,16,64,0x0,0x7f6600634ec0,32768,575330,64446764,200365517417340,200376896785031,200376896801511,200365517640813 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,375161,375161,1048576,256,0,0,8,0,16,64,0x0,0x7f6600634ec0,32768,592307,66327576,200365517667002,200376896822791,200376896838791,200365517816915 diff --git a/tests/workloads/kernel_verbose_3/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_3/MI200/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 2d0dae3cd2..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,375347,375347,1048576,256,0,0,8,0,16,64,0x0,0x7f0457b50ec0,27804,27804,11190,222440,16384,10815372,129006,0,43764752,200365991059341,200376896683431,200376896703751,200366006804217 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,375347,375347,1048576,256,0,0,8,0,16,64,0x0,0x7f0457b50ec0,41475,41475,13865,331808,16384,19384380,223221,0,78032800,200366006832841,200376896785031,200376896801511,200366007074167 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,375347,375347,1048576,256,0,0,8,0,16,64,0x0,0x7f0457b50ec0,41252,41252,13554,330024,16384,19142382,223336,0,77058516,200366007109434,200376896822791,200376896838791,200366007260570 diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_0.txt deleted file mode 100644 index 4ffdc32149..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6c277f4a37..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_10.txt deleted file mode 100644 index 7053d4dce6..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_11.txt deleted file mode 100644 index 77ae8b461f..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_12.txt deleted file mode 100644 index dfb2cf65e5..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_13.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_14.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_15.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_16.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_17.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_17.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_18.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_18.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_2.txt deleted file mode 100644 index 70b69f8928..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_3.txt deleted file mode 100644 index e47f8e33c9..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_4.txt deleted file mode 100644 index 2d96f365a9..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_5.txt deleted file mode 100644 index e50beed390..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_6.txt deleted file mode 100644 index 15a2277c1b..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_7.txt deleted file mode 100644 index b42ce91618..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_8.txt deleted file mode 100644 index 21d4c7a998..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_9.txt deleted file mode 100644 index 9ffe5778c3..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_3/MI200/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_3/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_3/MI200/pmc_perf.csv deleted file mode 100644 index 7c9af10527..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_1,obj_1,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_2,obj_2,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_3,obj_3,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_5,obj_5,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_6,obj_6,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_7,obj_7,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_9,obj_9,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_12,obj_12,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_13,obj_13,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_14,obj_14,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_17,obj_17,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_18,obj_18,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce36be8ec0,0,0,0,998532,11,0,0,1083440,0,0,0,980959,0,0,0,1030903,0,0,0,981390,0,0,0,1069686,0,0,0,1131769,0,0,0,1232356,0,0,0,1062747,0,0,0,1038058,0,0,0,1031835,0,0,0,1076817,0,0,0,1114690,0,0,0,1047006,0,0,0,1004792,0,0,0,1267535,0,0,0,1151763,0,0,0,1049694,0,0,0,992650,0,0,0,1084352,0,0,0,1062905,0,0,0,1080186,0,0,0,1067162,0,0,0,1109373,0,0,0,1033119,0,0,0,1094220,0,0,0,1044460,0,0,0,1100322,0,0,0,1071074,0,0,0,1056893,0,0,0,1127537,0,0,0,1109825,64,0x7fcb418e4ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,929430.0,64,0x7ff515f48ec0,231824,128092,16384,0,16384,16384,32768,49152,28977,28977,1943011.0,1334488.0,3205.0,166634.0,1043391.0,0.0,1326526.0,1027716.0,230113,136232,28977,0,28977,0,927264.0,483272.0,0.0,0.0,64,0x7f9f4b678ec0,0,393216,163840,0,0,0,0,0,17627,0.0,0.0,0.0,32768.0,0.0,0.0,428.0,32768.0,4096,16384,352,27627,1918,0,56.0,5.0,0.0,204806.0,64,0x7f24b44c4ec0,0,1321973,4096,4096,0,1354767,4096,4096,0,1222472,4096,4096,0,1273722,4096,4096,0,1223330,4096,4096,0,1437590,4096,4096,0,1053340,4096,4096,0,1197753,4096,4096,0,1110670,4096,4096,0,1201277,4096,4096,0,1283526,4096,4096,0,1159739,4096,4096,0,1071589,4096,4096,0,1339830,4096,4096,0,1619403,4096,4096,0,1277254,4096,4096,0,1217212,4096,4096,0,1202885,4096,4096,0,1131247,4096,4096,0,1569896,4096,4096,0,1065897,4096,4096,0,1068306,4096,4096,0,1195134,4096,4096,0,1260756,4096,4096,0,1582680,4096,4096,0,1030715,4096,4096,0,1073841,4096,4096,0,1140133,4096,4096,0,1528379,4096,4096,0,1118522,4096,4096,0,1189188,4096,4096,0,1318239,4096,4096,64,0x7f93502f4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,38788672.0,34533107.0,0.0,64,0x7fc9a0414ec0,114688,0,32768,32768,16384,16384,65536,49152,27474486.0,85701973.0,38726495.0,131072.0,0.0,193774.0,0,0,14978,504.0,131082.0,0.0,12.0,64,0x7f84c28d0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10365,0,816,27840,0,73095.0,131072.0,0.0,65568.0,64,0x7f78b2f18ec0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,0,28493,0,0,64,0x7f61d8d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12228,18953,8358,545,0,26802,204457.0,0.0,73375.0,131082.0,64,0x7fcb203c4ec0,0,0,0,224,0,65536,64151,56,64,0x7f8639bc4ec0,32768,32768,0,64,0x7f80789d4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,34813.0,46193.0,19343.0,64,0x7fa505dc4ec0,6369,0,4096,6358,0,4096,6369,0,4096,6400,0,4096,6386,0,4096,6372,0,4096,6356,0,4096,6413,0,4096,6421,0,4096,6370,0,4096,6362,0,4096,6370,0,4096,6404,0,4096,6388,0,4096,6374,0,4096,6358,0,4096,6373,0,4096,6418,0,4096,6367,0,4096,6358,0,4096,6389,0,4096,6394,0,4096,6331,0,4096,6509,0,4096,6345,0,4096,6372,0,4096,6416,0,4096,6366,0,4096,6359,0,4096,6389,0,4096,6396,0,4096,6332,0,4096,64,0x7f4979c7cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fd080e6cec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,50,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4097,0,0,0,4096,0,155,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f2f1f530ec0,11133304,9932039,857201,344064,1687571,0,0,163840,832.0,515140.0,0.0,524288.0,304714.0,32768.0,526086,0,0,11138,131072.0,131072.0,0.0,131072.0,64,0x7f40880acec0,1281,118966,0,0,65536,63800,56,1680,64,0x7fb6d0d44ec0,2298,4096,2298,6394,2295,4096,2295,6391,2333,4096,2333,6429,2304,4096,2304,6400,2292,4096,2292,6388,2362,4097,2363,6459,2288,4096,2288,6384,2309,4096,2309,6405,2307,4097,2308,6404,2300,4098,2302,6398,2298,4096,2298,6394,2338,4096,2338,6434,2308,4096,2308,6404,2292,4096,2292,6388,2310,4096,2310,6406,2290,4096,2290,6386,2288,4096,2288,6384,2308,4096,2308,6404,2292,4097,2293,6389,2300,4096,2300,6396,2306,4096,2306,6402,2354,4096,2354,6450,2274,4096,2274,6370,2463,4098,2465,6561,2299,4096,2299,6395,2288,4096,2288,6384,2308,4096,2308,6404,2295,4100,2299,6395,2306,4096,2306,6402,2310,4096,2310,6406,2358,4096,2358,6454,2276,4096,2276,6372,200376896683431,200376896703751 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce36be8ec0,1594,0,0,2720147,6,0,0,1869554,237,0,0,1993496,0,0,0,1923184,601,0,0,2130150,62,0,0,2018399,180,0,0,2134327,1167,0,0,2607349,2370,0,0,2542742,1381,0,0,1945373,1665,0,0,2542687,0,0,0,1535629,118,0,0,1941027,523,0,0,1974983,904,0,0,2531651,1115,0,0,2303815,2643,0,0,2702774,2608,0,0,2804743,157,0,0,1890348,0,0,0,1868577,0,0,0,1933870,221,0,0,2107803,0,0,0,1925904,0,0,0,2005264,0,0,0,1762695,2472,0,0,2491189,1386,0,0,2448452,0,0,0,1781075,0,0,0,1755621,62,0,0,1883518,56,0,0,1937660,670,0,0,2204976,64,0x7fcb418e4ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,1998111.0,64,0x7ff515f48ec0,329808,225588,16384,0,16384,16384,32768,49152,41225,41225,3209855.0,2470951.0,4763.0,361257.0,1643901.0,0.0,2459264.0,2150854.0,329800,234863,41225,0,41225,0,1319200.0,777557.0,0.0,0.0,64,0x7f9f4b678ec0,0,393216,163840,0,0,0,0,0,29613,0.0,0.0,0.0,32768.0,0.0,0.0,217.0,32768.0,4096,16384,302,40382,2073,0,56.0,9.0,0.0,200277.0,64,0x7f24b44c4ec0,0,3240352,2850,2850,0,3441033,2884,2884,0,3087288,2838,2838,0,3257695,2852,2852,0,4152851,2874,2874,0,4848014,2832,2832,0,3204429,2852,2852,0,3818273,2784,2784,0,3596741,2788,2788,0,4094721,2844,2844,0,2945150,2884,2884,0,3452935,2836,2836,0,3713736,2852,2852,0,4089463,2882,2882,0,4253109,2832,2832,0,3604687,2848,2848,0,4138665,2800,2800,0,4278658,2826,2826,0,3603473,2876,2876,0,3381891,2860,2860,0,3251591,2830,2830,0,3972817,2900,2900,0,4679674,2828,2828,0,4935258,2844,2844,0,4008260,2834,2834,0,3531928,2800,2800,0,3859378,2828,2828,0,4058627,2876,2876,0,3551846,2864,2864,0,3250186,2832,2832,0,3282636,2898,2898,0,4206694,2828,2828,64,0x7f93502f4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,123589825.0,59871763.0,0.0,64,0x7fc9a0414ec0,114688,0,32768,32768,16384,16384,65536,49152,60639735.0,206253529.0,51932166.0,131072.0,0.0,519385.0,0,0,25870,3094.0,131083.0,0.0,20.0,64,0x7f84c28d0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,15863,0,819,36741,0,69975.0,131072.0,0.0,45566.0,64,0x7f78b2f18ec0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,0,42285,0,0,64,0x7f61d8d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29844,27018,9579,2859,0,39240,200584.0,0.0,69498.0,131086.0,64,0x7fcb203c4ec0,0,0,0,56,0,65536,65536,0,64,0x7f8639bc4ec0,32768,32768,0,64,0x7f80789d4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,126632.0,45557.0,0.0,64,0x7fa505dc4ec0,6270,0,4096,6263,0,4096,6266,0,4096,6267,0,4096,6241,0,4096,6241,0,4096,6285,0,4096,6293,0,4096,6292,0,4096,6271,0,4096,6260,0,4096,6265,0,4096,6259,0,4096,6240,0,4096,6243,0,4096,6286,0,4096,6255,0,4096,6294,0,4096,6272,0,4096,6273,0,4096,6235,0,4096,6237,0,4096,6227,0,4096,6242,0,4096,6244,0,4096,6259,0,4096,6297,0,4096,6279,0,4096,6276,0,4096,6231,0,4096,6241,0,4096,6231,0,4096,64,0x7f4979c7cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fd080e6cec0,4097,0,83,0,4096,0,263,0,4096,0,0,0,4096,0,440,0,4096,0,623,0,4096,0,523,0,4096,0,691,0,4096,0,1236,0,4096,0,25,0,4096,0,2,0,4096,0,272,0,4096,0,3,0,4097,0,2,0,4096,0,94,0,4096,0,442,0,4097,0,113,0,4097,0,60,0,4096,0,174,0,4097,0,362,0,4096,0,118,0,4096,0,0,0,4096,0,496,0,4096,0,1319,0,4096,0,954,0,4096,0,72,0,4096,0,33,0,4099,0,229,0,4098,0,1484,0,4096,0,414,0,4096,0,105,0,4096,0,15,0,4096,0,199,0,64,0x7f2f1f530ec0,19169341,17753380,1071897,344064,2768728,0,0,163840,832.0,515136.0,0.0,524288.0,658206.0,32768.0,978464,0,0,13248,91430.0,91430.0,0.0,91430.0,64,0x7f40880acec0,0,183022,0,0,65536,63800,56,1680,64,0x7fb6d0d44ec0,2203,4096,2203,6299,2180,4096,2180,6276,2183,4096,2183,6279,2160,4096,2160,6256,2178,4096,2178,6274,2203,4097,2204,6300,2148,4096,2148,6244,2158,4096,2158,6254,2163,4097,2164,6260,2207,4097,2208,6304,2183,4096,2183,6279,2183,4096,2183,6279,2162,4096,2162,6258,2186,4096,2186,6282,2146,4096,2146,6242,2146,4097,2147,6243,2154,4096,2154,6250,2177,4096,2177,6273,2198,4097,2199,6295,2164,4096,2164,6260,2171,4096,2171,6267,2178,4096,2178,6274,2168,4096,2168,6264,2169,4096,2169,6265,2170,4096,2170,6266,2154,4096,2154,6250,2175,4096,2175,6271,2199,4100,2203,6299,2169,4100,2173,6269,2174,4096,2174,6270,2182,4096,2182,6278,2172,4096,2172,6268,200376896785031,200376896801511 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fce36be8ec0,406,0,0,2297015,95,0,0,1670061,0,0,0,1301013,631,0,0,2222911,0,0,0,1707719,75,0,0,2098806,0,0,0,1563213,665,0,0,2343553,0,0,0,1796945,148,0,0,2086040,0,0,0,1588797,23,0,0,1650979,188,0,0,1802622,570,0,0,1982464,2294,0,0,2585035,0,0,0,1776048,0,0,0,1648207,69,0,0,1905642,0,0,0,1750580,652,0,0,2373172,156,0,0,1930432,151,0,0,1780438,0,0,0,1728190,185,0,0,1786324,0,0,0,1554550,0,0,0,1542435,0,0,0,1682837,109,0,0,2210172,936,0,0,2359037,0,0,0,1611581,147,0,0,1812175,0,0,0,1638739,64,0x7fcb418e4ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2136956.0,64,0x7ff515f48ec0,344104,228695,16384,0,16384,16384,32768,49152,43012,43012,3248159.0,2501995.0,4888.0,380369.0,1671249.0,0.0,2491439.0,2184921.0,344096,237615,43012,0,43012,0,1376384.0,790746.0,0.0,0.0,64,0x7f9f4b678ec0,0,393216,163840,0,0,0,0,0,29670,0.0,0.0,0.0,32768.0,0.0,0.0,201.0,32768.0,4096,16384,302,41194,2052,0,56.0,11.0,0.0,201187.0,64,0x7f24b44c4ec0,0,2742633,2856,2856,0,3972046,2888,2888,0,3535771,2840,2840,0,3286446,2836,2836,0,3821916,2852,2852,0,4493425,2820,2820,0,4766883,2868,2868,0,3348808,2804,2804,0,2888609,2804,2804,0,3156405,2854,2854,0,3263170,2888,2888,0,3213062,2844,2844,0,3120700,2832,2832,0,3015277,2850,2850,0,4277960,2824,2824,0,4497900,2860,2860,0,3320978,2812,2812,0,5182465,2844,2844,0,3174972,2858,2858,0,3891725,2888,2888,0,3917166,2820,2820,0,4111423,2860,2860,0,4032120,2796,2796,0,3940525,2808,2808,0,3999693,2810,2810,0,2612443,2812,2812,0,4054957,2852,2852,0,4818374,2866,2866,0,3208529,2888,2888,0,3146986,2824,2824,0,2777054,2864,2864,0,3700566,2796,2796,64,0x7f93502f4ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,123389948.0,62176176.0,0.0,64,0x7fc9a0414ec0,114688,0,32768,32768,16384,16384,65536,49152,58076389.0,202073232.0,49908871.0,131072.0,0.0,489706.0,0,0,26137,3855.0,131085.0,0.0,24.0,64,0x7f84c28d0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20354,0,3698,37941,0,69436.0,131072.0,0.0,45839.0,64,0x7f78b2f18ec0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,0,41837,0,0,64,0x7f61d8d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30337,27048,9628,2838,0,39591,201175.0,0.0,70088.0,131087.0,64,0x7fcb203c4ec0,0,0,0,56,0,65536,65536,0,64,0x7f8639bc4ec0,32768,32768,0,64,0x7f80789d4ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131083.0,94218.0,45624.0,0.0,64,0x7fa505dc4ec0,6281,0,4096,6255,0,4096,6273,0,4096,6314,0,4096,6242,0,4096,6289,0,4096,6299,0,4096,6308,0,4096,6312,0,4096,6284,0,4096,6261,0,4096,6271,0,4096,6319,0,4096,6243,0,4096,6290,0,4096,6303,0,4096,6285,0,4096,6315,0,4096,6252,0,4096,6246,0,4096,6231,0,4096,6271,0,4096,6275,0,4096,6292,0,4096,6293,0,4096,6288,0,4096,6319,0,4096,6254,0,4096,6250,0,4096,6230,0,4096,6273,0,4096,6281,0,4096,64,0x7f4979c7cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7fd080e6cec0,4097,0,3,0,4096,0,568,0,4096,0,0,0,4096,0,511,0,4096,0,93,0,4096,0,261,0,4096,0,0,0,4096,0,3012,0,4096,0,379,0,4096,0,167,0,4096,0,3046,0,4096,0,0,0,4097,0,124,0,4096,0,0,0,4096,0,0,0,4097,0,20,0,4097,0,0,0,4096,0,405,0,4097,0,1096,0,4096,0,381,0,4096,0,29,0,4096,0,386,0,4096,0,400,0,4096,0,370,0,4096,0,0,0,4096,0,183,0,4099,0,8,0,4098,0,28,0,4096,0,79,0,4096,0,1,0,4096,0,109,0,4096,0,0,0,64,0x7f2f1f530ec0,19307708,18022335,941309,344064,2770543,0,0,163840,832.0,515146.0,0.0,524288.0,598275.0,32768.0,949488,0,0,13517,91076.0,91076.0,0.0,91076.0,64,0x7f40880acec0,0,187732,0,0,65536,63800,56,1680,64,0x7fb6d0d44ec0,2146,4096,2146,6242,2188,4096,2188,6284,2186,4096,2186,6282,2194,4096,2194,6290,2182,4096,2182,6278,2275,4097,2276,6372,2161,4096,2161,6257,2163,4096,2163,6259,2166,4097,2167,6263,2154,4097,2155,6251,2190,4096,2190,6286,2189,4096,2189,6285,2202,4096,2202,6298,2181,4096,2181,6277,2218,4096,2218,6314,2165,4097,2166,6262,2145,4096,2145,6241,2162,4096,2162,6258,2170,4097,2171,6267,2166,4096,2166,6262,2179,4096,2179,6275,2147,4096,2147,6243,2188,4096,2188,6284,2199,4096,2199,6295,2201,4096,2201,6297,2145,4096,2145,6241,2160,4096,2160,6256,2171,4100,2175,6271,2165,4100,2169,6265,2183,4096,2183,6279,2141,4096,2141,6237,2188,4096,2188,6284,200376896822791,200376896838791 diff --git a/tests/workloads/kernel_verbose_3/MI200/roofline.csv b/tests/workloads/kernel_verbose_3/MI200/roofline.csv deleted file mode 100644 index d96ac5199a..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/roofline.csv +++ /dev/null @@ -1,5 +0,0 @@ -device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.2186,1388.6204,1389.8169,5014.8477,5012.125,5017.5703,9223.8896,9223.1982,9224.5811,18054.182,18053.324,18055.039,20932.783,20872.1,20993.467,20264.432,20263.896,20264.967,170434.23,170429.53,170438.94,164877.72,164872.09,164883.34,41421.809,41421.203,41422.414,41479.105,41478.355,41479.855,166340.17,165847.98,166832.36 -1,1388.9524,1388.3408,1389.564,5027.9482,5025.8726,5030.0239,9234.459,9233.7734,9235.1445,18096.832,18092.123,18101.541,20974.258,20907.176,21041.34,20296.25,20295.471,20297.029,170864.36,170860.03,170868.69,165130.7,165125.72,165135.69,41484.047,41483.246,41484.848,41542.871,41542.039,41543.703,166875.55,166871.89,166879.2 -2,1388.8219,1388.2272,1389.4166,5035.7168,5033.1938,5038.2397,9258.5625,9257.7793,9259.3457,18103.361,18102.363,18104.359,21047.307,21046.99,21047.623,20352.283,20351.742,20352.824,171108.28,171103.72,171112.84,165483.47,165479.25,165487.69,41580.016,41578.984,41581.047,41635.012,41633.902,41636.121,166941.19,166348.92,167533.45 -3,1388.7208,1388.1876,1389.254,5029.9995,5028.6465,5031.3525,9240.0186,9239.4795,9240.5576,18025.795,18021.91,18029.68,21037.256,21036.809,21037.703,20314.672,20313.996,20315.348,171029.14,171026.12,171032.16,165241.84,165237.61,165246.08,41442.031,41285.902,41598.16,41584.781,41584.109,41585.453,167033.36,167030.98,167035.73 diff --git a/tests/workloads/kernel_verbose_3/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_3/MI200/sysinfo.csv deleted file mode 100644 index 2928a953ab..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_3,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:50:31 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_3/MI200/timestamps.csv b/tests/workloads/kernel_verbose_3/MI200/timestamps.csv deleted file mode 100644 index 4dd7623cbd..0000000000 --- a/tests/workloads/kernel_verbose_3/MI200/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,379175,379175,1048576,256,0,0,8,0,16,64,0x0,0x7fcd42dc8ec0,200376896658571,200376896683431,200376896703751,200376896714156 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,379175,379175,1048576,256,0,0,8,0,16,64,0x0,0x7fcd42dc8ec0,200376896714967,200376896785031,200376896801511,200376896803044 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,379175,379175,1048576,256,0,0,8,0,16,64,0x0,0x7fcd42dc8ec0,200376896812813,200376896822791,200376896838791,200376896840334 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 3ce8a7e3da..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,184787,184787,1048576,256,0,0,8,8,16,64,0x0,0x7f0b431aee80,48173,48173,16384,65536,14172,1840588,194313898560911,194326078140081,194326078163761,194313907696729 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,184787,184787,1048576,256,0,0,8,8,16,64,0x0,0x7f0b431aee80,42332,42332,16384,65536,8060,1048584,194313907719873,194326078246321,194326078266001,194313908055629 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,184787,184787,1048576,256,0,0,8,8,16,64,0x0,0x7f0b431aee80,42228,42228,16384,65536,8122,1048616,194313908088972,194326078286481,194326078305361,194313908306815 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 3e1fc6931e..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,184970,184970,1048576,256,0,0,8,8,16,64,0x0,0x7fde3b9bae80,0,0,0,194314397849244,194326078140081,194326078163761,194314405577707 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,184970,184970,1048576,256,0,0,8,8,16,64,0x0,0x7fde3b9bae80,0,0,0,194314405595651,194326078246321,194326078266001,194314405914695 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,184970,184970,1048576,256,0,0,8,8,16,64,0x0,0x7fde3b9bae80,0,0,0,194314405942998,194326078286481,194326078305361,194314406126466 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index 75b8202d77..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,185153,185153,1048576,256,0,0,8,8,16,64,0x0,0x7f8d97dd4e80,65536,219396,28112080,194314890482225,194326078140081,194326078163761,194314898156525 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,185153,185153,1048576,256,0,0,8,8,16,64,0x0,0x7f8d97dd4e80,65536,180206,23016480,194314898175772,194326078246321,194326078266001,194314898472644 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,185153,185153,1048576,256,0,0,8,8,16,64,0x0,0x7f8d97dd4e80,65536,189732,24288608,194314898500978,194326078286481,194326078305361,194314898675158 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index 3e8714f73f..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,185338,185338,1048576,256,0,0,8,8,16,64,0x0,0x7f83005d4e80,32768,653995,83708432,194315383386910,194326078140081,194326078163761,194315391168805 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,185338,185338,1048576,256,0,0,8,8,16,64,0x0,0x7f83005d4e80,32768,665869,85235244,194315391190145,194326078246321,194326078266001,194315391477589 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,185338,185338,1048576,256,0,0,8,8,16,64,0x0,0x7f83005d4e80,32768,664826,85079520,194315391505763,194326078286481,194326078305361,194315391737011 diff --git a/tests/workloads/kernel_verbose_4/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_4/MI100/SQ_LEVEL_WAVES.csv deleted file mode 100644 index b0b07c114f..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,185524,185524,1048576,256,0,0,8,8,16,64,0x0,0x7fc1be638e80,48328,48328,17216,386632,16384,25447382,235315,0,102274300,194315877642313,194326078140081,194326078163761,194315886401849 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,185524,185524,1048576,256,0,0,8,8,16,64,0x0,0x7fc1be638e80,43255,43255,13566,346048,16384,25165439,234630,0,101170844,194315886432357,194326078246321,194326078266001,194315886856550 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,185524,185524,1048576,256,0,0,8,8,16,64,0x0,0x7fc1be638e80,42703,42703,13505,341632,16384,24776662,229753,0,99603288,194315886895834,194326078286481,194326078305361,194315887116442 diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index 202141726e..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6f289aa046..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_10.txt deleted file mode 100644 index a00555d953..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_11.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_12.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_13.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_14.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_15.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_16.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 2180ee3f63..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_3.txt deleted file mode 100644 index 8f1ba90d04..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_4.txt deleted file mode 100644 index 9a82481329..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_5.txt deleted file mode 100644 index bbc1f21123..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_6.txt deleted file mode 100644 index b6368182b4..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_7.txt deleted file mode 100644 index 3f7673fd23..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_8.txt deleted file mode 100644 index facba6bd95..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_9.txt deleted file mode 100644 index d458645ea4..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_4/MI100/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI100/pmc_dispatch_info.csv b/tests/workloads/kernel_verbose_4/MI100/pmc_dispatch_info.csv deleted file mode 100644 index 17300ae9af..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/pmc_dispatch_info.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 diff --git a/tests/workloads/kernel_verbose_4/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_4/MI100/pmc_perf.csv deleted file mode 100644 index bec4692c88..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_1,obj_1,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_2,obj_2,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_4,obj_4,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_5,obj_5,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_8,obj_8,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_12,obj_12,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_13,obj_13,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_14,obj_14,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_15,obj_15,TCC_EA_ATOMIC_LEVEL_sum,wave_size_16,obj_16,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f96e4ac4e80,0,0,192,0,65536,64457,48,1311,31841,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47741,1668,0,48.0,264.0,0.0,262288.0,64,0x7f5ef0308e80,1778463,360448,163840,0,0,180224,114688,0,71426713.0,203167265.0,76086832.0,131072.0,0.0,598834.0,0,0,26004,74585.0,0.0,0.0,74585.0,64,0x7f6c34118e80,32768,0,0,0,16384,16384,393216,23021977,960.0,514019.0,0.0,524288.0,983449.0,32768.0,0,0,0,17750,131072.0,131072.0,0.0,131072.0,64,0x7ff8a140ce80,131072.0,131072.0,0.0,2568379.0,0.0,0.0,136601685.0,61311257.0,64,0x7f6c5942ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7faf7ef68e80,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,0,47900,0,0,64,0x7fa507448e80,4096,0,1202,0,4096,0,534,0,4099,0,0,0,4096,0,0,0,4096,0,1099,0,4096,0,0,0,4096,0,0,0,4096,0,856,0,4096,0,0,0,4096,0,804,0,4144,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,73,0,4096,0,0,0,4096,0,0,0,4144,0,0,0,4096,0,1218,0,4096,0,0,0,4096,0,3103,0,4195,0,2223,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,618,0,4096,0,0,0,4096,0,0,0,4096,0,3006,0,4096,0,0,0,64,0x7f934f204e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86326.0,44746.0,131111.0,0.0,64,0x7fbef9ac2e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,65597.0,135103.0,64,0x7f2ec35b4e80,383120,234664,3438341,16384,25464910,144,48,0,47889,47889,3872412.0,3008555.0,7163.0,988071.0,2058186.0,0.0,2999602.0,2687187.0,381663,244594,47889,0,47889,0,1532448.0,961880.0,0.0,0.0,64,0x7f8f51342e80,0,2348987,4096,4096,0,3164882,4096,4096,0,3270810,4096,4096,0,2486750,4096,4096,0,2390329,4096,4096,0,2862526,4096,4096,0,4599216,4096,4096,0,4165857,4096,4096,0,2044135,4096,4096,0,2849050,4096,4096,0,2793085,4096,4096,0,4879108,4096,4096,0,3070453,4096,4096,0,2885449,4096,4096,0,2799819,4096,4096,0,2483512,4096,4096,0,2516048,4096,4096,0,3405966,4096,4096,0,5395461,4096,4096,0,4059517,4096,4096,0,5452563,4096,4096,0,3003469,4096,4096,0,2429593,4096,4096,0,2643223,4096,4096,0,2046159,4096,4096,0,2896839,4096,4096,0,2391960,4096,4096,0,2436407,4096,4096,0,2898051,4096,4096,0,3117014,4096,4096,0,3994901,4096,4096,0,2624006,4096,4096,64,0x7fe71665ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131294.0,0.0,436.0,131293.0,64,0x7f4436e58e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8372,4276,8372,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb26bfcae80,4108,0,0,2059906,4983,0,0,2098059,920,0,0,1693058,5386,0,0,2179144,1053,0,0,1682983,1899,0,0,1788568,1252,0,0,1767342,4977,0,0,2156124,1744,0,0,1712961,5751,0,0,2234641,1677,0,0,1857668,3198,0,0,1961171,3003,0,0,1939991,1906,0,0,1873530,2116,0,0,1882706,3052,0,0,1989377,2052,0,0,1875555,1342,0,0,1734561,1455,0,0,1736999,1979,0,0,1838933,2284,0,0,1887073,3457,0,0,1998032,1571,0,0,1791744,3282,0,0,2013822,4209,0,0,2087168,884,0,0,1718885,4876,0,0,2181784,4006,0,0,2030795,1976,0,0,1866780,3802,0,0,2039070,1977,0,0,1866340,5068,0,0,2211134,64,0x7fca5ba54e80,190171,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14631,31015,9883,550,0,46227,262599.0,0.0,188.0,262411.0,64,0x7faff5f12e80,0.0,64,0x7fbabfec0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47294,0,131481.0,131072.0,0.0,131104.0,194326078140081,194326078163761 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f96e4ac4e80,0,0,48,0,65536,65536,0,0,31028,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42238,1676,0,48.0,268.0,0.0,262144.0,64,0x7f5ef0308e80,1169987,360448,163840,0,0,180224,114688,0,71601252.0,205731733.0,80519124.0,131072.0,0.0,638084.0,0,0,25583,64010.0,0.0,0.0,64010.0,64,0x7f6c34118e80,32768,0,0,0,16384,16384,393216,23310677,960.0,513970.0,0.0,524288.0,931546.0,32768.0,0,0,0,13891,86495.0,86495.0,0.0,86495.0,64,0x7ff8a140ce80,131072.0,131072.0,0.0,2608991.0,0.0,0.0,103623122.0,47412208.0,64,0x7f6c5942ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7faf7ef68e80,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,0,42172,0,0,64,0x7fa507448e80,4096,0,2134,0,4096,0,2058,0,4096,0,2159,0,4098,0,0,0,4096,0,2834,0,4096,0,2140,0,4096,0,710,0,4096,0,13,0,4096,0,481,0,4097,0,2528,0,4144,0,1381,0,4096,0,1071,0,4096,0,2193,0,4096,0,1787,0,4096,0,1780,0,4096,0,1247,0,4144,0,2236,0,4096,0,2325,0,4096,0,1340,0,4097,0,231,0,4284,0,6187,0,4096,0,2144,0,4096,0,27,0,4096,0,0,0,4096,0,1199,0,4096,0,3037,0,4096,0,781,0,4097,0,0,0,4096,0,831,0,4096,0,40,0,4096,0,678,0,4096,0,250,0,64,0x7f934f204e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86478.0,0.0,131112.0,0.0,64,0x7fbef9ac2e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,51387.0,120030.0,64,0x7f2ec35b4e80,342504,229951,3375912,16384,24411432,0,48,0,42812,42812,3738776.0,3036494.0,6510.0,1064186.0,2018271.0,0.0,3027596.0,2715475.0,342496,239335,42812,0,42812,0,1369984.0,808395.0,0.0,0.0,64,0x7f8f51342e80,0,5237007,2734,2734,0,4405635,2688,2688,0,5446506,2676,2676,0,4914779,2700,2700,0,4127621,2718,2718,0,4901803,2716,2716,0,4043342,2740,2740,0,3315239,2702,2702,0,3917745,2728,2728,0,5060741,2652,2652,0,4277062,2698,2698,0,3797931,2738,2738,0,4902456,2712,2712,0,3338990,2674,2674,0,4861305,2668,2668,0,4187925,2688,2688,0,4084944,2721,2721,0,4099613,2679,2679,0,4846924,2700,2700,0,3225790,2696,2696,0,3139896,2736,2736,0,3188827,2737,2737,0,5523246,2702,2702,0,2812349,2696,2696,0,4541139,2713,2713,0,3468348,2701,2701,0,4200414,2742,2742,0,4445441,2722,2722,0,4659840,2734,2734,0,3942971,2701,2701,0,5054764,2730,2730,0,3640417,2696,2696,64,0x7fe71665ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131710.0,0.0,1270.0,131707.0,64,0x7f4436e58e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,47,8193,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8336,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb26bfcae80,1157,0,0,1387560,3180,0,0,1594727,1717,0,0,1428057,2443,0,0,1534225,3130,0,0,1591318,1483,0,0,1469097,1386,0,0,1389458,1421,0,0,1328717,2187,0,0,1540140,1594,0,0,1408780,1140,0,0,1361729,2122,0,0,1556648,1649,0,0,1468613,477,0,0,1174541,1700,0,0,1513860,2905,0,0,1606934,1408,0,0,1435750,1772,0,0,1501579,1662,0,0,1426380,1010,0,0,1346971,684,0,0,1192991,1683,0,0,1480027,1394,0,0,1404646,4695,0,0,1784928,1782,0,0,1486329,2306,0,0,1599020,1301,0,0,1347891,5219,0,0,1804915,1381,0,0,1402904,6488,0,0,1862081,3967,0,0,1644655,1076,0,0,1373458,64,0x7fca5ba54e80,84961,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,15843,32227,8467,2381,0,41629,262458.0,0.0,47.0,262411.0,64,0x7faff5f12e80,0.0,64,0x7fbabfec0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2674,39939,0,131364.0,131072.0,0.0,86804.0,194326078246321,194326078266001 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f96e4ac4e80,0,0,48,0,65536,65536,0,0,30396,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,41606,1692,0,48.0,268.0,0.0,262144.0,64,0x7f5ef0308e80,1147318,360448,163840,0,0,180224,114688,0,71667473.0,208440349.0,80298221.0,131072.0,0.0,620144.0,0,0,24824,69265.0,0.0,0.0,69265.0,64,0x7f6c34118e80,32768,0,0,0,16384,16384,393216,22428819,960.0,513935.0,0.0,524288.0,996248.0,32768.0,0,0,0,13323,86623.0,86623.0,0.0,86623.0,64,0x7ff8a140ce80,131072.0,131072.0,0.0,2572338.0,0.0,0.0,108200627.0,48314364.0,64,0x7f6c5942ee80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7faf7ef68e80,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,0,42403,0,0,64,0x7fa507448e80,4096,0,119,0,4096,0,1507,0,4096,0,1205,0,4098,0,0,0,4096,0,0,0,4096,0,937,0,4096,0,1226,0,4096,0,33,0,4096,0,147,0,4097,0,1908,0,4144,0,582,0,4096,0,796,0,4096,0,140,0,4096,0,712,0,4096,0,918,0,4096,0,363,0,4144,0,562,0,4096,0,1591,0,4096,0,2052,0,4097,0,1553,0,4207,0,3032,0,4096,0,786,0,4096,0,105,0,4096,0,0,0,4096,0,5,0,4096,0,1227,0,4096,0,335,0,4097,0,5670,0,4096,0,425,0,4096,0,507,0,4096,0,695,0,4096,0,204,0,64,0x7f934f204e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86400.0,0.0,131112.0,0.0,64,0x7fbef9ac2e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,36787.0,115469.0,64,0x7f2ec35b4e80,341320,230368,3357258,16384,24672672,0,48,0,42664,42664,3745496.0,3016362.0,7131.0,1046872.0,2020801.0,0.0,3007669.0,2696261.0,341312,240149,42664,0,42664,0,1365248.0,800407.0,0.0,0.0,64,0x7f8f51342e80,0,4037446,2724,2724,0,3392456,2733,2733,0,3585363,2700,2700,0,3376778,2709,2709,0,4031272,2672,2672,0,4211063,2735,2735,0,2953762,2712,2712,0,3058574,2689,2689,0,3553286,2704,2704,0,4858023,2694,2694,0,3152171,2702,2702,0,3322048,2704,2704,0,4658845,2706,2706,0,3536338,2708,2708,0,3494502,2694,2694,0,3199045,2674,2674,0,3568971,2690,2690,0,4968358,2728,2728,0,3464865,2702,2702,0,4939027,2684,2684,0,5209197,2700,2700,0,3665624,2727,2727,0,2971241,2712,2712,0,4012833,2660,2660,0,3598312,2694,2694,0,4249312,2704,2704,0,3670929,2724,2724,0,2768055,2688,2688,0,4895275,2726,2726,0,3815208,2704,2704,0,3163108,2724,2724,0,3163384,2648,2648,64,0x7fe71665ee80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131322.0,0.0,498.0,131321.0,64,0x7f4436e58e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,47,8193,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8372,4276,8372,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fb26bfcae80,1973,0,0,1439207,5139,0,0,1769560,69,0,0,1090685,2642,0,0,1463000,441,0,0,1263988,1527,0,0,1419006,573,0,0,1375541,3150,0,0,1544802,2233,0,0,1438569,2341,0,0,1507245,200,0,0,1227553,1930,0,0,1438432,2391,0,0,1483800,1264,0,0,1359495,195,0,0,1161586,3351,0,0,1555005,2051,0,0,1376124,2322,0,0,1540157,332,0,0,1175214,2945,0,0,1422837,1811,0,0,1452336,724,0,0,1332711,3666,0,0,1655244,2715,0,0,1502502,3414,0,0,1540029,670,0,0,1222591,522,0,0,1207168,3202,0,0,1498841,1357,0,0,1432612,657,0,0,1305841,221,0,0,1250267,2920,0,0,1509323,64,0x7fca5ba54e80,80179,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14861,31245,8632,2373,0,42456,262441.0,0.0,47.0,262394.0,64,0x7faff5f12e80,0.0,64,0x7fbabfec0e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2667,39182,0,131348.0,131072.0,0.0,86862.0,194326078286481,194326078305361 diff --git a/tests/workloads/kernel_verbose_4/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_4/MI100/sysinfo.csv deleted file mode 100644 index c95cf342a3..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_4,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:09:38 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_4/MI100/timestamps.csv b/tests/workloads/kernel_verbose_4/MI100/timestamps.csv deleted file mode 100644 index fc4c2681f3..0000000000 --- a/tests/workloads/kernel_verbose_4/MI100/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,188851,188851,1048576,256,0,0,8,8,16,64,0x0,0x7fcdc177ce80,194326078115281,194326078140081,194326078163761,194326078175646 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,188851,188851,1048576,256,0,0,8,8,16,64,0x0,0x7fcdc177ce80,194326078176337,194326078246321,194326078266001,194326078267189 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,188851,188851,1048576,256,0,0,8,8,16,64,0x0,0x7fcdc177ce80,194326078277839,194326078286481,194326078305361,194326078306553 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index c8c3c11c3d..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348065,348065,1048576,256,0,0,8,0,16,64,0x0,0x7f6ec65bcec0,27938,27938,16384,65536,19427,2170752,199736671989683,199749380764970,199749380785450,199736687821853 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348065,348065,1048576,256,0,0,8,0,16,64,0x0,0x7f6ec65bcec0,40960,40960,16384,65536,9699,1048724,199736687842181,199749381010410,199749381026730,199736688142660 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348065,348065,1048576,256,0,0,8,0,16,64,0x0,0x7f6ec65bcec0,41140,41140,16384,65536,9396,1048684,199736688172496,199749381056970,199749381072490,199736688346195 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_LDS.csv deleted file mode 100644 index 2b9e01d65d..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_LDS.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348266,348266,1048576,256,0,0,8,0,16,64,0x0,0x7fecc9848ec0,0,0,0,199737153452827,199749380764970,199749380785450,199737169239551 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348266,348266,1048576,256,0,0,8,0,16,64,0x0,0x7fecc9848ec0,0,0,0,199737169257485,199749381010410,199749381026730,199737169557161 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348266,348266,1048576,256,0,0,8,0,16,64,0x0,0x7fecc9848ec0,0,0,0,199737169583481,199749381056970,199749381072490,199737169736681 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index f664a52ff6..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348467,348467,1048576,256,0,0,8,0,16,64,0x0,0x7ff2f8b2cec0,65536,185428,20819504,199737628417567,199749380764970,199749380785450,199737644116635 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348467,348467,1048576,256,0,0,8,0,16,64,0x0,0x7ff2f8b2cec0,65536,255620,28684728,199737644142494,199749381010410,199749381026730,199737644446790 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348467,348467,1048576,256,0,0,8,0,16,64,0x0,0x7ff2f8b2cec0,65536,250286,28090080,199737644472348,199749381056970,199749381072490,199737644628323 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_VMEM.csv deleted file mode 100644 index 03410d100d..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/SQ_INST_LEVEL_VMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348668,348668,1048576,256,0,0,8,0,16,64,0x0,0x7ffb6b5bcec0,32768,297966,33373480,199738105805011,199749380764970,199749380785450,199738121666256 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348668,348668,1048576,256,0,0,8,0,16,64,0x0,0x7ffb6b5bcec0,32768,597744,66947016,199738121684861,199749381010410,199749381026730,199738121958068 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348668,348668,1048576,256,0,0,8,0,16,64,0x0,0x7ffb6b5bcec0,32768,580746,65045176,199738121983746,199749381056970,199749381072490,199738122145412 diff --git a/tests/workloads/kernel_verbose_4/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_4/MI200/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 5b7e010307..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,348853,348853,1048576,256,0,0,8,0,16,64,0x0,0x7fc8703e4ec0,27559,27559,11150,220480,16384,10713927,126978,0,43354456,199738586972194,199749380764970,199749380785450,199738602691601 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,348853,348853,1048576,256,0,0,8,0,16,64,0x0,0x7fc8703e4ec0,41116,41116,13388,328936,16384,19033337,220605,0,76630672,199738602721107,199749381010410,199749381026730,199738603154046 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,348853,348853,1048576,256,0,0,8,0,16,64,0x0,0x7fc8703e4ec0,41528,41528,13594,332232,16384,19388701,224822,0,78030200,199738603190014,199749381056970,199749381072490,199738603386556 diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_0.txt deleted file mode 100644 index 4ffdc32149..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6c277f4a37..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_10.txt deleted file mode 100644 index 7053d4dce6..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_11.txt deleted file mode 100644 index 77ae8b461f..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_12.txt deleted file mode 100644 index dfb2cf65e5..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_13.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_14.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_15.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_16.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_17.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_17.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_18.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_18.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_2.txt deleted file mode 100644 index 70b69f8928..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_3.txt deleted file mode 100644 index e47f8e33c9..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_4.txt deleted file mode 100644 index 2d96f365a9..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_5.txt deleted file mode 100644 index e50beed390..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_6.txt deleted file mode 100644 index 15a2277c1b..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_7.txt deleted file mode 100644 index b42ce91618..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_8.txt deleted file mode 100644 index 21d4c7a998..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_9.txt deleted file mode 100644 index 9ffe5778c3..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_4/MI200/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_4/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_4/MI200/pmc_perf.csv deleted file mode 100644 index 8b0348920b..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_1,obj_1,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_2,obj_2,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_3,obj_3,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_4,obj_4,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_5,obj_5,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_6,obj_6,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_7,obj_7,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_8,obj_8,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_9,obj_9,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_12,obj_12,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_13,obj_13,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_14,obj_14,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_15,obj_15,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_16,obj_16,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_17,obj_17,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_18,obj_18,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f6e5b4ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7fd81e810ec0,227888,130668,16384,0,16384,16384,32768,49152,28485,28485,1976915.0,1346731.0,3502.0,162005.0,1058194.0,0.0,1338074.0,1038757.0,226177,138808,28485,0,28485,0,911520.0,492133.0,0.0,0.0,64,0x7f5244f38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,35133.0,45994.0,19542.0,64,0x7fbd9d184ec0,6332,0,4096,6379,0,4096,6385,0,4096,6388,0,4096,6379,0,4096,6415,0,4096,6342,0,4096,6402,0,4096,6405,0,4096,6337,0,4096,6381,0,4096,6386,0,4096,6389,0,4096,6384,0,4096,6416,0,4096,6345,0,4096,6395,0,4096,6400,0,4096,6366,0,4096,6365,0,4096,6388,0,4096,6398,0,4096,6379,0,4096,6572,0,4096,6406,0,4096,6395,0,4096,6409,0,4096,6371,0,4096,6366,0,4096,6392,0,4096,6397,0,4096,6382,0,4096,64,0x7fe272f00ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10615,0,815,28216,0,72438.0,131072.0,0.0,65568.0,64,0x7f536aeecec0,32768,32768,0,64,0x7f50437bcec0,10803107,9669253,789790,344064,1627540,0,0,163840,832.0,515140.0,0.0,524288.0,250900.0,32768.0,494328,0,0,11207,131072.0,131072.0,0.0,131072.0,64,0x7f641ab38ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,9,0,4096,0,0,0,4096,0,173,0,4096,0,69,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,24,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,14,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,40,0,4096,0,21,0,4096,0,0,0,4101,0,21,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f248ac6cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39939937.0,34902096.0,0.0,64,0x7fd0cb6bcec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,978039.0,64,0x7f5d6ba58ec0,0,1295420,4096,4096,0,1267420,4096,4096,0,1137361,4096,4096,0,1292375,4096,4096,0,1394049,4096,4096,0,1413718,4096,4096,0,1282078,4096,4096,0,1406440,4096,4096,0,1175897,4096,4096,0,1175191,4096,4096,0,1141265,4096,4096,0,1084551,4096,4096,0,1233535,4096,4096,0,1292197,4096,4096,0,1082658,4096,4096,0,1525718,4096,4096,0,1076275,4096,4096,0,1246682,4096,4096,0,1028374,4096,4096,0,1422522,4096,4096,0,1140737,4096,4096,0,1184374,4096,4096,0,1256059,4096,4096,0,1335820,4096,4096,0,1578280,4096,4096,0,961057,4096,4096,0,1286633,4096,4096,0,1199648,4096,4096,0,1284892,4096,4096,0,1057368,4096,4096,0,1091224,4096,4096,0,1293848,4096,4096,64,0x7f9ae5d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13652,19180,8940,545,0,28065,204169.0,0.0,73088.0,131081.0,64,0x7f909e244ec0,0,0,0,224,0,65536,64267,56,64,0x7f529fde8ec0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,0,28212,0,0,64,0x7f1acd934ec0,114688,0,32768,32768,16384,16384,65536,49152,26699351.0,81413137.0,36824372.0,131072.0,0.0,225596.0,0,0,14858,766.0,131082.0,0.0,12.0,64,0x7f87d1384ec0,2298,4096,2298,6394,2303,4096,2303,6399,2252,4096,2252,6348,2286,4096,2286,6382,2315,4096,2315,6411,2298,4096,2298,6394,2287,4096,2287,6383,2259,4096,2259,6355,2261,4096,2261,6357,2303,4097,2304,6400,2307,4096,2307,6403,2312,4097,2313,6409,2285,4096,2285,6381,2313,4096,2313,6409,2300,4096,2300,6396,2287,4096,2287,6383,2264,4096,2264,6360,2249,4096,2249,6345,2303,4097,2304,6400,2332,4096,2332,6428,2291,4096,2291,6387,2270,4096,2270,6366,2272,4096,2272,6368,2485,4098,2487,6583,2321,4096,2321,6417,2260,4096,2260,6356,2253,4096,2253,6349,2302,4101,2307,6403,2333,4096,2333,6429,2297,4096,2297,6393,2277,4096,2277,6373,2272,4096,2272,6368,64,0x7fca9853cec0,0,393216,163840,0,0,0,0,0,18303,0.0,0.0,0.0,32768.0,0.0,0.0,415.0,32768.0,4096,16384,352,29242,2021,0,56.0,6.0,0.0,204400.0,64,0x7f2c3627cec0,0,0,0,1060710,44,0,0,1106360,0,0,0,1081222,0,0,0,1023260,3,0,0,1106282,0,0,0,1070725,0,0,0,1020710,0,0,0,1174527,0,0,0,1011182,0,0,0,1042669,87,0,0,1092404,0,0,0,1052883,0,0,0,1058866,0,0,0,1064453,0,0,0,1060598,0,0,0,1107483,0,0,0,1068967,0,0,0,1145100,0,0,0,985717,0,0,0,1077602,20,0,0,1070334,0,0,0,1086426,99,0,0,1149875,0,0,0,1046518,0,0,0,1006129,0,0,0,1105596,0,0,0,1178090,0,0,0,1109748,0,0,0,1010572,0,0,0,1055077,0,0,0,1091509,26,0,0,1148206,64,0x7f7fc6578ec0,1296,119602,0,0,65536,63800,56,1680,199749380764970,199749380785450 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f6e5b4ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fd81e810ec0,329112,222763,16384,0,16384,16384,32768,49152,41138,41138,3173212.0,2449003.0,5326.0,375837.0,1713794.0,0.0,2437206.0,2129038.0,329104,232059,41138,0,41138,0,1316416.0,773783.0,0.0,0.0,64,0x7f5244f38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,93570.0,45609.0,0.0,64,0x7fbd9d184ec0,6276,0,4096,6262,0,4096,6274,0,4096,6234,0,4096,6248,0,4096,6292,0,4096,6255,0,4096,6259,0,4096,6260,0,4096,6281,0,4096,6265,0,4096,6268,0,4096,6236,0,4096,6249,0,4096,6293,0,4096,6255,0,4096,6259,0,4096,6272,0,4096,6264,0,4096,6243,0,4096,6266,0,4096,6289,0,4096,6261,0,4096,6238,0,4096,6239,0,4096,6263,0,4096,6275,0,4096,6262,0,4096,6247,0,4096,6266,0,4096,6292,0,4096,6264,0,4096,64,0x7fe272f00ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,16985,0,819,36469,0,69196.0,131072.0,0.0,45529.0,64,0x7f536aeecec0,32768,32768,0,64,0x7f50437bcec0,19630104,18288855,997185,344064,2813658,0,0,163840,832.0,515166.0,0.0,524288.0,568327.0,32768.0,1013168,0,0,13706,90994.0,90994.0,0.0,90994.0,64,0x7f641ab38ec0,4096,0,0,0,4096,0,3,0,4096,0,314,0,4096,0,163,0,4096,0,994,0,4096,0,566,0,4096,0,0,0,4096,0,423,0,4096,0,537,0,4096,0,217,0,4098,0,3,0,4096,0,1190,0,4096,0,189,0,4096,0,687,0,4096,0,256,0,4097,0,300,0,4097,0,0,0,4096,0,513,0,4097,0,290,0,4096,0,1145,0,4096,0,981,0,4096,0,578,0,4096,0,437,0,4096,0,474,0,4096,0,88,0,4096,0,21,0,4096,0,3,0,4096,0,211,0,4101,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f248ac6cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119451113.0,60267847.0,0.0,64,0x7fd0cb6bcec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,1976955.0,64,0x7f5d6ba58ec0,0,2939690,2820,2820,0,3426253,2868,2868,0,4013036,2860,2860,0,3841543,2868,2868,0,3112428,2890,2890,0,4302886,2852,2852,0,2904736,2888,2888,0,3725742,2824,2824,0,3264165,2824,2824,0,3233772,2824,2824,0,4304458,2868,2868,0,3540582,2860,2860,0,3720780,2868,2868,0,3554590,2892,2892,0,3827770,2852,2852,0,3146264,2888,2888,0,3211063,2842,2842,0,4188618,2876,2876,0,2949166,2836,2836,0,5277715,2832,2832,0,4832339,2836,2836,0,4745132,2884,2884,0,4603028,2840,2840,0,3605773,2840,2840,0,3654437,2844,2844,0,2909567,2838,2838,0,4004989,2876,2876,0,3367918,2836,2836,0,3277015,2828,2828,0,3135925,2840,2840,0,3735874,2896,2896,0,3432476,2830,2830,64,0x7f9ae5d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30999,27117,9916,2983,0,39213,200295.0,0.0,69211.0,131084.0,64,0x7f909e244ec0,0,0,0,56,0,65536,65536,0,64,0x7f529fde8ec0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,0,41676,0,0,64,0x7f1acd934ec0,114688,0,32768,32768,16384,16384,65536,49152,58198192.0,205684795.0,51659496.0,131072.0,0.0,571037.0,0,0,25370,2998.0,131083.0,0.0,20.0,64,0x7f87d1384ec0,2167,4096,2167,6263,2151,4096,2151,6247,2163,4096,2163,6259,2155,4096,2155,6251,2212,4096,2212,6308,2163,4096,2163,6259,2164,4096,2164,6260,2166,4096,2166,6262,2167,4096,2167,6263,2172,4097,2173,6269,2156,4097,2157,6253,2221,4097,2222,6318,2163,4096,2163,6259,2215,4096,2215,6311,2170,4096,2170,6266,2167,4096,2167,6263,2171,4097,2172,6268,2159,4096,2159,6255,2158,4097,2159,6255,2141,4096,2141,6237,2157,4096,2157,6253,2176,4096,2176,6272,2167,4096,2167,6263,2163,4096,2163,6259,2159,4096,2159,6255,2170,4096,2170,6266,2165,4096,2165,6261,2163,4099,2166,6262,2145,4098,2147,6243,2159,4096,2159,6255,2180,4096,2180,6276,2171,4096,2171,6267,64,0x7fca9853cec0,0,393216,163840,0,0,0,0,0,29627,0.0,0.0,0.0,32768.0,0.0,0.0,228.0,32768.0,4096,16384,302,41430,2065,0,56.0,10.0,0.0,200867.0,64,0x7f2c3627cec0,0,0,0,1660978,576,0,0,2205430,0,0,0,1691927,134,0,0,2178102,0,0,0,1866592,681,0,0,2193488,0,0,0,1450222,6,0,0,1973301,0,0,0,1503169,0,0,0,1730254,96,0,0,2004579,26,0,0,1890497,305,0,0,1860881,0,0,0,1804412,379,0,0,2093422,0,0,0,1697503,0,0,0,1693186,0,0,0,1919436,0,0,0,1443628,157,0,0,2134344,67,0,0,1804613,0,0,0,1678333,0,0,0,1758987,0,0,0,1759137,0,0,0,1736394,0,0,0,1312740,0,0,0,1483042,537,0,0,2437421,0,0,0,2065350,0,0,0,1873346,139,0,0,1655597,0,0,0,1748383,64,0x7f7fc6578ec0,0,186018,0,0,65536,63800,56,1680,199749381010410,199749381026730 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2f6e5b4ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7fd81e810ec0,330560,222288,16384,0,16384,16384,32768,49152,41319,41319,3167403.0,2420097.0,4960.0,320846.0,1624577.0,0.0,2408196.0,2100449.0,330552,232125,41319,0,41319,0,1322208.0,764152.0,0.0,0.0,64,0x7f5244f38ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,135279.0,45600.0,0.0,64,0x7fbd9d184ec0,6295,0,4096,6280,0,4096,6314,0,4096,6266,0,4096,6284,0,4096,6263,0,4096,6259,0,4096,6262,0,4096,6265,0,4096,6296,0,4096,6279,0,4096,6315,0,4096,6268,0,4096,6289,0,4096,6261,0,4096,6263,0,4096,6285,0,4096,6279,0,4096,6292,0,4096,6287,0,4096,6294,0,4096,6308,0,4096,6261,0,4096,6274,0,4096,6271,0,4096,6289,0,4096,6277,0,4096,6296,0,4096,6287,0,4096,6296,0,4096,6311,0,4096,6262,0,4096,64,0x7fe272f00ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20942,0,3127,38145,0,69565.0,131072.0,0.0,45440.0,64,0x7f536aeecec0,32768,32768,0,64,0x7f50437bcec0,19619179,18010368,1264747,344064,2830893,0,0,163840,832.0,515153.0,0.0,524288.0,524080.0,32768.0,1000691,0,0,13989,91164.0,91164.0,0.0,91164.0,64,0x7f641ab38ec0,4096,0,1141,0,4096,0,539,0,4096,0,2224,0,4096,0,1394,0,4096,0,218,0,4096,0,407,0,4096,0,1222,0,4096,0,1121,0,4096,0,979,0,4096,0,33,0,4098,0,314,0,4096,0,852,0,4096,0,1812,0,4096,0,546,0,4096,0,161,0,4097,0,325,0,4097,0,447,0,4096,0,259,0,4097,0,431,0,4096,0,793,0,4096,0,1301,0,4096,0,1185,0,4096,0,11,0,4096,0,1400,0,4096,0,28,0,4096,0,454,0,4096,0,553,0,4096,0,336,0,4101,0,31,0,4096,0,1365,0,4096,0,522,0,4096,0,382,0,64,0x7f248ac6cec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,117603812.0,58363570.0,0.0,64,0x7fd0cb6bcec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2044775.0,64,0x7f5d6ba58ec0,0,3387149,2812,2812,0,3672773,2846,2846,0,5032810,2852,2852,0,4135074,2844,2844,0,3299394,2916,2916,0,3858099,2864,2864,0,2681232,2884,2884,0,3352298,2836,2836,0,3203452,2832,2832,0,3320733,2818,2818,0,2943999,2846,2846,0,4470664,2848,2848,0,4323946,2844,2844,0,3199954,2916,2916,0,3732372,2860,2860,0,2952493,2884,2884,0,3387769,2824,2824,0,3421718,2864,2864,0,3213328,2844,2844,0,3671925,2816,2816,0,3649922,2824,2824,0,4162166,2864,2864,0,3739001,2860,2860,0,3944805,2852,2852,0,4077494,2848,2848,0,3294647,2816,2816,0,3254687,2864,2864,0,3414766,2844,2844,0,4710619,2820,2820,0,4307580,2824,2824,0,3322530,2876,2876,0,3601901,2864,2864,64,0x7f9ae5d50ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,34917,28899,9771,3687,0,40769,201084.0,0.0,70000.0,131084.0,64,0x7f909e244ec0,0,0,0,56,0,65536,65536,0,64,0x7f529fde8ec0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,0,40854,0,0,64,0x7f1acd934ec0,114688,0,32768,32768,16384,16384,65536,49152,56702455.0,195105281.0,42665129.0,131072.0,0.0,486307.0,0,0,24543,3941.0,131084.0,0.0,22.0,64,0x7f87d1384ec0,2160,4096,2160,6256,2148,4096,2148,6244,2152,4096,2152,6248,2121,4096,2121,6217,2159,4096,2159,6255,2169,4096,2169,6265,2158,4096,2158,6254,2146,4096,2146,6242,2146,4096,2146,6242,2165,4097,2166,6262,2157,4097,2158,6254,2210,4097,2211,6307,2123,4096,2123,6219,2160,4096,2160,6256,2170,4096,2170,6266,2165,4096,2165,6261,2206,4097,2207,6303,2206,4096,2206,6302,2160,4097,2161,6257,2161,4096,2161,6257,2144,4096,2144,6240,2128,4096,2128,6224,2152,4096,2152,6248,2158,4096,2158,6254,2164,4096,2164,6260,2203,4096,2203,6299,2208,4096,2208,6304,2159,4098,2161,6257,2166,4098,2168,6264,2152,4096,2152,6248,2132,4096,2132,6228,2156,4096,2156,6252,64,0x7fca9853cec0,0,393216,163840,0,0,0,0,0,29902,0.0,0.0,0.0,32768.0,0.0,0.0,242.0,32768.0,4096,16384,302,41638,2021,0,56.0,10.0,0.0,200309.0,64,0x7f2c3627cec0,25,0,0,1677051,460,0,0,2286718,1087,0,0,2304846,2273,0,0,2698650,169,0,0,2297086,581,0,0,2136583,16,0,0,1452752,439,0,0,2400393,1133,0,0,2316866,26,0,0,1703628,523,0,0,1862380,706,0,0,1963481,894,0,0,2059243,0,0,0,2044577,362,0,0,2229000,213,0,0,2271334,252,0,0,2187217,2348,0,0,2658178,0,0,0,1572261,666,0,0,2486274,1038,0,0,2113109,493,0,0,2198353,75,0,0,1981269,0,0,0,1728361,64,0,0,2162060,493,0,0,2011829,1571,0,0,2421765,0,0,0,1732236,318,0,0,2110194,1059,0,0,1795396,649,0,0,2356621,0,0,0,1658749,64,0x7f7fc6578ec0,0,186203,0,0,65536,63800,56,1680,199749381056970,199749381072490 diff --git a/tests/workloads/kernel_verbose_4/MI200/roofline.csv b/tests/workloads/kernel_verbose_4/MI200/roofline.csv deleted file mode 100644 index b13d4fb9f2..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/roofline.csv +++ /dev/null @@ -1,5 +0,0 @@ -device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.7625,1388.2411,1389.2838,5016.5361,5013.605,5019.4673,9223.2041,9222.5723,9223.8359,18050.207,18049.324,18051.09,20932.619,20872.697,20992.541,20263.148,20262.469,20263.828,170389.42,170384.58,170394.27,164857.81,164852.52,164863.11,41419.113,41418.391,41419.836,41478.637,41477.973,41479.301,166324,165836.27,166811.73 -1,1389.254,1388.6711,1389.8369,5027.2559,5025.0059,5029.5059,9233.7461,9233.0928,9234.3994,18092.617,18089.189,18096.045,20975.557,20909.123,21041.99,20295.359,20294.771,20295.947,170836.59,170832.16,170841.03,165098.92,165095.12,165102.72,41481.727,41480.871,41482.582,41535.816,41534.801,41536.832,166838.17,166834.67,166841.67 -2,1389.1714,1388.6238,1389.719,5036.0137,5033.8647,5038.1626,9259.9805,9259.0732,9260.8877,18106.842,18105.809,18107.875,21048.09,21047.76,21048.42,20353.053,20352.539,20353.566,171123.58,171119.7,171127.45,165503.53,165499.88,165507.19,41580.453,41579.621,41581.285,41638.012,41637.074,41638.949,166947.05,166360.5,167533.59 -3,1388.7527,1388.2761,1389.2292,5031.7871,5030.4165,5033.1577,9241.7812,9241.1855,9242.377,18022.385,18018.469,18026.301,21035.93,21035.412,21036.447,20313.078,20312.459,20313.697,171051.62,171047.64,171055.61,165233.8,165228.7,165238.89,41440.371,41288.145,41592.598,41582.023,41581.367,41582.68,167017.52,167015.72,167019.31 diff --git a/tests/workloads/kernel_verbose_4/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_4/MI200/sysinfo.csv deleted file mode 100644 index b1bdbe022e..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_4,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:40:03 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_4/MI200/timestamps.csv b/tests/workloads/kernel_verbose_4/MI200/timestamps.csv deleted file mode 100644 index 48347d8de1..0000000000 --- a/tests/workloads/kernel_verbose_4/MI200/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,352810,352810,1048576,256,0,0,8,0,16,64,0x0,0x7f9958dd8ec0,199749380736229,199749380764970,199749380785450,199749380797865 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,352810,352810,1048576,256,0,0,8,0,16,64,0x0,0x7f9958dd8ec0,199749380796593,199749381010410,199749381026730,199749381028502 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,352810,352810,1048576,256,0,0,8,0,16,64,0x0,0x7f9958dd8ec0,199749381037980,199749381056970,199749381072490,199749381073997 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_5/MI100/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 19b9118e94..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189129,189129,1048576,256,0,0,8,8,16,64,0x0,0x7f1e88b78e80,47888,47888,16384,65536,14433,1862592,194327668479458,194339836161015,194339836185335,194327676337277 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189129,189129,1048576,256,0,0,8,8,16,64,0x0,0x7f1e88b78e80,43039,43039,16384,65536,8098,1048584,194327676358677,194339836365335,194339836384535,194327676683011 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189129,189129,1048576,256,0,0,8,8,16,64,0x0,0x7f1e88b78e80,42802,42802,16384,65536,8330,1048576,194327676715643,194339836406935,194339836425975,194327676893850 diff --git a/tests/workloads/kernel_verbose_5/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_5/MI100/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 69ee17fcd3..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,189868,189868,1048576,256,0,0,8,8,16,64,0x0,0x7f48053c0e80,47704,47704,17048,381640,16384,25028052,232701,0,100607848,194329650334392,194339836161015,194339836185335,194329658009754 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,189868,189868,1048576,256,0,0,8,8,16,64,0x0,0x7f48053c0e80,42903,42903,13930,343232,16384,24547026,230432,0,98677920,194329658036545,194339836365335,194339836384535,194329658400675 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,189868,189868,1048576,256,0,0,8,8,16,64,0x0,0x7f48053c0e80,42215,42215,13410,337728,16384,24070442,226068,0,96775756,194329658439689,194339836406935,194339836425975,194329658670235 diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index 202141726e..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_BUSY_CU_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ SQC_TC_DATA_WRITE_REQ GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6f289aa046..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES SQC_ICACHE_MISSES_DUPLICATE GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_COALESCABLE_WAVEFRONT_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_10.txt deleted file mode 100644 index a00555d953..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_11.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_12.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_13.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_14.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_15.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_16.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 2180ee3f63..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE SQC_DCACHE_REQ_READ_1 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_3.txt deleted file mode 100644 index 8f1ba90d04..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU SQ_INSTS_VSKIPPED SQ_INSTS_SMEM TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_4.txt deleted file mode 100644 index 9a82481329..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG SQ_INSTS SQ_WAIT_ANY TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_5.txt deleted file mode 100644 index bbc1f21123..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_INSTS_VALU SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_WRREQ_IO_CREDIT_STALL_sum TCC_EA_WRREQ_GMI_CREDIT_STALL_sum TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_6.txt deleted file mode 100644 index b6368182b4..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU SQ_THREAD_CYCLES_VALU SQ_IFETCH TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum TCC_EA_RDREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_7.txt deleted file mode 100644 index 3f7673fd23..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 SQ_WAVES_LT_32 SQ_WAVES_LT_16 TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_EA_RDREQ_IO_CREDIT_STALL_sum TCC_EA_RDREQ_GMI_CREDIT_STALL_sum TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum TCC_TAG_STALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_8.txt deleted file mode 100644 index facba6bd95..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED SQ_INSTS_SMEM_NORM TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_9.txt deleted file mode 100644 index d458645ea4..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_5/MI100/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI100/pmc_perf.csv b/tests/workloads/kernel_verbose_5/MI100/pmc_perf.csv deleted file mode 100644 index ee0800033b..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_1,obj_1,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_6,obj_6,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_10,obj_10,TCC_EA_ATOMIC_LEVEL_sum,wave_size_11,obj_11,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_14,obj_14,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_15,obj_15,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_16,obj_16,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff152bdce80,1499613,360448,163840,0,0,180224,114688,0,69824868.0,192774399.0,72890617.0,131072.0,0.0,734883.0,0,0,26199,102634.0,0.0,0.0,102634.0,64,0x7f8735dece80,32768,0,0,0,16384,16384,393216,22517640,960.0,513930.0,0.0,524288.0,920924.0,32768.0,0,0,0,16834,131072.0,131072.0,0.0,131072.0,64,0x7f72d4350e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131333.0,0.0,514.0,131332.0,64,0x7f0845a66e80,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,0,48332,0,0,64,0x7ff61a272e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8471,4375,8471,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f4f9d2f6e80,0,3939748,4096,4096,0,4443055,4096,4096,0,3266882,4096,4096,0,2911959,4096,4096,0,4065717,4096,4096,0,3071282,4096,4096,0,4649556,4096,4096,0,3887334,4096,4096,0,4190930,4096,4096,0,3284101,4096,4096,0,5112928,4096,4096,0,3262087,4096,4096,0,4263841,4096,4096,0,3017669,4096,4096,0,5446783,4096,4096,0,4079591,4096,4096,0,4550102,4096,4096,0,4891926,4096,4096,0,3838648,4096,4096,0,3450667,4096,4096,0,4325669,4096,4096,0,2976756,4096,4096,0,4299053,4096,4096,0,2986696,4096,4096,0,4140733,4096,4096,0,3338287,4096,4096,0,3906922,4096,4096,0,4384229,4096,4096,0,3883644,4096,4096,0,2473675,4096,4096,0,4171046,4096,4096,0,3634635,4096,4096,64,0x7f9f2ec6ae80,188344,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13608,29992,10029,550,0,46442,262581.0,0.0,188.0,262393.0,64,0x7fa8312c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46836,0,131572.0,131072.0,0.0,131104.0,64,0x7f70169a0e80,392424,235362,3419058,16384,24849883,144,48,0,49052,49052,3882896.0,2966072.0,6251.0,1351704.0,2110113.0,0.0,2956889.0,2646381.0,391103,245302,49052,0,49052,0,1569664.0,972093.0,0.0,0.0,64,0x7f120dac0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86456.0,44616.0,131111.0,0.0,64,0x7f7d83402e80,0.0,64,0x7f96cc104e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,46104.0,109288.0,64,0x7f4b453eae80,3123,0,0,1931203,1585,0,0,1858254,2374,0,0,1796834,442,0,0,1569154,2735,0,0,2026502,957,0,0,1645619,1938,0,0,1798818,2306,0,0,1886738,2023,0,0,1802143,3424,0,0,1964058,1326,0,0,1735545,861,0,0,1690252,1890,0,0,1832679,671,0,0,1654111,2115,0,0,1802902,954,0,0,1752317,1445,0,0,1749518,834,0,0,1649391,2137,0,0,1776798,471,0,0,1580312,4684,0,0,2088290,1455,0,0,1723765,2832,0,0,1849038,1082,0,0,1760634,3534,0,0,2085132,907,0,0,1747966,1863,0,0,1799368,2226,0,0,1827243,2647,0,0,1874254,4737,0,0,2068035,3386,0,0,2018812,1467,0,0,1758289,64,0x7fd19fc96e80,4096,0,1138,0,4096,0,1270,0,4100,0,670,0,4096,0,287,0,4096,0,1017,0,4096,0,0,0,4144,0,0,0,4096,0,0,0,4096,0,6733,0,4096,0,894,0,4144,0,0,0,4216,0,5171,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4150,0,0,0,4096,0,9364,0,4096,0,1394,0,4096,0,181,0,4096,0,0,0,4096,0,0,0,4096,0,398,0,4096,0,152,0,4096,0,0,0,4096,0,66,0,4096,0,287,0,4096,0,0,0,4096,0,129,0,4216,0,980,0,4096,0,135,0,4096,0,0,0,4096,0,488,0,64,0x7faffe2a0e80,0,0,192,0,65536,64415,48,1529,32223,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48145,1710,0,48.0,255.0,0.0,262288.0,64,0x7f4e3f6d6e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdfc71ce80,131072.0,131072.0,0.0,2553503.0,0.0,0.0,106102580.0,61371369.0,194339836161015,194339836185335 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff152bdce80,1347457,360448,163840,0,0,180224,114688,0,65721003.0,188322359.0,74301065.0,131072.0,0.0,817243.0,0,0,25001,99300.0,0.0,0.0,99300.0,64,0x7f8735dece80,32768,0,0,0,16384,16384,393216,22361836,960.0,513922.0,0.0,524288.0,946179.0,32768.0,0,0,0,13964,86911.0,86911.0,0.0,86911.0,64,0x7f72d4350e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131382.0,0.0,618.0,131381.0,64,0x7f0845a66e80,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,0,42856,0,0,64,0x7ff61a272e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8470,4374,8470,0,8192,4096,8192,0,8192,4096,8192,47,8194,4145,8241,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f4f9d2f6e80,0,3518684,2710,2710,0,4231549,2741,2741,0,4057507,2692,2692,0,4903784,2728,2728,0,3307219,2717,2717,0,2949122,2736,2736,0,3198882,2716,2716,0,3364134,2727,2727,0,5182322,2696,2696,0,3019700,2708,2708,0,3040906,2712,2712,0,5054873,2728,2728,0,3684522,2716,2716,0,4375277,2712,2712,0,4608066,2708,2708,0,3996044,2683,2683,0,5373070,2698,2698,0,3628970,2712,2712,0,3036938,2692,2692,0,4411604,2702,2702,0,4219579,2684,2684,0,3396626,2779,2779,0,3038731,2709,2709,0,2917673,2662,2662,0,2653865,2704,2704,0,3889594,2748,2748,0,3298029,2708,2708,0,3160945,2744,2744,0,4108399,2688,2688,0,3145392,2758,2758,0,3738007,2724,2724,0,4972697,2708,2708,64,0x7f9f2ec6ae80,183144,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,10524,26908,8578,2411,0,41597,262495.0,0.0,47.0,262448.0,64,0x7fa8312c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2756,41301,0,131508.0,131072.0,0.0,86974.0,64,0x7f70169a0e80,342608,231992,3366611,16384,24103847,0,48,0,42825,42825,3769538.0,3020480.0,5081.0,1146243.0,2152781.0,0.0,3011816.0,2701946.0,342600,241453,42825,0,42825,0,1370400.0,827545.0,0.0,0.0,64,0x7f120dac0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,49432.0,37197.0,31128.0,0.0,64,0x7f7d83402e80,0.0,64,0x7f96cc104e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,73418.0,138198.0,64,0x7f4b453eae80,1540,0,0,1444301,1386,0,0,1370255,1984,0,0,1460020,1823,0,0,1364651,571,0,0,1298101,1909,0,0,1536794,804,0,0,1402101,2211,0,0,1439847,1534,0,0,1378863,3516,0,0,1674602,1296,0,0,1287668,921,0,0,1386270,2090,0,0,1436246,571,0,0,1308261,1940,0,0,1397466,2692,0,0,1611344,1564,0,0,1394917,312,0,0,1304531,1135,0,0,1385174,1856,0,0,1399700,5155,0,0,1754415,352,0,0,1237235,1413,0,0,1383004,834,0,0,1195428,2955,0,0,1543371,2663,0,0,1563322,3129,0,0,1509995,4932,0,0,1669094,3640,0,0,1729842,2782,0,0,1500497,2802,0,0,1554076,1813,0,0,1412117,64,0x7fd19fc96e80,4096,0,8972,0,4096,0,0,0,4097,0,3048,0,4096,0,623,0,4096,0,1277,0,4097,0,683,0,4144,0,634,0,4098,0,602,0,4096,0,1000,0,4096,0,717,0,4144,0,625,0,4216,0,1863,0,4096,0,0,0,4096,0,1633,0,4096,0,1709,0,4139,0,12,0,4096,0,939,0,4096,0,1297,0,4096,0,1856,0,4096,0,667,0,4096,0,6453,0,4096,0,1536,0,4096,0,124,0,4097,0,0,0,4096,0,439,0,4096,0,319,0,4096,0,1372,0,4096,0,0,0,4216,0,1,0,4096,0,157,0,4096,0,995,0,4096,0,21,0,64,0x7faffe2a0e80,0,0,48,0,65536,65536,0,0,32188,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,43552,1767,0,48.0,364.0,0.0,262144.0,64,0x7f4e3f6d6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdfc71ce80,131072.0,131072.0,0.0,2566412.0,0.0,0.0,137327742.0,48410073.0,194339836365335,194339836384535 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7ff152bdce80,1322927,360448,163840,0,0,180224,114688,0,67761045.0,195182409.0,74818673.0,131072.0,0.0,830136.0,0,0,24728,124626.0,0.0,0.0,124626.0,64,0x7f8735dece80,32768,0,0,0,16384,16384,393216,22532751,960.0,513891.0,0.0,524288.0,880969.0,32768.0,0,0,0,13611,86501.0,86501.0,0.0,86501.0,64,0x7f72d4350e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131442.0,0.0,738.0,131441.0,64,0x7f0845a66e80,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,0,43163,0,0,64,0x7ff61a272e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8476,4380,8476,0,8192,4096,8192,0,8192,4096,8192,47,8194,4145,8241,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,64,0x7f4f9d2f6e80,0,3086531,2683,2683,0,3317971,2746,2746,0,3352513,2684,2684,0,3146409,2736,2736,0,3151727,2676,2676,0,3192235,2744,2744,0,4376009,2702,2702,0,3202802,2720,2720,0,3259134,2686,2686,0,3800343,2708,2708,0,4164544,2712,2712,0,5007777,2716,2716,0,3543308,2696,2696,0,3046028,2728,2728,0,3951001,2712,2712,0,3081473,2690,2690,0,3430534,2676,2676,0,4548064,2724,2724,0,4307039,2700,2700,0,2770369,2724,2724,0,4926197,2676,2676,0,4759543,2780,2780,0,2904016,2672,2672,0,2674117,2682,2682,0,2712433,2660,2660,0,3723130,2730,2730,0,3027792,2746,2746,0,5357453,2738,2738,0,2946611,2688,2688,0,3470740,2738,2738,0,3642104,2724,2724,0,3791165,2694,2694,64,0x7f9f2ec6ae80,183111,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,10793,27177,8547,2427,0,41005,262465.0,0.0,47.0,262418.0,64,0x7fa8312c6e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2753,40874,0,131486.0,131072.0,0.0,86902.0,64,0x7f70169a0e80,343176,228919,3326199,16384,24374477,0,48,0,42896,42896,3723476.0,2979824.0,4955.0,1145869.0,2122116.0,0.0,2971114.0,2662193.0,343168,238681,42896,0,42896,0,1372672.0,815676.0,0.0,0.0,64,0x7f120dac0e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86525.0,0.0,131112.0,0.0,64,0x7f7d83402e80,0.0,64,0x7f96cc104e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,74538.0,142626.0,64,0x7f4b453eae80,4663,0,0,1719035,4195,0,0,1705745,1860,0,0,1485385,4286,0,0,1670609,1887,0,0,1438755,1922,0,0,1492049,2334,0,0,1461240,4691,0,0,1707754,1212,0,0,1369671,1726,0,0,1412373,2977,0,0,1561380,120,0,0,1264876,2134,0,0,1387316,3406,0,0,1458464,3058,0,0,1645266,2781,0,0,1542979,1451,0,0,1413717,254,0,0,1161879,3414,0,0,1555880,1934,0,0,1454006,1569,0,0,1457370,2026,0,0,1440167,3540,0,0,1586729,2286,0,0,1475484,3771,0,0,1617066,695,0,0,1221590,2953,0,0,1623377,4190,0,0,1717194,3460,0,0,1512751,3341,0,0,1485875,5129,0,0,1712068,4177,0,0,1646353,64,0x7fd19fc96e80,4096,0,2325,0,4096,0,777,0,4097,0,1666,0,4096,0,1212,0,4096,0,4085,0,4097,0,2021,0,4144,0,1527,0,4098,0,1600,0,4096,0,1350,0,4096,0,2403,0,4144,0,1505,0,4216,0,1587,0,4096,0,1329,0,4096,0,547,0,4096,0,1710,0,4199,0,2801,0,4096,0,2783,0,4096,0,3770,0,4096,0,1964,0,4096,0,577,0,4096,0,2787,0,4096,0,1761,0,4096,0,1228,0,4097,0,177,0,4096,0,907,0,4096,0,2452,0,4096,0,1400,0,4096,0,334,0,4216,0,1781,0,4096,0,2604,0,4096,0,992,0,4096,0,931,0,64,0x7faffe2a0e80,0,0,48,0,65536,65536,0,0,30399,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42067,1751,0,48.0,327.0,0.0,262144.0,64,0x7f4e3f6d6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fcdfc71ce80,131072.0,131072.0,0.0,2580798.0,0.0,0.0,127933603.0,44561024.0,194339836406935,194339836425975 diff --git a/tests/workloads/kernel_verbose_5/MI100/sysinfo.csv b/tests/workloads/kernel_verbose_5/MI100/sysinfo.csv deleted file mode 100644 index d47d561271..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_5,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:09:52 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/kernel_verbose_5/MI100/timestamps.csv b/tests/workloads/kernel_verbose_5/MI100/timestamps.csv deleted file mode 100644 index 55ab5c0c9b..0000000000 --- a/tests/workloads/kernel_verbose_5/MI100/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,193214,193214,1048576,256,0,0,8,8,16,64,0x0,0x7f161346ce80,194339836137003,194339836161015,194339836185335,194339836198729 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,193214,193214,1048576,256,0,0,8,8,16,64,0x0,0x7f161346ce80,194339836198048,194339836365335,194339836384535,194339836385834 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,193214,193214,1048576,256,0,0,8,8,16,64,0x0,0x7f161346ce80,194339836397035,194339836406935,194339836425975,194339836426992 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/kernel_verbose_5/MI200/SQ_IFETCH_LEVEL.csv deleted file mode 100644 index 04f0b9eff5..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/SQ_IFETCH_LEVEL.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,353243,353243,1048576,256,0,0,8,0,16,64,0x0,0x7f22368d4ec0,27758,27758,16384,65536,13694,1543472,199842697294641,199855576360179,199855576380339,199842713192646 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,353243,353243,1048576,256,0,0,8,0,16,64,0x0,0x7f22368d4ec0,41938,41938,16384,65536,9427,1048652,199842713218094,199855576464819,199855576481459,199842713520406 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,353243,353243,1048576,256,0,0,8,0,16,64,0x0,0x7f22368d4ec0,41692,41692,16384,65536,9176,1048624,199842713550233,199855576502899,199855576518579,199842713708813 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_SMEM.csv deleted file mode 100644 index b2282f88d2..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_SMEM.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,353643,353643,1048576,256,0,0,8,0,16,64,0x0,0x7fd986054ec0,65536,173084,19363944,199843663138849,199855576360179,199855576380339,199843678826435 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,353643,353643,1048576,256,0,0,8,0,16,64,0x0,0x7fd986054ec0,65536,261280,29317904,199843678836955,199855576464819,199855576481459,199843679089202 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,353643,353643,1048576,256,0,0,8,0,16,64,0x0,0x7fd986054ec0,65536,261428,29254416,199843679116284,199855576502899,199855576518579,199843679262340 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/kernel_verbose_5/MI200/SQ_LEVEL_WAVES.csv deleted file mode 100644 index 8612883695..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/SQ_LEVEL_WAVES.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,354046,354046,1048576,256,0,0,8,0,16,64,0x0,0x7f88dc418ec0,28307,28307,10953,226464,16384,11233584,133850,0,45441188,199844616863730,199855576360179,199855576380339,199844632629614 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,354046,354046,1048576,256,0,0,8,0,16,64,0x0,0x7f88dc418ec0,41933,41933,14003,335472,16384,19589760,227074,0,78847996,199844632658339,199855576464819,199855576481459,199844632941905 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,354046,354046,1048576,256,0,0,8,0,16,64,0x0,0x7f88dc418ec0,41231,41231,13891,329856,16384,19366564,222291,0,77959488,199844632977062,199855576502899,199855576518579,199844633142895 diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_IFETCH_LEVEL.txt deleted file mode 100644 index 293092f641..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_IFETCH_LEVEL.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE SQ_WAVES SQ_IFETCH SQ_IFETCH_LEVEL SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_LDS.txt deleted file mode 100644 index 08439eedce..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_LDS.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_LDS SQ_INST_LEVEL_LDS SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt deleted file mode 100644 index 6cca322d4e..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM SQ_INST_LEVEL_SMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt deleted file mode 100644 index e527ad31ba..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VMEM SQ_INST_LEVEL_VMEM SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_LEVEL_WAVES.txt deleted file mode 100644 index 3f8e04adb3..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/SQ_LEVEL_WAVES.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: GRBM_COUNT GRBM_GUI_ACTIVE CPC_ME1_BUSY_FOR_PACKET_DECODE SQ_CYCLES SQ_WAVES SQ_WAVE_CYCLES SQ_BUSY_CYCLES SQ_LEVEL_WAVES SQ_ACCUM_PREV_HIRES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_0.txt deleted file mode 100644 index 4ffdc32149..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_CYCLES SQ_BUSY_CYCLES SQ_WAVES SQ_INSTS_VALU_CVT SQ_INSTS_VMEM_WR SQ_INSTS_VMEM_RD SQ_INSTS_VMEM SQ_INSTS_SALU GRBM_COUNT GRBM_GUI_ACTIVE TCP_GATE_EN1_sum TCP_GATE_EN2_sum TCP_TD_TCP_STALL_CYCLES_sum TCP_TCR_TCP_STALL_CYCLES_sum TA_TA_BUSY_sum TA_BUFFER_WAVEFRONTS_sum TD_TD_BUSY_sum TD_TC_STALL_sum SPI_CSN_WINDOW_VALID SPI_CSN_BUSY CPC_CPC_STAT_BUSY CPC_CPC_STAT_IDLE CPF_CPF_STAT_BUSY CPF_CPF_STAT_STALL TCC_CYCLE_sum TCC_BUSY_sum TCC_PROBE_sum TCC_PROBE_ALL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_1.txt deleted file mode 100644 index 6c277f4a37..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VSKIPPED SQ_INSTS SQ_INSTS_VALU SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 GRBM_SPI_BUSY TCP_READ_TAGCONFLICT_STALL_CYCLES_sum TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum TCP_TA_TCP_STATE_READ_sum TA_BUFFER_READ_WAVEFRONTS_sum TA_BUFFER_WRITE_WAVEFRONTS_sum TD_SPI_STALL_sum TD_LOAD_WAVEFRONT_sum SPI_CSN_NUM_THREADGROUPS SPI_CSN_WAVE CPC_CPC_TCIU_BUSY CPC_CPC_TCIU_IDLE CPF_CPF_TCIU_BUSY CPF_CPF_TCIU_STALL TCC_NC_REQ_sum TCC_UC_REQ_sum TCC_CC_REQ_sum TCC_RW_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_10.txt deleted file mode 100644 index 7053d4dce6..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_10.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_TC_DATA_WRITE_REQ SQC_TC_DATA_ATOMIC_REQ SQC_TC_STALL SQC_TC_REQ SQC_DCACHE_REQ_READ_16 SQC_ICACHE_REQ SQC_ICACHE_HITS SQC_ICACHE_MISSES - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_11.txt deleted file mode 100644 index 77ae8b461f..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_11.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_ICACHE_MISSES_DUPLICATE SQC_DCACHE_INPUT_VALID_READYB SQC_DCACHE_ATOMIC SQC_DCACHE_REQ_READ_8 SQC_DCACHE_REQ SQC_DCACHE_HITS SQC_DCACHE_MISSES SQC_DCACHE_MISSES_DUPLICATE - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_12.txt deleted file mode 100644 index dfb2cf65e5..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_12.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQC_DCACHE_REQ_READ_1 SQC_DCACHE_REQ_READ_2 SQC_DCACHE_REQ_READ_4 - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_13.txt deleted file mode 100644 index 062fc9644a..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_13.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_ATOMIC[0] TCC_CYCLE[0] TCC_EA_ATOMIC[0] TCC_EA_ATOMIC_LEVEL[0] TCC_ATOMIC[1] TCC_CYCLE[1] TCC_EA_ATOMIC[1] TCC_EA_ATOMIC_LEVEL[1] TCC_ATOMIC[2] TCC_CYCLE[2] TCC_EA_ATOMIC[2] TCC_EA_ATOMIC_LEVEL[2] TCC_ATOMIC[3] TCC_CYCLE[3] TCC_EA_ATOMIC[3] TCC_EA_ATOMIC_LEVEL[3] TCC_ATOMIC[4] TCC_CYCLE[4] TCC_EA_ATOMIC[4] TCC_EA_ATOMIC_LEVEL[4] TCC_ATOMIC[5] TCC_CYCLE[5] TCC_EA_ATOMIC[5] TCC_EA_ATOMIC_LEVEL[5] TCC_ATOMIC[6] TCC_CYCLE[6] TCC_EA_ATOMIC[6] TCC_EA_ATOMIC_LEVEL[6] TCC_ATOMIC[7] TCC_CYCLE[7] TCC_EA_ATOMIC[7] TCC_EA_ATOMIC_LEVEL[7] TCC_ATOMIC[8] TCC_CYCLE[8] TCC_EA_ATOMIC[8] TCC_EA_ATOMIC_LEVEL[8] TCC_ATOMIC[9] TCC_CYCLE[9] TCC_EA_ATOMIC[9] TCC_EA_ATOMIC_LEVEL[9] TCC_ATOMIC[10] TCC_CYCLE[10] TCC_EA_ATOMIC[10] TCC_EA_ATOMIC_LEVEL[10] TCC_ATOMIC[11] TCC_CYCLE[11] TCC_EA_ATOMIC[11] TCC_EA_ATOMIC_LEVEL[11] TCC_ATOMIC[12] TCC_CYCLE[12] TCC_EA_ATOMIC[12] TCC_EA_ATOMIC_LEVEL[12] TCC_ATOMIC[13] TCC_CYCLE[13] TCC_EA_ATOMIC[13] TCC_EA_ATOMIC_LEVEL[13] TCC_ATOMIC[14] TCC_CYCLE[14] TCC_EA_ATOMIC[14] TCC_EA_ATOMIC_LEVEL[14] TCC_ATOMIC[15] TCC_CYCLE[15] TCC_EA_ATOMIC[15] TCC_EA_ATOMIC_LEVEL[15] TCC_ATOMIC[16] TCC_CYCLE[16] TCC_EA_ATOMIC[16] TCC_EA_ATOMIC_LEVEL[16] TCC_ATOMIC[17] TCC_CYCLE[17] TCC_EA_ATOMIC[17] TCC_EA_ATOMIC_LEVEL[17] TCC_ATOMIC[18] TCC_CYCLE[18] TCC_EA_ATOMIC[18] TCC_EA_ATOMIC_LEVEL[18] TCC_ATOMIC[19] TCC_CYCLE[19] TCC_EA_ATOMIC[19] TCC_EA_ATOMIC_LEVEL[19] TCC_ATOMIC[20] TCC_CYCLE[20] TCC_EA_ATOMIC[20] TCC_EA_ATOMIC_LEVEL[20] TCC_ATOMIC[21] TCC_CYCLE[21] TCC_EA_ATOMIC[21] TCC_EA_ATOMIC_LEVEL[21] TCC_ATOMIC[22] TCC_CYCLE[22] TCC_EA_ATOMIC[22] TCC_EA_ATOMIC_LEVEL[22] TCC_ATOMIC[23] TCC_CYCLE[23] TCC_EA_ATOMIC[23] TCC_EA_ATOMIC_LEVEL[23] TCC_ATOMIC[24] TCC_CYCLE[24] TCC_EA_ATOMIC[24] TCC_EA_ATOMIC_LEVEL[24] TCC_ATOMIC[25] TCC_CYCLE[25] TCC_EA_ATOMIC[25] TCC_EA_ATOMIC_LEVEL[25] TCC_ATOMIC[26] TCC_CYCLE[26] TCC_EA_ATOMIC[26] TCC_EA_ATOMIC_LEVEL[26] TCC_ATOMIC[27] TCC_CYCLE[27] TCC_EA_ATOMIC[27] TCC_EA_ATOMIC_LEVEL[27] TCC_ATOMIC[28] TCC_CYCLE[28] TCC_EA_ATOMIC[28] TCC_EA_ATOMIC_LEVEL[28] TCC_ATOMIC[29] TCC_CYCLE[29] TCC_EA_ATOMIC[29] TCC_EA_ATOMIC_LEVEL[29] TCC_ATOMIC[30] TCC_CYCLE[30] TCC_EA_ATOMIC[30] TCC_EA_ATOMIC_LEVEL[30] TCC_ATOMIC[31] TCC_CYCLE[31] TCC_EA_ATOMIC[31] TCC_EA_ATOMIC_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_14.txt deleted file mode 100644 index e0698dbf57..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_14.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ[0] TCC_EA_RDREQ_32B[0] TCC_EA_RDREQ_DRAM_CREDIT_STALL[0] TCC_EA_RDREQ_GMI_CREDIT_STALL[0] TCC_EA_RDREQ[1] TCC_EA_RDREQ_32B[1] TCC_EA_RDREQ_DRAM_CREDIT_STALL[1] TCC_EA_RDREQ_GMI_CREDIT_STALL[1] TCC_EA_RDREQ[2] TCC_EA_RDREQ_32B[2] TCC_EA_RDREQ_DRAM_CREDIT_STALL[2] TCC_EA_RDREQ_GMI_CREDIT_STALL[2] TCC_EA_RDREQ[3] TCC_EA_RDREQ_32B[3] TCC_EA_RDREQ_DRAM_CREDIT_STALL[3] TCC_EA_RDREQ_GMI_CREDIT_STALL[3] TCC_EA_RDREQ[4] TCC_EA_RDREQ_32B[4] TCC_EA_RDREQ_DRAM_CREDIT_STALL[4] TCC_EA_RDREQ_GMI_CREDIT_STALL[4] TCC_EA_RDREQ[5] TCC_EA_RDREQ_32B[5] TCC_EA_RDREQ_DRAM_CREDIT_STALL[5] TCC_EA_RDREQ_GMI_CREDIT_STALL[5] TCC_EA_RDREQ[6] TCC_EA_RDREQ_32B[6] TCC_EA_RDREQ_DRAM_CREDIT_STALL[6] TCC_EA_RDREQ_GMI_CREDIT_STALL[6] TCC_EA_RDREQ[7] TCC_EA_RDREQ_32B[7] TCC_EA_RDREQ_DRAM_CREDIT_STALL[7] TCC_EA_RDREQ_GMI_CREDIT_STALL[7] TCC_EA_RDREQ[8] TCC_EA_RDREQ_32B[8] TCC_EA_RDREQ_DRAM_CREDIT_STALL[8] TCC_EA_RDREQ_GMI_CREDIT_STALL[8] TCC_EA_RDREQ[9] TCC_EA_RDREQ_32B[9] TCC_EA_RDREQ_DRAM_CREDIT_STALL[9] TCC_EA_RDREQ_GMI_CREDIT_STALL[9] TCC_EA_RDREQ[10] TCC_EA_RDREQ_32B[10] TCC_EA_RDREQ_DRAM_CREDIT_STALL[10] TCC_EA_RDREQ_GMI_CREDIT_STALL[10] TCC_EA_RDREQ[11] TCC_EA_RDREQ_32B[11] TCC_EA_RDREQ_DRAM_CREDIT_STALL[11] TCC_EA_RDREQ_GMI_CREDIT_STALL[11] TCC_EA_RDREQ[12] TCC_EA_RDREQ_32B[12] TCC_EA_RDREQ_DRAM_CREDIT_STALL[12] TCC_EA_RDREQ_GMI_CREDIT_STALL[12] TCC_EA_RDREQ[13] TCC_EA_RDREQ_32B[13] TCC_EA_RDREQ_DRAM_CREDIT_STALL[13] TCC_EA_RDREQ_GMI_CREDIT_STALL[13] TCC_EA_RDREQ[14] TCC_EA_RDREQ_32B[14] TCC_EA_RDREQ_DRAM_CREDIT_STALL[14] TCC_EA_RDREQ_GMI_CREDIT_STALL[14] TCC_EA_RDREQ[15] TCC_EA_RDREQ_32B[15] TCC_EA_RDREQ_DRAM_CREDIT_STALL[15] TCC_EA_RDREQ_GMI_CREDIT_STALL[15] TCC_EA_RDREQ[16] TCC_EA_RDREQ_32B[16] TCC_EA_RDREQ_DRAM_CREDIT_STALL[16] TCC_EA_RDREQ_GMI_CREDIT_STALL[16] TCC_EA_RDREQ[17] TCC_EA_RDREQ_32B[17] TCC_EA_RDREQ_DRAM_CREDIT_STALL[17] TCC_EA_RDREQ_GMI_CREDIT_STALL[17] TCC_EA_RDREQ[18] TCC_EA_RDREQ_32B[18] TCC_EA_RDREQ_DRAM_CREDIT_STALL[18] TCC_EA_RDREQ_GMI_CREDIT_STALL[18] TCC_EA_RDREQ[19] TCC_EA_RDREQ_32B[19] TCC_EA_RDREQ_DRAM_CREDIT_STALL[19] TCC_EA_RDREQ_GMI_CREDIT_STALL[19] TCC_EA_RDREQ[20] TCC_EA_RDREQ_32B[20] TCC_EA_RDREQ_DRAM_CREDIT_STALL[20] TCC_EA_RDREQ_GMI_CREDIT_STALL[20] TCC_EA_RDREQ[21] TCC_EA_RDREQ_32B[21] TCC_EA_RDREQ_DRAM_CREDIT_STALL[21] TCC_EA_RDREQ_GMI_CREDIT_STALL[21] TCC_EA_RDREQ[22] TCC_EA_RDREQ_32B[22] TCC_EA_RDREQ_DRAM_CREDIT_STALL[22] TCC_EA_RDREQ_GMI_CREDIT_STALL[22] TCC_EA_RDREQ[23] TCC_EA_RDREQ_32B[23] TCC_EA_RDREQ_DRAM_CREDIT_STALL[23] TCC_EA_RDREQ_GMI_CREDIT_STALL[23] TCC_EA_RDREQ[24] TCC_EA_RDREQ_32B[24] TCC_EA_RDREQ_DRAM_CREDIT_STALL[24] TCC_EA_RDREQ_GMI_CREDIT_STALL[24] TCC_EA_RDREQ[25] TCC_EA_RDREQ_32B[25] TCC_EA_RDREQ_DRAM_CREDIT_STALL[25] TCC_EA_RDREQ_GMI_CREDIT_STALL[25] TCC_EA_RDREQ[26] TCC_EA_RDREQ_32B[26] TCC_EA_RDREQ_DRAM_CREDIT_STALL[26] TCC_EA_RDREQ_GMI_CREDIT_STALL[26] TCC_EA_RDREQ[27] TCC_EA_RDREQ_32B[27] TCC_EA_RDREQ_DRAM_CREDIT_STALL[27] TCC_EA_RDREQ_GMI_CREDIT_STALL[27] TCC_EA_RDREQ[28] TCC_EA_RDREQ_32B[28] TCC_EA_RDREQ_DRAM_CREDIT_STALL[28] TCC_EA_RDREQ_GMI_CREDIT_STALL[28] TCC_EA_RDREQ[29] TCC_EA_RDREQ_32B[29] TCC_EA_RDREQ_DRAM_CREDIT_STALL[29] TCC_EA_RDREQ_GMI_CREDIT_STALL[29] TCC_EA_RDREQ[30] TCC_EA_RDREQ_32B[30] TCC_EA_RDREQ_DRAM_CREDIT_STALL[30] TCC_EA_RDREQ_GMI_CREDIT_STALL[30] TCC_EA_RDREQ[31] TCC_EA_RDREQ_32B[31] TCC_EA_RDREQ_DRAM_CREDIT_STALL[31] TCC_EA_RDREQ_GMI_CREDIT_STALL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_15.txt deleted file mode 100644 index 77ad088669..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_15.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_RDREQ_IO_CREDIT_STALL[0] TCC_EA_RDREQ_LEVEL[0] TCC_EA_WRREQ[0] TCC_EA_WRREQ_64B[0] TCC_EA_RDREQ_IO_CREDIT_STALL[1] TCC_EA_RDREQ_LEVEL[1] TCC_EA_WRREQ[1] TCC_EA_WRREQ_64B[1] TCC_EA_RDREQ_IO_CREDIT_STALL[2] TCC_EA_RDREQ_LEVEL[2] TCC_EA_WRREQ[2] TCC_EA_WRREQ_64B[2] TCC_EA_RDREQ_IO_CREDIT_STALL[3] TCC_EA_RDREQ_LEVEL[3] TCC_EA_WRREQ[3] TCC_EA_WRREQ_64B[3] TCC_EA_RDREQ_IO_CREDIT_STALL[4] TCC_EA_RDREQ_LEVEL[4] TCC_EA_WRREQ[4] TCC_EA_WRREQ_64B[4] TCC_EA_RDREQ_IO_CREDIT_STALL[5] TCC_EA_RDREQ_LEVEL[5] TCC_EA_WRREQ[5] TCC_EA_WRREQ_64B[5] TCC_EA_RDREQ_IO_CREDIT_STALL[6] TCC_EA_RDREQ_LEVEL[6] TCC_EA_WRREQ[6] TCC_EA_WRREQ_64B[6] TCC_EA_RDREQ_IO_CREDIT_STALL[7] TCC_EA_RDREQ_LEVEL[7] TCC_EA_WRREQ[7] TCC_EA_WRREQ_64B[7] TCC_EA_RDREQ_IO_CREDIT_STALL[8] TCC_EA_RDREQ_LEVEL[8] TCC_EA_WRREQ[8] TCC_EA_WRREQ_64B[8] TCC_EA_RDREQ_IO_CREDIT_STALL[9] TCC_EA_RDREQ_LEVEL[9] TCC_EA_WRREQ[9] TCC_EA_WRREQ_64B[9] TCC_EA_RDREQ_IO_CREDIT_STALL[10] TCC_EA_RDREQ_LEVEL[10] TCC_EA_WRREQ[10] TCC_EA_WRREQ_64B[10] TCC_EA_RDREQ_IO_CREDIT_STALL[11] TCC_EA_RDREQ_LEVEL[11] TCC_EA_WRREQ[11] TCC_EA_WRREQ_64B[11] TCC_EA_RDREQ_IO_CREDIT_STALL[12] TCC_EA_RDREQ_LEVEL[12] TCC_EA_WRREQ[12] TCC_EA_WRREQ_64B[12] TCC_EA_RDREQ_IO_CREDIT_STALL[13] TCC_EA_RDREQ_LEVEL[13] TCC_EA_WRREQ[13] TCC_EA_WRREQ_64B[13] TCC_EA_RDREQ_IO_CREDIT_STALL[14] TCC_EA_RDREQ_LEVEL[14] TCC_EA_WRREQ[14] TCC_EA_WRREQ_64B[14] TCC_EA_RDREQ_IO_CREDIT_STALL[15] TCC_EA_RDREQ_LEVEL[15] TCC_EA_WRREQ[15] TCC_EA_WRREQ_64B[15] TCC_EA_RDREQ_IO_CREDIT_STALL[16] TCC_EA_RDREQ_LEVEL[16] TCC_EA_WRREQ[16] TCC_EA_WRREQ_64B[16] TCC_EA_RDREQ_IO_CREDIT_STALL[17] TCC_EA_RDREQ_LEVEL[17] TCC_EA_WRREQ[17] TCC_EA_WRREQ_64B[17] TCC_EA_RDREQ_IO_CREDIT_STALL[18] TCC_EA_RDREQ_LEVEL[18] TCC_EA_WRREQ[18] TCC_EA_WRREQ_64B[18] TCC_EA_RDREQ_IO_CREDIT_STALL[19] TCC_EA_RDREQ_LEVEL[19] TCC_EA_WRREQ[19] TCC_EA_WRREQ_64B[19] TCC_EA_RDREQ_IO_CREDIT_STALL[20] TCC_EA_RDREQ_LEVEL[20] TCC_EA_WRREQ[20] TCC_EA_WRREQ_64B[20] TCC_EA_RDREQ_IO_CREDIT_STALL[21] TCC_EA_RDREQ_LEVEL[21] TCC_EA_WRREQ[21] TCC_EA_WRREQ_64B[21] TCC_EA_RDREQ_IO_CREDIT_STALL[22] TCC_EA_RDREQ_LEVEL[22] TCC_EA_WRREQ[22] TCC_EA_WRREQ_64B[22] TCC_EA_RDREQ_IO_CREDIT_STALL[23] TCC_EA_RDREQ_LEVEL[23] TCC_EA_WRREQ[23] TCC_EA_WRREQ_64B[23] TCC_EA_RDREQ_IO_CREDIT_STALL[24] TCC_EA_RDREQ_LEVEL[24] TCC_EA_WRREQ[24] TCC_EA_WRREQ_64B[24] TCC_EA_RDREQ_IO_CREDIT_STALL[25] TCC_EA_RDREQ_LEVEL[25] TCC_EA_WRREQ[25] TCC_EA_WRREQ_64B[25] TCC_EA_RDREQ_IO_CREDIT_STALL[26] TCC_EA_RDREQ_LEVEL[26] TCC_EA_WRREQ[26] TCC_EA_WRREQ_64B[26] TCC_EA_RDREQ_IO_CREDIT_STALL[27] TCC_EA_RDREQ_LEVEL[27] TCC_EA_WRREQ[27] TCC_EA_WRREQ_64B[27] TCC_EA_RDREQ_IO_CREDIT_STALL[28] TCC_EA_RDREQ_LEVEL[28] TCC_EA_WRREQ[28] TCC_EA_WRREQ_64B[28] TCC_EA_RDREQ_IO_CREDIT_STALL[29] TCC_EA_RDREQ_LEVEL[29] TCC_EA_WRREQ[29] TCC_EA_WRREQ_64B[29] TCC_EA_RDREQ_IO_CREDIT_STALL[30] TCC_EA_RDREQ_LEVEL[30] TCC_EA_WRREQ[30] TCC_EA_WRREQ_64B[30] TCC_EA_RDREQ_IO_CREDIT_STALL[31] TCC_EA_RDREQ_LEVEL[31] TCC_EA_WRREQ[31] TCC_EA_WRREQ_64B[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_16.txt deleted file mode 100644 index d0628bb948..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_16.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_EA_WRREQ_DRAM_CREDIT_STALL[0] TCC_EA_WRREQ_GMI_CREDIT_STALL[0] TCC_EA_WRREQ_IO_CREDIT_STALL[0] TCC_EA_WRREQ_LEVEL[0] TCC_EA_WRREQ_DRAM_CREDIT_STALL[1] TCC_EA_WRREQ_GMI_CREDIT_STALL[1] TCC_EA_WRREQ_IO_CREDIT_STALL[1] TCC_EA_WRREQ_LEVEL[1] TCC_EA_WRREQ_DRAM_CREDIT_STALL[2] TCC_EA_WRREQ_GMI_CREDIT_STALL[2] TCC_EA_WRREQ_IO_CREDIT_STALL[2] TCC_EA_WRREQ_LEVEL[2] TCC_EA_WRREQ_DRAM_CREDIT_STALL[3] TCC_EA_WRREQ_GMI_CREDIT_STALL[3] TCC_EA_WRREQ_IO_CREDIT_STALL[3] TCC_EA_WRREQ_LEVEL[3] TCC_EA_WRREQ_DRAM_CREDIT_STALL[4] TCC_EA_WRREQ_GMI_CREDIT_STALL[4] TCC_EA_WRREQ_IO_CREDIT_STALL[4] TCC_EA_WRREQ_LEVEL[4] TCC_EA_WRREQ_DRAM_CREDIT_STALL[5] TCC_EA_WRREQ_GMI_CREDIT_STALL[5] TCC_EA_WRREQ_IO_CREDIT_STALL[5] TCC_EA_WRREQ_LEVEL[5] TCC_EA_WRREQ_DRAM_CREDIT_STALL[6] TCC_EA_WRREQ_GMI_CREDIT_STALL[6] TCC_EA_WRREQ_IO_CREDIT_STALL[6] TCC_EA_WRREQ_LEVEL[6] TCC_EA_WRREQ_DRAM_CREDIT_STALL[7] TCC_EA_WRREQ_GMI_CREDIT_STALL[7] TCC_EA_WRREQ_IO_CREDIT_STALL[7] TCC_EA_WRREQ_LEVEL[7] TCC_EA_WRREQ_DRAM_CREDIT_STALL[8] TCC_EA_WRREQ_GMI_CREDIT_STALL[8] TCC_EA_WRREQ_IO_CREDIT_STALL[8] TCC_EA_WRREQ_LEVEL[8] TCC_EA_WRREQ_DRAM_CREDIT_STALL[9] TCC_EA_WRREQ_GMI_CREDIT_STALL[9] TCC_EA_WRREQ_IO_CREDIT_STALL[9] TCC_EA_WRREQ_LEVEL[9] TCC_EA_WRREQ_DRAM_CREDIT_STALL[10] TCC_EA_WRREQ_GMI_CREDIT_STALL[10] TCC_EA_WRREQ_IO_CREDIT_STALL[10] TCC_EA_WRREQ_LEVEL[10] TCC_EA_WRREQ_DRAM_CREDIT_STALL[11] TCC_EA_WRREQ_GMI_CREDIT_STALL[11] TCC_EA_WRREQ_IO_CREDIT_STALL[11] TCC_EA_WRREQ_LEVEL[11] TCC_EA_WRREQ_DRAM_CREDIT_STALL[12] TCC_EA_WRREQ_GMI_CREDIT_STALL[12] TCC_EA_WRREQ_IO_CREDIT_STALL[12] TCC_EA_WRREQ_LEVEL[12] TCC_EA_WRREQ_DRAM_CREDIT_STALL[13] TCC_EA_WRREQ_GMI_CREDIT_STALL[13] TCC_EA_WRREQ_IO_CREDIT_STALL[13] TCC_EA_WRREQ_LEVEL[13] TCC_EA_WRREQ_DRAM_CREDIT_STALL[14] TCC_EA_WRREQ_GMI_CREDIT_STALL[14] TCC_EA_WRREQ_IO_CREDIT_STALL[14] TCC_EA_WRREQ_LEVEL[14] TCC_EA_WRREQ_DRAM_CREDIT_STALL[15] TCC_EA_WRREQ_GMI_CREDIT_STALL[15] TCC_EA_WRREQ_IO_CREDIT_STALL[15] TCC_EA_WRREQ_LEVEL[15] TCC_EA_WRREQ_DRAM_CREDIT_STALL[16] TCC_EA_WRREQ_GMI_CREDIT_STALL[16] TCC_EA_WRREQ_IO_CREDIT_STALL[16] TCC_EA_WRREQ_LEVEL[16] TCC_EA_WRREQ_DRAM_CREDIT_STALL[17] TCC_EA_WRREQ_GMI_CREDIT_STALL[17] TCC_EA_WRREQ_IO_CREDIT_STALL[17] TCC_EA_WRREQ_LEVEL[17] TCC_EA_WRREQ_DRAM_CREDIT_STALL[18] TCC_EA_WRREQ_GMI_CREDIT_STALL[18] TCC_EA_WRREQ_IO_CREDIT_STALL[18] TCC_EA_WRREQ_LEVEL[18] TCC_EA_WRREQ_DRAM_CREDIT_STALL[19] TCC_EA_WRREQ_GMI_CREDIT_STALL[19] TCC_EA_WRREQ_IO_CREDIT_STALL[19] TCC_EA_WRREQ_LEVEL[19] TCC_EA_WRREQ_DRAM_CREDIT_STALL[20] TCC_EA_WRREQ_GMI_CREDIT_STALL[20] TCC_EA_WRREQ_IO_CREDIT_STALL[20] TCC_EA_WRREQ_LEVEL[20] TCC_EA_WRREQ_DRAM_CREDIT_STALL[21] TCC_EA_WRREQ_GMI_CREDIT_STALL[21] TCC_EA_WRREQ_IO_CREDIT_STALL[21] TCC_EA_WRREQ_LEVEL[21] TCC_EA_WRREQ_DRAM_CREDIT_STALL[22] TCC_EA_WRREQ_GMI_CREDIT_STALL[22] TCC_EA_WRREQ_IO_CREDIT_STALL[22] TCC_EA_WRREQ_LEVEL[22] TCC_EA_WRREQ_DRAM_CREDIT_STALL[23] TCC_EA_WRREQ_GMI_CREDIT_STALL[23] TCC_EA_WRREQ_IO_CREDIT_STALL[23] TCC_EA_WRREQ_LEVEL[23] TCC_EA_WRREQ_DRAM_CREDIT_STALL[24] TCC_EA_WRREQ_GMI_CREDIT_STALL[24] TCC_EA_WRREQ_IO_CREDIT_STALL[24] TCC_EA_WRREQ_LEVEL[24] TCC_EA_WRREQ_DRAM_CREDIT_STALL[25] TCC_EA_WRREQ_GMI_CREDIT_STALL[25] TCC_EA_WRREQ_IO_CREDIT_STALL[25] TCC_EA_WRREQ_LEVEL[25] TCC_EA_WRREQ_DRAM_CREDIT_STALL[26] TCC_EA_WRREQ_GMI_CREDIT_STALL[26] TCC_EA_WRREQ_IO_CREDIT_STALL[26] TCC_EA_WRREQ_LEVEL[26] TCC_EA_WRREQ_DRAM_CREDIT_STALL[27] TCC_EA_WRREQ_GMI_CREDIT_STALL[27] TCC_EA_WRREQ_IO_CREDIT_STALL[27] TCC_EA_WRREQ_LEVEL[27] TCC_EA_WRREQ_DRAM_CREDIT_STALL[28] TCC_EA_WRREQ_GMI_CREDIT_STALL[28] TCC_EA_WRREQ_IO_CREDIT_STALL[28] TCC_EA_WRREQ_LEVEL[28] TCC_EA_WRREQ_DRAM_CREDIT_STALL[29] TCC_EA_WRREQ_GMI_CREDIT_STALL[29] TCC_EA_WRREQ_IO_CREDIT_STALL[29] TCC_EA_WRREQ_LEVEL[29] TCC_EA_WRREQ_DRAM_CREDIT_STALL[30] TCC_EA_WRREQ_GMI_CREDIT_STALL[30] TCC_EA_WRREQ_IO_CREDIT_STALL[30] TCC_EA_WRREQ_LEVEL[30] TCC_EA_WRREQ_DRAM_CREDIT_STALL[31] TCC_EA_WRREQ_GMI_CREDIT_STALL[31] TCC_EA_WRREQ_IO_CREDIT_STALL[31] TCC_EA_WRREQ_LEVEL[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_17.txt deleted file mode 100644 index 343869c5f1..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_17.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_HIT[0] TCC_MISS[0] TCC_READ[0] TCC_REQ[0] TCC_HIT[1] TCC_MISS[1] TCC_READ[1] TCC_REQ[1] TCC_HIT[2] TCC_MISS[2] TCC_READ[2] TCC_REQ[2] TCC_HIT[3] TCC_MISS[3] TCC_READ[3] TCC_REQ[3] TCC_HIT[4] TCC_MISS[4] TCC_READ[4] TCC_REQ[4] TCC_HIT[5] TCC_MISS[5] TCC_READ[5] TCC_REQ[5] TCC_HIT[6] TCC_MISS[6] TCC_READ[6] TCC_REQ[6] TCC_HIT[7] TCC_MISS[7] TCC_READ[7] TCC_REQ[7] TCC_HIT[8] TCC_MISS[8] TCC_READ[8] TCC_REQ[8] TCC_HIT[9] TCC_MISS[9] TCC_READ[9] TCC_REQ[9] TCC_HIT[10] TCC_MISS[10] TCC_READ[10] TCC_REQ[10] TCC_HIT[11] TCC_MISS[11] TCC_READ[11] TCC_REQ[11] TCC_HIT[12] TCC_MISS[12] TCC_READ[12] TCC_REQ[12] TCC_HIT[13] TCC_MISS[13] TCC_READ[13] TCC_REQ[13] TCC_HIT[14] TCC_MISS[14] TCC_READ[14] TCC_REQ[14] TCC_HIT[15] TCC_MISS[15] TCC_READ[15] TCC_REQ[15] TCC_HIT[16] TCC_MISS[16] TCC_READ[16] TCC_REQ[16] TCC_HIT[17] TCC_MISS[17] TCC_READ[17] TCC_REQ[17] TCC_HIT[18] TCC_MISS[18] TCC_READ[18] TCC_REQ[18] TCC_HIT[19] TCC_MISS[19] TCC_READ[19] TCC_REQ[19] TCC_HIT[20] TCC_MISS[20] TCC_READ[20] TCC_REQ[20] TCC_HIT[21] TCC_MISS[21] TCC_READ[21] TCC_REQ[21] TCC_HIT[22] TCC_MISS[22] TCC_READ[22] TCC_REQ[22] TCC_HIT[23] TCC_MISS[23] TCC_READ[23] TCC_REQ[23] TCC_HIT[24] TCC_MISS[24] TCC_READ[24] TCC_REQ[24] TCC_HIT[25] TCC_MISS[25] TCC_READ[25] TCC_REQ[25] TCC_HIT[26] TCC_MISS[26] TCC_READ[26] TCC_REQ[26] TCC_HIT[27] TCC_MISS[27] TCC_READ[27] TCC_REQ[27] TCC_HIT[28] TCC_MISS[28] TCC_READ[28] TCC_REQ[28] TCC_HIT[29] TCC_MISS[29] TCC_READ[29] TCC_REQ[29] TCC_HIT[30] TCC_MISS[30] TCC_READ[30] TCC_REQ[30] TCC_HIT[31] TCC_MISS[31] TCC_READ[31] TCC_REQ[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_18.txt deleted file mode 100644 index a74cefd281..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_18.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: TCC_RW_REQ[0] TCC_TOO_MANY_EA_WRREQS_STALL[0] TCC_WRITE[0] TCC_RW_REQ[1] TCC_TOO_MANY_EA_WRREQS_STALL[1] TCC_WRITE[1] TCC_RW_REQ[2] TCC_TOO_MANY_EA_WRREQS_STALL[2] TCC_WRITE[2] TCC_RW_REQ[3] TCC_TOO_MANY_EA_WRREQS_STALL[3] TCC_WRITE[3] TCC_RW_REQ[4] TCC_TOO_MANY_EA_WRREQS_STALL[4] TCC_WRITE[4] TCC_RW_REQ[5] TCC_TOO_MANY_EA_WRREQS_STALL[5] TCC_WRITE[5] TCC_RW_REQ[6] TCC_TOO_MANY_EA_WRREQS_STALL[6] TCC_WRITE[6] TCC_RW_REQ[7] TCC_TOO_MANY_EA_WRREQS_STALL[7] TCC_WRITE[7] TCC_RW_REQ[8] TCC_TOO_MANY_EA_WRREQS_STALL[8] TCC_WRITE[8] TCC_RW_REQ[9] TCC_TOO_MANY_EA_WRREQS_STALL[9] TCC_WRITE[9] TCC_RW_REQ[10] TCC_TOO_MANY_EA_WRREQS_STALL[10] TCC_WRITE[10] TCC_RW_REQ[11] TCC_TOO_MANY_EA_WRREQS_STALL[11] TCC_WRITE[11] TCC_RW_REQ[12] TCC_TOO_MANY_EA_WRREQS_STALL[12] TCC_WRITE[12] TCC_RW_REQ[13] TCC_TOO_MANY_EA_WRREQS_STALL[13] TCC_WRITE[13] TCC_RW_REQ[14] TCC_TOO_MANY_EA_WRREQS_STALL[14] TCC_WRITE[14] TCC_RW_REQ[15] TCC_TOO_MANY_EA_WRREQS_STALL[15] TCC_WRITE[15] TCC_RW_REQ[16] TCC_TOO_MANY_EA_WRREQS_STALL[16] TCC_WRITE[16] TCC_RW_REQ[17] TCC_TOO_MANY_EA_WRREQS_STALL[17] TCC_WRITE[17] TCC_RW_REQ[18] TCC_TOO_MANY_EA_WRREQS_STALL[18] TCC_WRITE[18] TCC_RW_REQ[19] TCC_TOO_MANY_EA_WRREQS_STALL[19] TCC_WRITE[19] TCC_RW_REQ[20] TCC_TOO_MANY_EA_WRREQS_STALL[20] TCC_WRITE[20] TCC_RW_REQ[21] TCC_TOO_MANY_EA_WRREQS_STALL[21] TCC_WRITE[21] TCC_RW_REQ[22] TCC_TOO_MANY_EA_WRREQS_STALL[22] TCC_WRITE[22] TCC_RW_REQ[23] TCC_TOO_MANY_EA_WRREQS_STALL[23] TCC_WRITE[23] TCC_RW_REQ[24] TCC_TOO_MANY_EA_WRREQS_STALL[24] TCC_WRITE[24] TCC_RW_REQ[25] TCC_TOO_MANY_EA_WRREQS_STALL[25] TCC_WRITE[25] TCC_RW_REQ[26] TCC_TOO_MANY_EA_WRREQS_STALL[26] TCC_WRITE[26] TCC_RW_REQ[27] TCC_TOO_MANY_EA_WRREQS_STALL[27] TCC_WRITE[27] TCC_RW_REQ[28] TCC_TOO_MANY_EA_WRREQS_STALL[28] TCC_WRITE[28] TCC_RW_REQ[29] TCC_TOO_MANY_EA_WRREQS_STALL[29] TCC_WRITE[29] TCC_RW_REQ[30] TCC_TOO_MANY_EA_WRREQS_STALL[30] TCC_WRITE[30] TCC_RW_REQ[31] TCC_TOO_MANY_EA_WRREQS_STALL[31] TCC_WRITE[31] - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_2.txt deleted file mode 100644 index 70b69f8928..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_INT32 TCP_VOLATILE_sum TCP_TOTAL_ACCESSES_sum TCP_TOTAL_READ_sum TCP_TOTAL_WRITE_sum TA_BUFFER_ATOMIC_WAVEFRONTS_sum TA_BUFFER_TOTAL_CYCLES_sum TD_ATOMIC_WAVEFRONT_sum TD_STORE_WAVEFRONT_sum SPI_RA_REQ_NO_ALLOC SPI_RA_REQ_NO_ALLOC_CSN CPC_CPC_STAT_STALL CPC_UTCL1_STALL_ON_TRANSLATION CPF_CPF_STAT_IDLE CPF_CPF_TCIU_IDLE TCC_REQ_sum TCC_STREAMING_REQ_sum TCC_HIT_sum TCC_MISS_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_3.txt deleted file mode 100644 index e47f8e33c9..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_3.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_INT64 SQ_INSTS_SMEM SQ_INSTS_FLAT SQ_INSTS_LDS SQ_INSTS_GDS SQ_INSTS_EXP_GDS SQ_INSTS_BRANCH SQ_INSTS_SENDMSG TCP_TOTAL_ATOMIC_WITH_RET_sum TCP_TOTAL_ATOMIC_WITHOUT_RET_sum TCP_TOTAL_WRITEBACK_INVALIDATES_sum TCP_TOTAL_CACHE_ACCESSES_sum TA_BUFFER_COALESCED_READ_CYCLES_sum TA_BUFFER_COALESCED_WRITE_CYCLES_sum TD_COALESCABLE_WAVEFRONT_sum SPI_RA_RES_STALL_CSN SPI_RA_TMP_STALL_CSN CPC_CPC_UTCL2IU_BUSY CPC_CPC_UTCL2IU_IDLE CPF_CMP_UTCL1_STALL_ON_TRANSLATION TCC_READ_sum TCC_WRITE_sum TCC_ATOMIC_sum TCC_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_4.txt deleted file mode 100644 index 2d96f365a9..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_4.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVE_CYCLES SQ_WAIT_ANY SQ_WAIT_INST_ANY SQ_ACTIVE_INST_ANY SQ_BUSY_CU_CYCLES SQ_ACTIVE_INST_VMEM SQ_ACTIVE_INST_LDS SQ_ACTIVE_INST_VALU TCP_UTCL1_TRANSLATION_MISS_sum TCP_UTCL1_TRANSLATION_HIT_sum TCP_UTCL1_PERMISSION_MISS_sum TCP_UTCL1_REQUEST_sum TA_ADDR_STALLED_BY_TC_CYCLES_sum TA_TOTAL_WAVEFRONTS_sum SPI_RA_WAVE_SIMD_FULL_CSN SPI_RA_VGPR_SIMD_FULL_CSN CPC_CPC_UTCL2IU_STALL CPC_ME1_BUSY_FOR_PACKET_DECODE TCC_EA_WRREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WR_UNCACHED_32B_sum TCC_EA_WRREQ_DRAM_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_5.txt deleted file mode 100644 index e50beed390..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_5.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_ACTIVE_INST_SCA SQ_ACTIVE_INST_EXP_GDS SQ_ACTIVE_INST_MISC SQ_ACTIVE_INST_FLAT SQ_INST_CYCLES_VMEM_WR SQ_INST_CYCLES_VMEM_RD SQ_INST_CYCLES_SMEM SQ_INST_CYCLES_SALU TCP_TCP_LATENCY_sum TCP_TCC_READ_REQ_LATENCY_sum TCP_TCC_WRITE_REQ_LATENCY_sum TCP_TCC_READ_REQ_sum TA_ADDR_STALLED_BY_TD_CYCLES_sum TA_DATA_STALLED_BY_TC_CYCLES_sum SPI_RA_SGPR_SIMD_FULL_CSN SPI_RA_LDS_CU_FULL_CSN CPC_ME1_DC0_SPI_BUSY TCC_EA_WRREQ_STALL_sum TCC_EA_RDREQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RD_UNCACHED_32B_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_6.txt deleted file mode 100644 index 15a2277c1b..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_6.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_THREAD_CYCLES_VALU SQ_IFETCH SQ_LDS_BANK_CONFLICT SQ_LDS_ADDR_CONFLICT SQ_LDS_UNALIGNED_STALL SQ_WAVES_EQ_64 SQ_WAVES_LT_64 SQ_WAVES_LT_48 TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum TCP_TCC_NC_READ_REQ_sum TA_FLAT_WAVEFRONTS_sum TA_FLAT_READ_WAVEFRONTS_sum SPI_RA_BAR_CU_FULL_CSN SPI_RA_TGLIM_CU_FULL_CSN TCC_EA_RDREQ_DRAM_sum TCC_TAG_STALL_sum TCC_NORMAL_WRITEBACK_sum TCC_ALL_TC_OP_WB_WRITEBACK_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_7.txt deleted file mode 100644 index b42ce91618..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_7.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_WAVES_LT_32 SQ_WAVES_LT_16 SQ_ITEMS SQ_LDS_MEM_VIOLATIONS SQ_LDS_ATOMIC_RETURN SQ_LDS_IDX_ACTIVE SQ_WAVES_RESTORED SQ_WAVES_SAVED TCP_TCC_NC_WRITE_REQ_sum TCP_TCC_NC_ATOMIC_REQ_sum TCP_TCC_UC_READ_REQ_sum TCP_TCC_UC_WRITE_REQ_sum TA_FLAT_WRITE_WAVEFRONTS_sum TA_FLAT_ATOMIC_WAVEFRONTS_sum SPI_RA_WVLIM_STALL_CSN SPI_SWC_CSC_WR TCC_NORMAL_EVICT_sum TCC_ALL_TC_OP_INV_EVICT_sum TCC_TOO_MANY_EA_WRREQS_STALL_sum TCC_EA_ATOMIC_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_8.txt deleted file mode 100644 index 21d4c7a998..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_8.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_SMEM_NORM SQ_INSTS_MFMA SQ_INSTS_VALU_MFMA_I8 SQ_INSTS_VALU_MFMA_F16 SQ_INSTS_VALU_MFMA_BF16 SQ_INSTS_VALU_MFMA_F32 SQ_INSTS_VALU_MFMA_F64 SQ_VALU_MFMA_BUSY_CYCLES TCP_TCC_UC_ATOMIC_REQ_sum TCP_TCC_CC_READ_REQ_sum TCP_TCC_CC_WRITE_REQ_sum TCP_TCC_CC_ATOMIC_REQ_sum SPI_VWC_CSC_WR SPI_RA_BULKY_CU_FULL_CSN TCC_EA_RDREQ_LEVEL_sum TCC_EA_WRREQ_LEVEL_sum TCC_EA_ATOMIC_LEVEL_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_9.txt deleted file mode 100644 index 9ffe5778c3..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/pmc_perf_9.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_FLAT_LDS_ONLY SQ_INSTS_VALU_MFMA_MOPS_I8 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 SQC_TC_INST_REQ SQC_TC_DATA_READ_REQ TCP_TCC_RW_READ_REQ_sum TCP_TCC_RW_WRITE_REQ_sum TCP_TCC_RW_ATOMIC_REQ_sum TCP_PENDING_STALL_CYCLES_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/perfmon/timestamps.txt b/tests/workloads/kernel_verbose_5/MI200/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/kernel_verbose_5/MI200/pmc_perf.csv b/tests/workloads/kernel_verbose_5/MI200/pmc_perf.csv deleted file mode 100644 index 68b236abe3..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/pmc_perf.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_1,obj_1,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_2,obj_2,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_3,obj_3,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_4,obj_4,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_7,obj_7,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_8,obj_8,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_9,obj_9,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_10,obj_10,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_11,obj_11,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_14,obj_14,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_15,obj_15,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_16,obj_16,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_17,obj_17,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_18,obj_18,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7faf0bc30ec0,230680,131907,16384,0,16384,16384,32768,49152,28834,28834,1992463.0,1416205.0,3424.0,151322.0,1123559.0,0.0,1408683.0,1111503.0,228969,140030,28834,0,28834,0,922688.0,493585.0,0.0,0.0,64,0x7f3fa0d08ec0,10920182,9928588,647530,344064,1635530,0,0,163840,832.0,515136.0,0.0,524288.0,263908.0,32768.0,484575,0,0,10847,131072.0,131072.0,0.0,131072.0,64,0x7fee1fd78ec0,0,1294043,4096,4096,0,1179623,4096,4096,0,1343759,4096,4096,0,1307993,4096,4096,0,1140025,4096,4096,0,1612067,4096,4096,0,1186362,4096,4096,0,1315869,4096,4096,0,1131318,4096,4096,0,1133330,4096,4096,0,1108961,4096,4096,0,1305492,4096,4096,0,1187943,4096,4096,0,1145887,4096,4096,0,1313106,4096,4096,0,1324761,4096,4096,0,1198429,4096,4096,0,1207007,4096,4096,0,1131412,4096,4096,0,1383544,4096,4096,0,1029790,4096,4096,0,1819610,4096,4096,0,1462597,4096,4096,0,1176151,4096,4096,0,1129491,4096,4096,0,1106642,4096,4096,0,1224066,4096,4096,0,1140871,4096,4096,0,1248507,4096,4096,0,1062605,4096,4096,0,1166831,4096,4096,0,1345424,4096,4096,64,0x7fcdf8740ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12268,18688,7820,545,0,26156,204286.0,0.0,73206.0,131080.0,64,0x7fe6bad74ec0,0,393216,163840,0,0,0,0,0,18307,0.0,0.0,0.0,32768.0,0.0,0.0,381.0,32768.0,4096,16384,352,28734,1982,0,56.0,7.0,0.0,204399.0,64,0x7f0732708ec0,6336,0,4096,6376,0,4096,6376,0,4096,6449,0,4096,6360,0,4096,6390,0,4096,6364,0,4096,6395,0,4096,6398,0,4096,6340,0,4096,6376,0,4096,6376,0,4096,6453,0,4096,6364,0,4096,6394,0,4096,6364,0,4096,6339,0,4096,6390,0,4096,6376,0,4096,6349,0,4096,6422,0,4096,6412,0,4096,6374,0,4096,6582,0,4096,6415,0,4096,6340,0,4096,6393,0,4096,6378,0,4096,6347,0,4096,6425,0,4096,6415,0,4096,6375,0,4096,64,0x7f779dc18ec0,2218,4099,2221,6317,2301,4096,2301,6397,2289,4096,2289,6385,2323,4096,2323,6419,2287,4096,2287,6383,2291,4096,2291,6387,2247,4096,2247,6343,2297,4096,2297,6393,2295,4096,2295,6391,2220,4096,2220,6316,2307,4096,2307,6403,2290,4096,2290,6386,2325,4096,2325,6421,2291,4096,2291,6387,2290,4096,2290,6386,2251,4096,2251,6347,2274,4096,2274,6370,2283,4096,2283,6379,2280,4098,2282,6378,2283,4096,2283,6379,2322,4096,2322,6418,2323,4096,2323,6419,2296,4096,2296,6392,2441,4098,2443,6539,2274,4096,2274,6370,2272,4096,2272,6368,2283,4096,2283,6379,2279,4096,2279,6375,2290,4096,2290,6386,2326,4096,2326,6422,2327,4096,2327,6423,2349,4097,2350,6446,64,0x7f2de1778ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f6e6cc84ec0,4096,0,14,0,4096,0,151,0,4096,0,0,0,4096,0,232,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,91,0,4096,0,76,0,4096,0,46,0,4096,0,68,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,65,0,4097,0,147,0,4097,0,6,0,4096,0,65,0,4096,0,17,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,77,0,4100,0,0,0,4096,0,82,0,4096,0,215,0,4096,0,26,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f0da5fd0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10375,0,814,26950,0,73182.0,131072.0,0.0,65568.0,64,0x7fafe65c4ec0,0,0,0,224,0,65536,64215,56,64,0x7fb469ab8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,34503.0,46188.0,19348.0,64,0x7f01a6500ec0,0,0,0,1092005,0,0,0,1089074,0,0,0,1035974,0,0,0,1162858,21,0,0,1221153,97,0,0,1207141,0,0,0,1054401,0,0,0,1132993,0,0,0,1000441,0,0,0,1083011,0,0,0,1022785,0,0,0,1026577,0,0,0,958099,0,0,0,1079211,191,0,0,1244224,9,0,0,1233237,0,0,0,1043911,0,0,0,1074089,4,0,0,1073967,264,0,0,1390233,0,0,0,993520,0,0,0,1068643,0,0,0,1059660,0,0,0,1134638,0,0,0,1168395,0,0,0,988146,0,0,0,1043386,0,0,0,1223013,0,0,0,1170092,0,0,0,995145,0,0,0,1070150,0,0,0,1165258,64,0x7f14d1ef4ec0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,0,27878,0,0,64,0x7fa9abb20ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,987560.0,64,0x7f45db7a0ec0,114688,0,32768,32768,16384,16384,65536,49152,27583386.0,86084092.0,39380069.0,131072.0,0.0,197650.0,0,0,15345,808.0,131080.0,0.0,8.0,64,0x7f4ab1148ec0,32768,32768,0,64,0x7f919f270ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39771619.0,35264159.0,0.0,64,0x7f2c30ad0ec0,1223,117633,0,0,65536,63800,56,1680,199855576360179,199855576380339 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7faf0bc30ec0,303864,210822,16384,0,16384,16384,32768,49152,37982,37982,3017252.0,2430599.0,5004.0,392631.0,1603801.0,0.0,2418147.0,2109628.0,303856,219933,37982,0,37982,0,1215424.0,782486.0,0.0,0.0,64,0x7f3fa0d08ec0,17457179,16858737,254378,344064,2526932,0,0,163840,0.0,524288.0,0.0,524288.0,534338.0,32768.0,737631,0,0,11538,90762.0,90762.0,0.0,90762.0,64,0x7fee1fd78ec0,0,3118224,2832,2832,0,3261055,2876,2876,0,3655187,2876,2876,0,3725380,2876,2876,0,3655126,2890,2890,0,4218172,2852,2852,0,3800127,2892,2892,0,3247809,2828,2828,0,3713563,2828,2828,0,2704879,2832,2832,0,3180484,2876,2876,0,3445378,2876,2876,0,3438040,2872,2872,0,3949512,2884,2884,0,3914862,2848,2848,0,3064322,2892,2892,0,3261739,2824,2824,0,4429124,2874,2874,0,3383179,2844,2844,0,3517378,2844,2844,0,3357375,2828,2828,0,3737385,2900,2900,0,4115302,2846,2846,0,3843878,2824,2824,0,3894509,2824,2824,0,3078837,2824,2824,0,3642306,2876,2876,0,3805127,2844,2844,0,3120755,2844,2844,0,3299928,2828,2828,0,3075429,2900,2900,0,3865800,2848,2848,64,0x7fcdf8740ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31503,27653,9598,2884,0,39454,200900.0,0.0,69815.0,131085.0,64,0x7fe6bad74ec0,0,393216,163840,0,0,0,0,0,29913,0.0,0.0,0.0,32768.0,0.0,0.0,241.0,32768.0,4096,16384,302,41069,2026,0,56.0,10.0,0.0,201195.0,64,0x7f0732708ec0,6275,0,4096,6266,0,4096,6246,0,4096,6263,0,4096,6242,0,4096,6236,0,4096,6254,0,4096,6259,0,4096,6258,0,4096,6278,0,4096,6265,0,4096,6247,0,4096,6267,0,4096,6243,0,4096,6233,0,4096,6256,0,4096,6274,0,4096,6258,0,4096,6265,0,4096,6252,0,4096,6262,0,4096,6254,0,4096,6227,0,4096,6223,0,4096,6223,0,4096,6274,0,4096,6264,0,4096,6265,0,4096,6260,0,4096,6265,0,4096,6257,0,4096,6229,0,4096,64,0x7f779dc18ec0,2212,4100,2216,6312,2229,4098,2231,6327,2217,4097,2218,6314,2181,4096,2181,6277,2179,4096,2179,6275,2194,4096,2194,6290,2168,4096,2168,6264,2177,4096,2177,6273,2177,4096,2177,6273,2211,4096,2211,6307,2233,4096,2233,6329,2217,4096,2217,6313,2184,4096,2184,6280,2185,4096,2185,6281,2198,4096,2198,6294,2168,4096,2168,6264,2169,4096,2169,6265,2203,4096,2203,6299,2235,4098,2237,6333,2212,4096,2212,6308,2189,4096,2189,6285,2193,4096,2193,6289,2134,4096,2134,6230,2178,4096,2178,6274,2182,4096,2182,6278,2166,4096,2166,6262,2200,4096,2200,6296,2244,4097,2245,6341,2209,4096,2209,6305,2187,4096,2187,6283,2194,4096,2194,6290,2198,4097,2199,6295,64,0x7f2de1778ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f6e6cc84ec0,4096,0,298,0,4096,0,57,0,4098,0,121,0,4096,0,871,0,4097,0,927,0,4096,0,538,0,4096,0,1030,0,4096,0,1340,0,4096,0,557,0,4096,0,313,0,4096,0,554,0,4096,0,611,0,4097,0,292,0,4096,0,2357,0,4096,0,1070,0,4097,0,1090,0,4096,0,898,0,4097,0,1084,0,4097,0,752,0,4096,0,447,0,4096,0,1710,0,4096,0,610,0,4096,0,625,0,4096,0,1619,0,4096,0,1520,0,4100,0,125,0,4096,0,426,0,4096,0,683,0,4097,0,1464,0,4096,0,530,0,4096,0,1195,0,4096,0,738,0,64,0x7f0da5fd0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21337,0,2714,38454,0,69733.0,131072.0,0.0,45609.0,64,0x7fafe65c4ec0,0,0,0,56,0,65536,65536,0,64,0x7fb469ab8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,105091.0,45612.0,0.0,64,0x7f01a6500ec0,0,0,0,1547715,0,0,0,1895436,0,0,0,1639521,0,0,0,1912827,64,0,0,1748731,1139,0,0,2134241,0,0,0,1581029,266,0,0,2089147,0,0,0,1839559,0,0,0,1511723,0,0,0,1853730,0,0,0,1998002,0,0,0,1471157,26,0,0,1845058,0,0,0,2011350,0,0,0,1667585,0,0,0,1849370,0,0,0,1901748,81,0,0,1879494,171,0,0,2133104,0,0,0,1516145,280,0,0,1881994,32,0,0,1987480,0,0,0,2122447,0,0,0,1580493,0,0,0,1972374,0,0,0,1673834,0,0,0,1760131,0,0,0,1667013,0,0,0,1445299,26,0,0,1763949,138,0,0,2052419,64,0x7f14d1ef4ec0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,0,41274,0,0,64,0x7fa9abb20ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2003653.0,64,0x7f45db7a0ec0,114688,0,32768,32768,16384,16384,65536,49152,57785445.0,195794080.0,46777541.0,131072.0,0.0,506614.0,0,0,23278,3912.0,131073.0,0.0,0.0,64,0x7f4ab1148ec0,32768,32768,0,64,0x7f919f270ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118741265.0,58141396.0,0.0,64,0x7f2c30ad0ec0,0,204845,0,0,65536,63800,56,1680,199855576464819,199855576481459 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7faf0bc30ec0,328312,221517,16384,0,16384,16384,32768,49152,41038,41038,3156901.0,2474907.0,4814.0,365446.0,1623645.0,0.0,2461722.0,2154515.0,328304,231043,41038,0,41038,0,1313216.0,767227.0,0.0,0.0,64,0x7f3fa0d08ec0,19141904,18041249,756591,344064,2767961,0,0,163840,832.0,515146.0,0.0,524288.0,579320.0,32768.0,961827,0,0,13250,91256.0,91256.0,0.0,91256.0,64,0x7fee1fd78ec0,0,3317020,2824,2824,0,3917642,2872,2872,0,3669871,2860,2860,0,4815879,2868,2868,0,3724570,2870,2870,0,4117769,2848,2848,0,3483454,2868,2868,0,4210386,2828,2828,0,3168618,2828,2828,0,3609674,2826,2826,0,3412411,2872,2872,0,2953535,2860,2860,0,3780585,2868,2868,0,3806005,2874,2874,0,3795130,2848,2848,0,3911999,2856,2856,0,4582343,2832,2832,0,4440612,2836,2836,0,3488933,2854,2854,0,3351485,2836,2836,0,4894774,2832,2832,0,4223851,2876,2876,0,4446861,2820,2820,0,4601305,2832,2832,0,3916128,2832,2832,0,3862893,2826,2826,0,4301803,2828,2828,0,4111966,2858,2858,0,3511557,2836,2836,0,3643517,2840,2840,0,3233508,2876,2876,0,3690737,2820,2820,64,0x7fcdf8740ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29653,27002,9610,3157,0,38993,200335.0,0.0,69252.0,131083.0,64,0x7fe6bad74ec0,0,393216,163840,0,0,0,0,0,29946,0.0,0.0,0.0,32768.0,0.0,0.0,232.0,32768.0,4096,16384,302,40895,2005,0,56.0,10.0,0.0,200454.0,64,0x7f0732708ec0,6269,0,4096,6274,0,4096,6245,0,4096,6259,0,4096,6262,0,4096,6271,0,4096,6272,0,4096,6254,0,4096,6253,0,4096,6266,0,4096,6274,0,4096,6245,0,4096,6265,0,4096,6268,0,4096,6276,0,4096,6270,0,4096,6272,0,4096,6271,0,4096,6262,0,4096,6254,0,4096,6251,0,4096,6250,0,4096,6239,0,4096,6282,0,4096,6284,0,4096,6270,0,4096,6276,0,4096,6267,0,4096,6257,0,4096,6250,0,4096,6252,0,4096,6243,0,4096,64,0x7f779dc18ec0,2188,4100,2192,6288,2185,4098,2187,6283,2167,4097,2168,6264,2178,4096,2178,6274,2151,4096,2151,6247,2173,4096,2173,6269,2187,4096,2187,6283,2168,4096,2168,6264,2165,4096,2165,6261,2192,4096,2192,6288,2183,4096,2183,6279,2173,4096,2173,6269,2179,4096,2179,6275,2151,4096,2151,6247,2177,4096,2177,6273,2190,4096,2190,6286,2141,4096,2141,6237,2139,4096,2139,6235,2193,4098,2195,6291,2179,4096,2179,6275,2146,4096,2146,6242,2178,4096,2178,6274,2174,4096,2174,6270,2178,4096,2178,6274,2185,4096,2185,6281,2141,4096,2141,6237,2141,4096,2141,6237,2192,4097,2193,6289,2180,4096,2180,6276,2143,4096,2143,6239,2182,4096,2182,6278,2231,4097,2232,6328,64,0x7f2de1778ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f6e6cc84ec0,4096,0,726,0,4096,0,1142,0,4098,0,686,0,4096,0,863,0,4097,0,963,0,4096,0,5,0,4096,0,398,0,4096,0,830,0,4096,0,644,0,4096,0,1569,0,4096,0,735,0,4096,0,0,0,4097,0,0,0,4096,0,778,0,4096,0,110,0,4097,0,490,0,4096,0,617,0,4097,0,312,0,4097,0,986,0,4096,0,400,0,4096,0,688,0,4096,0,697,0,4096,0,1169,0,4096,0,1587,0,4096,0,335,0,4100,0,364,0,4096,0,115,0,4096,0,962,0,4097,0,192,0,4096,0,419,0,4096,0,262,0,4096,0,936,0,64,0x7f0da5fd0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,22740,0,2720,39449,0,69871.0,131072.0,0.0,45668.0,64,0x7fafe65c4ec0,0,0,0,56,0,65536,65536,0,64,0x7fb469ab8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131085.0,86862.0,45515.0,0.0,64,0x7f01a6500ec0,7,0,0,1718556,601,0,0,2173730,9,0,0,2184674,0,0,0,1566960,186,0,0,1769966,0,0,0,1335502,115,0,0,1566006,69,0,0,2027798,148,0,0,2088893,245,0,0,1747696,0,0,0,1601415,0,0,0,1539228,0,0,0,1741793,57,0,0,1604001,0,0,0,1361187,167,0,0,1811428,178,0,0,2212179,0,0,0,1716561,0,0,0,1415555,110,0,0,1827595,0,0,0,1559563,45,0,0,2042839,0,0,0,1596467,0,0,0,1817249,0,0,0,1879937,0,0,0,1754566,0,0,0,1932763,0,0,0,1541753,186,0,0,1946934,0,0,0,1451277,0,0,0,1397953,0,0,0,1691843,64,0x7f14d1ef4ec0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,0,41934,0,0,64,0x7fa9abb20ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2095169.0,64,0x7f45db7a0ec0,114688,0,32768,32768,16384,16384,65536,49152,59553355.0,201014624.0,50577064.0,131072.0,0.0,536773.0,0,0,25345,4083.0,131082.0,0.0,18.0,64,0x7f4ab1148ec0,32768,32768,0,64,0x7f919f270ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,122091435.0,60575096.0,0.0,64,0x7f2c30ad0ec0,0,195561,0,0,65536,63800,56,1680,199855576502899,199855576518579 diff --git a/tests/workloads/kernel_verbose_5/MI200/roofline.csv b/tests/workloads/kernel_verbose_5/MI200/roofline.csv deleted file mode 100644 index 71240f3964..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/roofline.csv +++ /dev/null @@ -1,5 +0,0 @@ -device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.8767,1388.2836,1389.4698,5016.0059,5012.9766,5019.0352,9224.0928,9223.3945,9224.791,18051.355,18049.885,18052.826,20936.43,20876.176,20996.684,20265.637,20265.018,20266.256,170439.45,170435.92,170442.98,164875.23,164870.25,164880.22,41421.074,41420.531,41421.617,41476.754,41476.145,41477.363,166335.31,165844.97,166825.66 -1,1389.168,1388.6588,1389.6771,5028.2383,5026.2607,5030.2158,9235.3203,9234.7559,9235.8848,18094.438,18090.258,18098.617,20975.785,20908.943,21042.627,20295.773,20295.225,20296.322,170850.08,170846.11,170854.05,165119.91,165115.77,165124.05,41485.68,41484.938,41486.422,41544.367,41543.547,41545.188,166856.59,166852.83,166860.36 -2,1388.4858,1387.9718,1388.9999,5036.541,5034.3604,5038.7217,9263.6934,9262.9854,9264.4014,18109.801,18108.615,18110.986,21050.965,21050.545,21051.385,20356.039,20355.549,20356.529,171162.62,171158.59,171166.66,165532.17,165528.11,165536.23,41583.977,41583.031,41584.922,41639.477,41638.352,41640.602,166952.73,166361.81,167543.66 -3,1389.3755,1388.6982,1390.0527,5032.1636,5030.7754,5033.5518,9243.207,9242.6523,9243.7617,18028.232,18025.232,18031.232,21036.127,21035.678,21036.576,20314.527,20313.791,20315.264,171022.38,171017.88,171026.88,165242.08,165237.72,165246.44,41443.5,41289.41,41597.59,41584.898,41584.383,41585.414,167024.86,167022.92,167026.8 diff --git a/tests/workloads/kernel_verbose_5/MI200/sysinfo.csv b/tests/workloads/kernel_verbose_5/MI200/sysinfo.csv deleted file mode 100644 index bf0083881d..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/sysinfo.csv +++ /dev/null @@ -1,2 +0,0 @@ -workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_5,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:41:49 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_5/MI200/timestamps.csv b/tests/workloads/kernel_verbose_5/MI200/timestamps.csv deleted file mode 100644 index b02f2351fd..0000000000 --- a/tests/workloads/kernel_verbose_5/MI200/timestamps.csv +++ /dev/null @@ -1,4 +0,0 @@ -Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,357956,357956,1048576,256,0,0,8,0,16,64,0x0,0x7f847a4d0ec0,199855576335457,199855576360179,199855576380339,199855576391773 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,357956,357956,1048576,256,0,0,8,0,16,64,0x0,0x7f847a4d0ec0,199855576391062,199855576464819,199855576481459,199855576482615 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,357956,357956,1048576,256,0,0,8,0,16,64,0x0,0x7f847a4d0ec0,199855576492554,199855576502899,199855576518579,199855576519625 diff --git a/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_fp32.pdf index e4bd70888b..2940217ea6 100644 Binary files a/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_int8_fp16.pdf index 7260beac8c..8244db8d49 100644 Binary files a/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/mem_levels_HBM/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/mem_levels_HBM/MI200/log.txt b/tests/workloads/mem_levels_HBM/MI200/log.txt new file mode 100644 index 0000000000..21397a1293 --- /dev/null +++ b/tests/workloads/mem_levels_HBM/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/mem_levels_HBM/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_164952' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164952_4179858' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164952_4179858/input0_results_240321_164952' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164952_4179858/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164952_4179858/input0_results_240321_164952 + |-> [rocprof] File 'tests/workloads/mem_levels_HBM/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_164952' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164952_4180059' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164952_4180059/input0_results_240321_164952' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164952_4180059/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164952_4180059/input0_results_240321_164952 + |-> [rocprof] File 'tests/workloads/mem_levels_HBM/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_164953' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_HBM/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164953_4180245' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164953_4180245/input0_results_240321_164953' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164953_4180245/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164953_4180245/input0_results_240321_164953 + |-> [rocprof] File 'tests/workloads/mem_levels_HBM/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_HBM/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_164953' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_HBM/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164953_4180428' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164953_4180428/input0_results_240321_164953' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164953_4180428/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164953_4180428/input0_results_240321_164953 + |-> [rocprof] File 'tests/workloads/mem_levels_HBM/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/mem_levels_HBM/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/mem_levels_HBM/MI200/pmc_dispatch_info.csv b/tests/workloads/mem_levels_HBM/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/mem_levels_HBM/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/mem_levels_HBM/MI200/pmc_perf.csv b/tests/workloads/mem_levels_HBM/MI200/pmc_perf.csv index 9d8c271e16..46f1d63a75 100644 --- a/tests/workloads/mem_levels_HBM/MI200/pmc_perf.csv +++ b/tests/workloads/mem_levels_HBM/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4d100e8ec0,0,0,64,0x7fc2e5b74ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f4c6605cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131084.0,131072.0,131072.0,200583561849560,200583561870200 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4d100e8ec0,0,0,64,0x7fc2e5b74ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f4c6605cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,90830.0,90830.0,200583562039320,200583562056120 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f4d100e8ec0,0,0,64,0x7fc2e5b74ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f4c6605cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131086.0,90980.0,90980.0,200583562075640,200583562091960 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_2,obj_2,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3cbc220ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,131072.0,131072.0,64,0x7fbef46b8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f66aff38ec0,0,0,1413525768600826,1413525768620986 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3cbc220ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,91060.0,91060.0,64,0x7fbef46b8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f66aff38ec0,0,0,1413525768639386,1413525768655226 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3cbc220ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,91196.0,91196.0,64,0x7fbef46b8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f66aff38ec0,0,0,1413525768716826,1413525768733626 diff --git a/tests/workloads/mem_levels_HBM/MI200/roofline.csv b/tests/workloads/mem_levels_HBM/MI200/roofline.csv index b6f4573efa..7478b27f56 100644 --- a/tests/workloads/mem_levels_HBM/MI200/roofline.csv +++ b/tests/workloads/mem_levels_HBM/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.8192,1388.2648,1389.3737,5013.7007,5010.8032,5016.5981,9220.3008,9219.6768,9220.9248,18046.27,18045.166,18047.373,20925.436,20865.465,20985.406,20258.646,20257.859,20259.434,170355.98,170351.92,170360.05,164824.19,164819.73,164828.64,41408.594,41407.973,41409.215,41468.672,41468.012,41469.332,166288.56,165801.78,166775.34 -1,1388.7679,1388.194,1389.3419,5028.3472,5026.4688,5030.2256,9232.9189,9232.3037,9233.5342,18087.969,18084.123,18091.814,20970.318,20904.287,21036.35,20289.684,20289.047,20290.32,170813.36,170808.7,170818.02,165088.77,165085.47,165092.06,41481.121,41480.18,41482.062,41531.738,41530.934,41532.543,166843.84,166840.59,166847.09 -2,1388.6815,1388.1339,1389.2291,5034.7876,5032.5112,5037.064,9259.1953,9258.5098,9259.8809,18103.152,18102.32,18103.984,21047.027,21046.686,21047.369,20350.014,20349.436,20350.592,171126.44,171123.09,171129.78,165508.53,165503.56,165513.5,41582.25,41581.242,41583.258,41626.5,41625.523,41627.477,166922.27,166336.48,167508.05 -3,1388.3733,1387.8055,1388.941,5032.3071,5030.8726,5033.7417,9241.541,9240.9033,9242.1787,18026.908,18023.426,18030.391,21031.641,21031.111,21032.17,20311.537,20310.902,20312.172,171016.69,171012.39,171020.98,165227.72,165223.23,165232.2,41444.879,41292.223,41597.535,41581.984,41581.426,41582.543,167021.09,167019.38,167022.81 +0,1388.7961,1388.2343,1389.358,5017.1123,5014.1782,5020.0464,9228.8867,9228.1543,9229.6191,17717.547,17714.455,17720.639,20948.875,20888.047,21009.703,20279.322,20278.77,20279.875,170559.28,170554.77,170563.8,164963.36,164957.72,164969,41443.391,41442.828,41443.953,41501.996,41501.41,41502.582,166425.84,165934.58,166917.11 +1,1389.2327,1388.6554,1389.8099,5028.5542,5026.6152,5030.4932,9232.4766,9231.8623,9233.0908,18228.039,18226.191,18229.887,20973.672,20907.033,21040.311,20291.543,20290.92,20292.166,170818.94,170814.95,170822.92,165083.78,165078.36,165089.2,41478.141,41477.461,41478.82,41536.602,41535.789,41537.414,166863.77,166860.47,166867.06 +2,1388.4871,1387.9318,1389.0424,5035.6152,5033.5391,5037.6914,9261.6484,9260.9941,9262.3027,18218.148,18217.162,18219.135,21053.178,21052.74,21053.615,20353.918,20353.305,20354.531,171133.72,171130.09,171137.34,165514.92,165512.11,165517.73,41587.039,41586.328,41587.75,41649.613,41648.402,41650.824,166996.73,166403.67,167589.8 +3,1388.8845,1388.3364,1389.4326,5033.6382,5032.0835,5035.1929,9238.1201,9237.4004,9238.8398,18328.684,18327.855,18329.512,21033.447,21032.889,21034.006,20307.252,20306.781,20307.723,171032.2,171026.08,171038.33,165181.12,165176.36,165185.89,41429.016,41275.828,41582.203,41568.402,41567.309,41569.496,166991.27,166986.69,166995.84 diff --git a/tests/workloads/mem_levels_HBM/MI200/sysinfo.csv b/tests/workloads/mem_levels_HBM/MI200/sysinfo.csv index bc5180ecb6..c6803fddd3 100644 --- a/tests/workloads/mem_levels_HBM/MI200/sysinfo.csv +++ b/tests/workloads/mem_levels_HBM/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -mem_levels_HBM,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:54:09 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +mem_levels_HBM,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:49:51 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/mem_levels_HBM/MI200/timestamps.csv b/tests/workloads/mem_levels_HBM/MI200/timestamps.csv index 2e657d92cf..fedcabf2a6 100644 --- a/tests/workloads/mem_levels_HBM/MI200/timestamps.csv +++ b/tests/workloads/mem_levels_HBM/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,386449,386449,1048576,256,0,0,8,0,16,64,0x0,0x7fdd23544ec0,200583561822620,200583561849560,200583561870200,200583561883295 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,386449,386449,1048576,256,0,0,8,0,16,64,0x0,0x7fdd23544ec0,200583561881662,200583562039320,200583562056120,200583562057945 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,386449,386449,1048576,256,0,0,8,0,16,64,0x0,0x7fdd23544ec0,200583562067413,200583562075640,200583562091960,200583562093653 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4180588,4180588,1048576,256,0,0,8,0,16,64,0x0,0x7f17fa8dcec0,1413525768575626,1413525768600826,1413525768620986,1413525768636732 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4180588,4180588,1048576,256,0,0,8,0,16,64,0x0,0x7f17fa8dcec0,1413525768631722,1413525768639386,1413525768655226,1413525768714028 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4180588,4180588,1048576,256,0,0,8,0,16,64,0x0,0x7f17fa8dcec0,1413525768665296,1413525768716826,1413525768733626,1413525768734717 diff --git a/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_0.txt b/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_0.txt deleted file mode 100644 index dfc38b8643..0000000000 --- a/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_0.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_ADD_F16 SQ_INSTS_VALU_MUL_F16 SQ_INSTS_VALU_FMA_F16 SQ_INSTS_VALU_TRANS_F16 SQ_INSTS_VALU_ADD_F32 SQ_INSTS_VALU_MUL_F32 SQ_INSTS_VALU_FMA_F32 SQ_INSTS_VALU_TRANS_F32 TCP_TCC_READ_REQ_sum TCP_TOTAL_CACHE_ACCESSES_sum TCP_TCC_WRITE_REQ_sum TCP_TCC_ATOMIC_WITH_RET_REQ_sum TCC_EA_RDREQ_32B_sum TCC_EA_RDREQ_sum TCC_EA_WRREQ_64B_sum TCC_EA_WRREQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_1.txt b/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_1.txt deleted file mode 100644 index cd7a1d5f55..0000000000 --- a/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_1.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_INSTS_VALU_ADD_F64 SQ_INSTS_VALU_MUL_F64 SQ_INSTS_VALU_FMA_F64 SQ_INSTS_VALU_TRANS_F64 SQ_INSTS_VALU_MFMA_MOPS_F16 SQ_INSTS_VALU_MFMA_MOPS_BF16 SQ_INSTS_VALU_MFMA_MOPS_F32 SQ_INSTS_VALU_MFMA_MOPS_F64 TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum - -gpu: -range: -kernel: diff --git a/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_2.txt b/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_2.txt deleted file mode 100644 index 952da7fef3..0000000000 --- a/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/pmc_perf_2.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: SQ_LDS_IDX_ACTIVE SQ_LDS_BANK_CONFLICT - -gpu: -range: -kernel: diff --git a/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/timestamps.txt b/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/timestamps.txt deleted file mode 100644 index 676cca1b80..0000000000 --- a/tests/workloads/mem_levels_HBM_LDS/MI100/perfmon/timestamps.txt +++ /dev/null @@ -1,5 +0,0 @@ -pmc: - -gpu: -range: -kernel: diff --git a/tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_fp32.pdf index 7b3ecf0c43..d84cbb18a6 100644 Binary files a/tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf index d41b6f0ccd..689f921f31 100644 Binary files a/tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/mem_levels_HBM_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/mem_levels_HBM_LDS/MI200/log.txt b/tests/workloads/mem_levels_HBM_LDS/MI200/log.txt new file mode 100644 index 0000000000..b3e41f3012 --- /dev/null +++ b/tests/workloads/mem_levels_HBM_LDS/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/mem_levels_HBM_LDS/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155803_4066293' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155803_4066293/input0_results_240321_155803' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155803_4066293/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155803_4066293/input0_results_240321_155803 + |-> [rocprof] File 'tests/workloads/mem_levels_HBM_LDS/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155803' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155803_4066496' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155803_4066496/input0_results_240321_155803' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155803_4066496/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155803_4066496/input0_results_240321_155803 + |-> [rocprof] File 'tests/workloads/mem_levels_HBM_LDS/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155804_4066697' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155804_4066697/input0_results_240321_155804' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155804_4066697/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155804_4066697/input0_results_240321_155804 + |-> [rocprof] File 'tests/workloads/mem_levels_HBM_LDS/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155804' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_HBM_LDS/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155804_4066896' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155804_4066896/input0_results_240321_155804' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155804_4066896/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155804_4066896/input0_results_240321_155804 + |-> [rocprof] File 'tests/workloads/mem_levels_HBM_LDS/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/mem_levels_HBM_LDS/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/mem_levels_HBM_LDS/MI200/pmc_dispatch_info.csv b/tests/workloads/mem_levels_HBM_LDS/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/mem_levels_HBM_LDS/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/mem_levels_HBM_LDS/MI200/pmc_perf.csv b/tests/workloads/mem_levels_HBM_LDS/MI200/pmc_perf.csv index 5fa40ea439..e8cbf861b0 100644 --- a/tests/workloads/mem_levels_HBM_LDS/MI200/pmc_perf.csv +++ b/tests/workloads/mem_levels_HBM_LDS/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7feee0864ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd357878ec0,0,0,64,0x7fb204568ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,131072.0,131072.0,195338933881345,195338933901025 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7feee0864ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd357878ec0,0,0,64,0x7fb204568ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131075.0,91387.0,91387.0,195338933920705,195338933936545 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7feee0864ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fd357878ec0,0,0,64,0x7fb204568ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,91044.0,91044.0,195338933987265,195338934004385 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7ff40fe9cec0,0,0,64,0x7feb72bb8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131084.0,131072.0,131072.0,64,0x7f6bfb458ec0,0,0,0,0,0,0,0,0,0.0,1410417037819376,1410417037838896 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7ff40fe9cec0,0,0,64,0x7feb72bb8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131085.0,91094.0,91094.0,64,0x7f6bfb458ec0,0,0,0,0,0,0,0,0,0.0,1410417037857936,1410417037873616 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7ff40fe9cec0,0,0,64,0x7feb72bb8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131085.0,91382.0,91382.0,64,0x7f6bfb458ec0,0,0,0,0,0,0,0,0,0.0,1410417037934736,1410417037951376 diff --git a/tests/workloads/mem_levels_HBM_LDS/MI200/roofline.csv b/tests/workloads/mem_levels_HBM_LDS/MI200/roofline.csv index c38584d6a8..7d07713e3f 100644 --- a/tests/workloads/mem_levels_HBM_LDS/MI200/roofline.csv +++ b/tests/workloads/mem_levels_HBM_LDS/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.6022,1388.1732,1389.0311,5014.729,5011.7075,5017.7505,9224.4746,9223.8604,9225.0889,17644.547,17643.588,17645.506,20932.666,20871.959,20993.373,20263.797,20263.117,20264.477,170396.06,170393.03,170399.09,164856.5,164851.47,164861.53,41417.699,41417.109,41418.289,41478.871,41478.25,41479.492,166341.88,165851.14,166832.61 -1,1389.0854,1388.5117,1389.6592,5027.6904,5025.498,5029.8828,9233.2461,9232.5029,9233.9893,18073.365,18072.473,18074.258,20973.09,20906.457,21039.723,20291.908,20291.34,20292.477,170809.05,170804.78,170813.31,165061.28,165056.72,165065.84,41469.859,41469.074,41470.645,41532.102,41531.242,41532.961,166828.31,166824.73,166831.89 -2,1388.7145,1388.1824,1389.2466,5035.5684,5033.3159,5037.8208,9261.0947,9260.3857,9261.8037,18264.561,18263.541,18265.58,21046.051,21045.646,21046.455,20347.016,20346.473,20347.559,171088.84,171084.22,171093.47,165458.38,165454.94,165461.81,41568.98,41568.012,41569.949,41628.668,41627.453,41629.883,166919.02,166321.91,167516.12 -3,1389.0045,1388.4553,1389.5537,5032.7505,5031.3872,5034.1138,9240.3096,9239.7148,9240.9043,18324.441,18321.764,18327.119,21030.551,21030.232,21030.869,20308.547,20308,20309.094,171009.16,171003.72,171014.59,165215.02,165211.34,165218.69,41433.988,41278.551,41589.426,41580.328,41579.258,41581.398,166979.05,166975.12,166982.97 +0,1389.0127,1388.4346,1389.5908,5016.6357,5013.2837,5019.9878,9226.9141,9226.2559,9227.5723,17714.752,17711.609,17717.895,20946.084,20885.652,21006.516,20274.053,20273.354,20274.752,170512.95,170509.27,170516.64,164936.66,164932.36,164940.95,41440.172,41439.602,41440.742,41499.789,41499.102,41500.477,166431.06,165936.47,166925.66 +1,1389.1116,1388.5483,1389.6748,5026.6143,5024.6279,5028.6006,9232.5088,9231.7939,9233.2236,18228.721,18227.502,18229.939,20973.818,20907.156,21040.48,20291.057,20290.479,20291.635,170820.78,170815.75,170825.81,165085.83,165080.77,165090.89,41480.25,41479.516,41480.984,41540.191,41539.348,41541.035,166867.69,166864.81,166870.56 +2,1389.0757,1388.5199,1389.6315,5035.6162,5033.4756,5037.7568,9260.3818,9259.7031,9261.0605,18217.684,18216.707,18218.66,21050.98,21050.303,21051.658,20355.6,20355.047,20356.152,171134.14,171130.92,171137.36,165546.58,165543.98,165549.17,41586.676,41586.074,41587.277,41645.219,41644.406,41646.031,166964.3,166370.59,167558 +3,1388.9468,1388.3365,1389.557,5032.6313,5030.9702,5034.2925,9239.7568,9239.0088,9240.5049,18331.176,18330.484,18331.867,21035.518,21035.199,21035.836,20313.02,20312.512,20313.527,171053.95,171048.23,171059.67,165209.97,165206.36,165213.58,41436.438,41282.953,41589.922,41569.164,41568.086,41570.242,166979.73,166975.97,166983.5 diff --git a/tests/workloads/mem_levels_HBM_LDS/MI200/sysinfo.csv b/tests/workloads/mem_levels_HBM_LDS/MI200/sysinfo.csv index 3b1c359943..ce5fcd40ab 100644 --- a/tests/workloads/mem_levels_HBM_LDS/MI200/sysinfo.csv +++ b/tests/workloads/mem_levels_HBM_LDS/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -mem_levels_HBM_LDS,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 01:57:58 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +mem_levels_HBM_LDS,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 03:58:02 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/mem_levels_HBM_LDS/MI200/timestamps.csv b/tests/workloads/mem_levels_HBM_LDS/MI200/timestamps.csv index 2da9ee4047..7107bf16a5 100644 --- a/tests/workloads/mem_levels_HBM_LDS/MI200/timestamps.csv +++ b/tests/workloads/mem_levels_HBM_LDS/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,170673,170673,1048576,256,0,0,8,0,16,64,0x0,0x7f4ded3b4ec0,195338933857259,195338933881345,195338933901025,195338933916040 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,170673,170673,1048576,256,0,0,8,0,16,64,0x0,0x7f4ded3b4ec0,195338933911962,195338933920705,195338933936545,195338933984079 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,170673,170673,1048576,256,0,0,8,0,16,64,0x0,0x7f4ded3b4ec0,195338933947059,195338933987265,195338934004385,195338934005339 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4067056,4067056,1048576,256,0,0,8,0,16,64,0x0,0x7f76f3bd0ec0,1410417037795507,1410417037819376,1410417037838896,1410417037855591 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4067056,4067056,1048576,256,0,0,8,0,16,64,0x0,0x7f76f3bd0ec0,1410417037849910,1410417037857936,1410417037873616,1410417037933218 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4067056,4067056,1048576,256,0,0,8,0,16,64,0x0,0x7f76f3bd0ec0,1410417037883874,1410417037934736,1410417037951376,1410417037952374 diff --git a/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_fp32.pdf index c950b66b57..5894bf6a0e 100644 Binary files a/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_int8_fp16.pdf index 997f21265a..1d49eb00ae 100644 Binary files a/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/mem_levels_L2/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/mem_levels_L2/MI200/log.txt b/tests/workloads/mem_levels_L2/MI200/log.txt new file mode 100644 index 0000000000..d130d5f5c7 --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/mem_levels_L2/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_164623' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164623_4172447' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164623_4172447/input0_results_240321_164623' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164623_4172447/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164623_4172447/input0_results_240321_164623 + |-> [rocprof] File 'tests/workloads/mem_levels_L2/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_164624' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164624_4172648' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164624_4172648/input0_results_240321_164624' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164624_4172648/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164624_4172648/input0_results_240321_164624 + |-> [rocprof] File 'tests/workloads/mem_levels_L2/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_164624' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_L2/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164624_4172849' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164624_4172849/input0_results_240321_164624' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164624_4172849/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164624_4172849/input0_results_240321_164624 + |-> [rocprof] File 'tests/workloads/mem_levels_L2/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_L2/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_164625' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_L2/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164625_4173050' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164625_4173050/input0_results_240321_164625' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164625_4173050/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164625_4173050/input0_results_240321_164625 + |-> [rocprof] File 'tests/workloads/mem_levels_L2/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/mem_levels_L2/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/mem_levels_L2/MI200/pmc_dispatch_info.csv b/tests/workloads/mem_levels_L2/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/mem_levels_L2/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/mem_levels_L2/MI200/pmc_perf.csv b/tests/workloads/mem_levels_L2/MI200/pmc_perf.csv index 047fffd111..6346b2b6a1 100644 --- a/tests/workloads/mem_levels_L2/MI200/pmc_perf.csv +++ b/tests/workloads/mem_levels_L2/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f764ae94ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f3ee4578ec0,0,0,64,0x7f5f9f2b8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131079.0,131072.0,131072.0,200269062125200,200269062145520 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f764ae94ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f3ee4578ec0,0,0,64,0x7f5f9f2b8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,90825.0,90825.0,200269062165520,200269062181200 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f764ae94ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f3ee4578ec0,0,0,64,0x7f5f9f2b8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,91006.0,91006.0,200269062256560,200269062273200 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3d95e2cec0,0,0,64,0x7f6d3ee70ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,131072.0,131072.0,64,0x7fca6c6bcec0,0,0,0,0,0,0,0,0,0.0,1413317650641624,1413317650661624 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3d95e2cec0,0,0,64,0x7f6d3ee70ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,91356.0,91356.0,64,0x7fca6c6bcec0,0,0,0,0,0,0,0,0,0.0,1413317650753782,1413317650770102 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f3d95e2cec0,0,0,64,0x7f6d3ee70ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,91672.0,91672.0,64,0x7fca6c6bcec0,0,0,0,0,0,0,0,0,0.0,1413317650790582,1413317650806102 diff --git a/tests/workloads/mem_levels_L2/MI200/roofline.csv b/tests/workloads/mem_levels_L2/MI200/roofline.csv index 92ba4e75ad..08480d4245 100644 --- a/tests/workloads/mem_levels_L2/MI200/roofline.csv +++ b/tests/workloads/mem_levels_L2/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.4659,1387.9966,1388.9353,5014.292,5011.3125,5017.2715,9222.2314,9221.6152,9222.8477,18047.654,18046.666,18048.643,20934.172,20874.197,20994.146,20264.623,20263.846,20265.4,170416.62,170413.19,170420.06,164843.52,164838.78,164848.25,41416.324,41415.676,41416.973,41470.824,41470.078,41471.57,166316.98,165829.77,166804.2 -1,1389.0763,1388.5209,1389.6317,5027.7285,5025.7261,5029.731,9236.2383,9235.5508,9236.9258,18094.5,18091.361,18097.639,20977.633,20911.295,21043.971,20297.01,20296.498,20297.521,170866.23,170862.42,170870.05,165155.59,165152.28,165158.91,41491.578,41490.852,41492.305,41550.871,41550.168,41551.574,166913.05,166909.62,166916.47 -2,1389.0742,1388.4591,1389.6893,5036.0171,5033.8262,5038.208,9262.3984,9261.6523,9263.1445,18107.012,18106.16,18107.863,21049.77,21049.328,21050.211,20350.424,20349.812,20351.035,171118.78,171113.83,171123.73,165490.17,165486.91,165493.44,41582.547,41581.484,41583.609,41642.512,41641.527,41643.496,166939.88,166355.44,167524.31 -3,1389.3132,1388.7598,1389.8667,5031.4556,5030.2266,5032.6846,9240.3389,9239.6533,9241.0244,18023.418,18019.99,18026.846,21029.805,21029.383,21030.227,20311.688,20311.004,20312.371,171010.95,171007.27,171014.64,165229.59,165226.11,165233.08,41444.262,41292.633,41595.891,41581.301,41580.785,41581.816,167019.86,167018.14,167021.58 +0,1388.7178,1388.1896,1389.246,5018.666,5015.4512,5021.8809,9231.0859,9230.3936,9231.7783,17725.035,17722.184,17727.887,20952.629,20892.541,21012.717,20278.465,20277.949,20278.98,170571.14,170567.47,170574.81,164985.88,164981.55,164990.2,41449.062,41448.52,41449.605,41505.551,41504.988,41506.113,166443.59,165954.23,166932.95 +1,1389.0547,1388.5078,1389.6016,5029.5796,5027.5835,5031.5757,9237.5469,9236.8379,9238.2559,18237.801,18236.527,18239.074,20985.418,20918.387,21052.449,20300.842,20300.064,20301.619,170901.59,170897.7,170905.48,165133.02,165128.77,165137.27,41492.945,41492.172,41493.719,41546.195,41545.402,41546.988,166898.34,166895.47,166901.22 +2,1388.4581,1387.9199,1388.9963,5035.3501,5033.2256,5037.4746,9260.4307,9259.7188,9261.1426,18215.729,18214.719,18216.738,21051.035,21050.469,21051.602,20353.141,20352.602,20353.68,171126.91,171122.77,171131.05,165515.69,165512.42,165518.95,41587.316,41586.445,41588.188,41645.754,41644.844,41646.664,166960.75,166368.98,167552.52 +3,1389.0531,1388.4916,1389.6146,5033.5762,5031.752,5035.4004,9241.2314,9240.4795,9241.9834,18337.893,18336.994,18338.791,21039.508,21039.113,21039.902,20316.68,20316.256,20317.104,171076.56,171071.28,171081.84,165190.95,165185.02,165196.89,41438.965,41286.578,41591.352,41581.551,41580.324,41582.777,167038.31,167034.03,167042.59 diff --git a/tests/workloads/mem_levels_L2/MI200/sysinfo.csv b/tests/workloads/mem_levels_L2/MI200/sysinfo.csv index 4319443e9e..57584dd5ab 100644 --- a/tests/workloads/mem_levels_L2/MI200/sysinfo.csv +++ b/tests/workloads/mem_levels_L2/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -mem_levels_L2,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:48:54 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +mem_levels_L2,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:46:23 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/mem_levels_L2/MI200/timestamps.csv b/tests/workloads/mem_levels_L2/MI200/timestamps.csv index ac6d613e93..1ab8865c79 100644 --- a/tests/workloads/mem_levels_L2/MI200/timestamps.csv +++ b/tests/workloads/mem_levels_L2/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,374061,374061,1048576,256,0,0,8,0,16,64,0x0,0x7f5e2ba9cec0,200269062098147,200269062125200,200269062145520,200269062176465 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,374061,374061,1048576,256,0,0,8,0,16,64,0x0,0x7f5e2ba9cec0,200269062157580,200269062165520,200269062181200,200269062252319 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,374061,374061,1048576,256,0,0,8,0,16,64,0x0,0x7f5e2ba9cec0,200269062191985,200269062256560,200269062273200,200269062274741 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4173210,4173210,1048576,256,0,0,8,0,16,64,0x0,0x7f3b3c010ec0,1413317650614737,1413317650641624,1413317650661624,1413317650672877 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4173210,4173210,1048576,256,0,0,8,0,16,64,0x0,0x7f3b3c010ec0,1413317650673138,1413317650753782,1413317650770102,1413317650771724 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4173210,4173210,1048576,256,0,0,8,0,16,64,0x0,0x7f3b3c010ec0,1413317650781653,1413317650790582,1413317650806102,1413317650807622 diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf index f10d0a494f..515030a871 100644 Binary files a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf index 9d77d9c6aa..7070ac19e7 100644 Binary files a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/log.txt b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/log.txt new file mode 100644 index 0000000000..f4ddd9e8b6 --- /dev/null +++ b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/mem_levels_L2_vL1d_LDS/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_164814' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164814_4178530' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164814_4178530/input0_results_240321_164814' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164814_4178530/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164814_4178530/input0_results_240321_164814 + |-> [rocprof] File 'tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_164814' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164814_4178732' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164814_4178732/input0_results_240321_164814' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164814_4178732/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164814_4178732/input0_results_240321_164814 + |-> [rocprof] File 'tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_164815' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164815_4178933' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164815_4178933/input0_results_240321_164815' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164815_4178933/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164815_4178933/input0_results_240321_164815 + |-> [rocprof] File 'tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_164815' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_L2_vL1d_LDS/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164815_4179116' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164815_4179116/input0_results_240321_164815' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164815_4179116/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164815_4179116/input0_results_240321_164815 + |-> [rocprof] File 'tests/workloads/mem_levels_L2_vL1d_LDS/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/mem_levels_L2_vL1d_LDS/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_dispatch_info.csv b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_perf.csv b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_perf.csv index 2650e501b6..6183d3c42a 100644 --- a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_perf.csv +++ b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fcd5e914ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,131072.0,131072.0,64,0x7f68ab268ec0,0,0,64,0x7f05c688cec0,0,0,0,0,0,0,0,0,0.0,200485788314555,200485788334875 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fcd5e914ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131075.0,90821.0,90821.0,64,0x7f68ab268ec0,0,0,64,0x7f05c688cec0,0,0,0,0,0,0,0,0,0.0,200485788418075,200485788434555 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fcd5e914ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,91436.0,91436.0,64,0x7f68ab268ec0,0,0,64,0x7f05c688cec0,0,0,0,0,0,0,0,0,0.0,200485788455035,200485788470875 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_2,obj_2,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f75f1334ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,131072.0,131072.0,64,0x7fb1221e8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f9eeb654ec0,0,0,1413428049202524,1413428049222364 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f75f1334ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,90938.0,90938.0,64,0x7fb1221e8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f9eeb654ec0,0,0,1413428049243964,1413428049259164 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f75f1334ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,91100.0,91100.0,64,0x7fb1221e8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f9eeb654ec0,0,0,1413428049445404,1413428049461884 diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/roofline.csv b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/roofline.csv index d1c69e29ee..245383471a 100644 --- a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/roofline.csv +++ b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.71,1388.0851,1389.3348,5015.6416,5012.4077,5018.8755,9221.0615,9220.3203,9221.8027,18047.641,18046.66,18048.621,20929.766,20869.402,20990.129,20259.381,20258.553,20260.209,170381.14,170377.98,170384.3,164808.59,164802.62,164814.56,41404.789,41404.305,41405.273,41463.492,41462.957,41464.027,166275.06,165783.09,166767.03 -1,1389.9252,1389.3696,1390.4807,5028.3955,5026.2358,5030.5552,9235.6982,9235.0195,9236.377,18097.492,18093.602,18101.383,20977.562,20910.457,21044.668,20295.43,20294.902,20295.957,170856.73,170852.86,170860.61,165125.81,165121.42,165130.2,41486.941,41486.215,41487.668,41548.336,41547.336,41549.336,166901.75,166899.2,166904.3 -2,1388.7102,1388.0908,1389.3296,5035.1221,5032.6846,5037.5596,9261.1064,9260.2969,9261.916,18105.98,18105.223,18106.738,21047.494,21047.111,21047.877,20350.797,20350.26,20351.334,171111.06,171107.72,171114.41,165487.22,165482.73,165491.7,41569.801,41568.918,41570.684,41631.086,41629.863,41632.309,166914.52,166321.44,167507.59 -3,1388.6821,1388.1644,1389.1998,5031.4268,5029.9575,5032.896,9239.6416,9239.1045,9240.1787,18022.305,18018.371,18026.238,21030.922,21030.502,21031.342,20312.498,20311.791,20313.205,171019.19,171015.36,171023.02,165215.59,165211.05,165220.14,41435.734,41280.879,41590.59,41576.676,41575.914,41577.438,166998.91,166996.25,167001.56 +0,1388.7827,1388.2915,1389.2739,5018.3086,5014.8462,5021.771,9228.6035,9227.9209,9229.2861,17722.082,17719.162,17725.002,20951.244,20890.9,21011.588,20277.102,20276.543,20277.66,170539.91,170536.92,170542.89,164963.05,164958.72,164967.38,41443.133,41442.66,41443.605,41500.484,41499.664,41501.305,166421.53,165930.41,166912.66 +1,1389.5157,1388.9551,1390.0764,5030.2261,5028.041,5032.4111,9233.9971,9233.3105,9234.6836,18232.682,18230.621,18234.742,20978.223,20911.531,21044.914,20295.32,20294.715,20295.926,170847.36,170843.75,170850.97,165102,165098.17,165105.83,41482.453,41481.566,41483.34,41541.289,41540.512,41542.066,166895.55,166892.19,166898.91 +2,1389.0669,1388.485,1389.6488,5037.2329,5035.1396,5039.3262,9260.4209,9259.6543,9261.1875,18218.359,18217.311,18219.408,21051.707,21051.141,21052.273,20350.018,20349.479,20350.557,171138.52,171133.86,171143.17,165512.2,165508.47,165515.94,41588.02,41587.18,41588.859,41641.316,41640.586,41642.047,166967.73,166373.22,167562.25 +3,1388.7233,1388.1927,1389.2538,5034.4536,5032.8916,5036.0156,9241.6523,9240.9854,9242.3193,18334.277,18333.338,18335.217,21039.312,21039.037,21039.588,20315.133,20314.621,20315.645,171077.77,171073.17,171082.36,165206.31,165201.3,165211.33,41440.859,41287.066,41594.652,41572.375,41568.496,41576.254,166999.95,166995.8,167004.11 diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/sysinfo.csv b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/sysinfo.csv index 9a0d2ce066..e5d95bedca 100644 --- a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/sysinfo.csv +++ b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -mem_levels_L2_vL1d_LDS,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:52:31 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +mem_levels_L2_vL1d_LDS,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:48:13 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/timestamps.csv b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/timestamps.csv index d98fd5be35..623b435913 100644 --- a/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/timestamps.csv +++ b/tests/workloads/mem_levels_L2_vL1d_LDS/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,385087,385087,1048576,256,0,0,8,0,16,64,0x0,0x7f2816f38ec0,200485788288903,200485788314555,200485788334875,200485788345050 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,385087,385087,1048576,256,0,0,8,0,16,64,0x0,0x7f2816f38ec0,200485788345651,200485788418075,200485788434555,200485788435771 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,385087,385087,1048576,256,0,0,8,0,16,64,0x0,0x7f2816f38ec0,200485788445760,200485788455035,200485788470875,200485788471930 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4179276,4179276,1048576,256,0,0,8,0,16,64,0x0,0x7f9fe763cec0,1413428049177126,1413428049202524,1413428049222364,1413428049242449 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4179276,4179276,1048576,256,0,0,8,0,16,64,0x0,0x7f9fe763cec0,1413428049233372,1413428049243964,1413428049259164,1413428049442978 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4179276,4179276,1048576,256,0,0,8,0,16,64,0x0,0x7f9fe763cec0,1413428049269731,1413428049445404,1413428049461884,1413428049462866 diff --git a/tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_fp32.pdf index 6ef9010f06..5f7e4d0fbc 100644 Binary files a/tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf index c757f7971a..e262a052f7 100644 Binary files a/tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/mem_levels_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/mem_levels_LDS/MI200/log.txt b/tests/workloads/mem_levels_LDS/MI200/log.txt new file mode 100644 index 0000000000..3f8cdb9384 --- /dev/null +++ b/tests/workloads/mem_levels_LDS/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/mem_levels_LDS/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_164447' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164447_4171344' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164447_4171344/input0_results_240321_164447' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164447_4171344/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164447_4171344/input0_results_240321_164447 + |-> [rocprof] File 'tests/workloads/mem_levels_LDS/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_164448' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164448_4171545' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164448_4171545/input0_results_240321_164448' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164448_4171545/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164448_4171545/input0_results_240321_164448 + |-> [rocprof] File 'tests/workloads/mem_levels_LDS/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_164448' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_LDS/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164448_4171746' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164448_4171746/input0_results_240321_164448' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164448_4171746/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164448_4171746/input0_results_240321_164448 + |-> [rocprof] File 'tests/workloads/mem_levels_LDS/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_LDS/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_164449' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_LDS/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_164449_4171949' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_164449_4171949/input0_results_240321_164449' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_164449_4171949/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_164449_4171949/input0_results_240321_164449 + |-> [rocprof] File 'tests/workloads/mem_levels_LDS/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/mem_levels_LDS/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/mem_levels_LDS/MI200/pmc_dispatch_info.csv b/tests/workloads/mem_levels_LDS/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/mem_levels_LDS/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/mem_levels_LDS/MI200/pmc_perf.csv b/tests/workloads/mem_levels_LDS/MI200/pmc_perf.csv index fc3bd2175e..41a8eb522d 100644 --- a/tests/workloads/mem_levels_LDS/MI200/pmc_perf.csv +++ b/tests/workloads/mem_levels_LDS/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_2,obj_2,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2032bf8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,131072.0,131072.0,64,0x7fb475f04ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f31c9714ec0,0,0,199641709663276,199641709683916 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2032bf8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,91166.0,91166.0,64,0x7fb475f04ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f31c9714ec0,0,0,199641709702796,199641709718636 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f2032bf8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,91190.0,91190.0,64,0x7fb475f04ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f31c9714ec0,0,0,199641709852876,199641709869196 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f55fb5ccec0,0,0,0,0,0,0,0,0,0.0,64,0x7ffb27624ec0,0,0,64,0x7fd0574d4ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,131072.0,131072.0,1413221282640092,1413221282660092 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f55fb5ccec0,0,0,0,0,0,0,0,0,0.0,64,0x7ffb27624ec0,0,0,64,0x7fd0574d4ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,91136.0,91136.0,1413221282678492,1413221282694012 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f55fb5ccec0,0,0,0,0,0,0,0,0,0.0,64,0x7ffb27624ec0,0,0,64,0x7fd0574d4ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,91392.0,91392.0,1413221282804572,1413221282821372 diff --git a/tests/workloads/mem_levels_LDS/MI200/roofline.csv b/tests/workloads/mem_levels_LDS/MI200/roofline.csv index a0d013651f..70b5398470 100644 --- a/tests/workloads/mem_levels_LDS/MI200/roofline.csv +++ b/tests/workloads/mem_levels_LDS/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.208,1388.6708,1389.7452,5015.7246,5012.7803,5018.6689,9223.2314,9222.5098,9223.9531,18050.051,18049.08,18051.021,20931.023,20870.521,20991.525,20262.693,20262.086,20263.301,170380.16,170376.55,170383.77,164855.38,164851.84,164858.91,41416.621,41416.102,41417.141,41474.363,41473.715,41475.012,166324.69,165833.86,166815.52 -1,1389.1123,1388.4735,1389.7511,5027.3423,5025.4141,5029.2705,9234.0068,9233.3955,9234.6182,18091.939,18087.717,18096.162,20970.238,20902.568,21037.908,20292.068,20291.582,20292.555,170812.91,170809.3,170816.52,165089.83,165085.92,165093.73,41479.238,41478.445,41480.031,41538.242,41537.418,41539.066,166867.59,166864.39,166870.8 -2,1388.4167,1387.8839,1388.9496,5037.4282,5035.3491,5039.5073,9258.9961,9258.0479,9259.9443,18100.652,18099.789,18101.516,21044.637,21044.076,21045.197,20350.686,20350.098,20351.273,171118.66,171114.05,171123.27,165517.77,165512.83,165522.7,41588.477,41587.434,41589.52,41640.578,41639.359,41641.797,166976.88,166380.55,167573.2 -3,1388.9985,1388.4253,1389.5718,5032.9883,5031.6147,5034.3618,9242.0703,9241.4688,9242.6719,18026.377,18022.652,18030.102,21038.605,21037.83,21039.381,20313.467,20312.76,20314.174,171046.84,171041.8,171051.89,165234.94,165230.95,165238.92,41442.641,41287.805,41597.477,41587.176,41586.625,41587.727,167031.52,167029.59,167033.44 +0,1388.7186,1388.1327,1389.3046,5015.7085,5012.689,5018.728,9226.6367,9226.0068,9227.2666,17715.197,17712.188,17718.207,20940.016,20879.469,21000.562,20270.877,20270.371,20271.383,170490.02,170485.95,170494.08,164947.94,164944.3,164951.58,41446.891,41446.293,41447.488,41507.133,41506.473,41507.793,166442.95,165949.58,166936.33 +1,1389.1569,1388.5553,1389.7584,5029.0771,5027.1943,5030.96,9235.2646,9234.5635,9235.9658,18231.475,18230.371,18232.578,20979.172,20912.504,21045.84,20296.105,20295.477,20296.734,170868.38,170862.78,170873.97,165127.72,165123.17,165132.27,41487.309,41486.578,41488.039,41544.238,41543.438,41545.039,166897.42,166894.55,166900.3 +2,1388.504,1387.9669,1389.0411,5036.9033,5034.8838,5038.9229,9261.6826,9261.0137,9262.3516,18219.43,18218.414,18220.445,21053.189,21052.588,21053.791,20353.5,20352.92,20354.08,171152.12,171148.39,171155.86,165520.27,165514.97,165525.56,41583.523,41582.754,41584.293,41640.359,41639.566,41641.152,166967.56,166378.7,167556.42 +3,1388.9884,1388.4158,1389.561,5034.4736,5032.7705,5036.1768,9239.8984,9238.9766,9240.8203,18329.654,18328.809,18330.5,21034.637,21034.285,21034.988,20310.254,20309.848,20310.66,171035.66,171031.44,171039.88,165162.28,165157.86,165166.7,41434.504,41281.914,41587.094,41569.852,41568.402,41571.301,166969.19,166964.59,166973.78 diff --git a/tests/workloads/mem_levels_LDS/MI200/sysinfo.csv b/tests/workloads/mem_levels_LDS/MI200/sysinfo.csv index 08376c6468..0bc8912cba 100644 --- a/tests/workloads/mem_levels_LDS/MI200/sysinfo.csv +++ b/tests/workloads/mem_levels_LDS/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -mem_levels_LDS,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:38:27 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +mem_levels_LDS,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:44:46 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/mem_levels_LDS/MI200/timestamps.csv b/tests/workloads/mem_levels_LDS/MI200/timestamps.csv index 9f68809ab2..3dba7f19a3 100644 --- a/tests/workloads/mem_levels_LDS/MI200/timestamps.csv +++ b/tests/workloads/mem_levels_LDS/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,347605,347605,1048576,256,0,0,8,0,16,64,0x0,0x7fc28a350ec0,199641709638640,199641709663276,199641709683916,199641709697061 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,347605,347605,1048576,256,0,0,8,0,16,64,0x0,0x7fc28a350ec0,199641709695157,199641709702796,199641709718636,199641709850090 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,347605,347605,1048576,256,0,0,8,0,16,64,0x0,0x7fc28a350ec0,199641709729322,199641709852876,199641709869196,199641709870539 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4172109,4172109,1048576,256,0,0,8,0,16,64,0x0,0x7f6761094ec0,1413221282615260,1413221282640092,1413221282660092,1413221282698268 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4172109,4172109,1048576,256,0,0,8,0,16,64,0x0,0x7f6761094ec0,1413221282671006,1413221282678492,1413221282694012,1413221282799038 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4172109,4172109,1048576,256,0,0,8,0,16,64,0x0,0x7f6761094ec0,1413221282704189,1413221282804572,1413221282821372,1413221282822412 diff --git a/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_fp32.pdf index 0c59a7c3c9..ca4c9f1daf 100644 Binary files a/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_int8_fp16.pdf index a9951bcaf6..31868df0b6 100644 Binary files a/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/mem_levels_vL1D/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/mem_levels_vL1D/MI200/log.txt b/tests/workloads/mem_levels_vL1D/MI200/log.txt new file mode 100644 index 0000000000..bcab496de8 --- /dev/null +++ b/tests/workloads/mem_levels_vL1D/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/mem_levels_vL1D/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155939' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155939_4067394' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155939_4067394/input0_results_240321_155939' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155939_4067394/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155939_4067394/input0_results_240321_155939 + |-> [rocprof] File 'tests/workloads/mem_levels_vL1D/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155940' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155940_4067595' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155940_4067595/input0_results_240321_155940' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155940_4067595/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155940_4067595/input0_results_240321_155940 + |-> [rocprof] File 'tests/workloads/mem_levels_vL1D/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155940' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_vL1D/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155940_4067796' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155940_4067796/input0_results_240321_155940' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155940_4067796/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155940_4067796/input0_results_240321_155940 + |-> [rocprof] File 'tests/workloads/mem_levels_vL1D/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_vL1D/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155941' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_vL1D/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155941_4067997' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155941_4067997/input0_results_240321_155941' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155941_4067997/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155941_4067997/input0_results_240321_155941 + |-> [rocprof] File 'tests/workloads/mem_levels_vL1D/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/mem_levels_vL1D/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/mem_levels_vL1D/MI200/pmc_dispatch_info.csv b/tests/workloads/mem_levels_vL1D/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/mem_levels_vL1D/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/mem_levels_vL1D/MI200/pmc_perf.csv b/tests/workloads/mem_levels_vL1D/MI200/pmc_perf.csv index d2c46d603a..6d3a218e69 100644 --- a/tests/workloads/mem_levels_vL1D/MI200/pmc_perf.csv +++ b/tests/workloads/mem_levels_vL1D/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f540ada8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f6e73bbcec0,0,0,64,0x7f5e0ab28ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,131072.0,131072.0,195435555133441,195435555153921 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f540ada8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f6e73bbcec0,0,0,64,0x7f5e0ab28ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,91074.0,91074.0,195435555243361,195435555259681 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f540ada8ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f6e73bbcec0,0,0,64,0x7f5e0ab28ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,91332.0,91332.0,195435555279681,195435555295521 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fe0a4e94ec0,0,0,64,0x7f4fa6354ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f0922eb8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,131072.0,131072.0,1410513588209915,1410513588230875 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fe0a4e94ec0,0,0,64,0x7f4fa6354ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f0922eb8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131084.0,91022.0,91022.0,1410513588327675,1410513588344315 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fe0a4e94ec0,0,0,64,0x7f4fa6354ec0,0,0,0,0,0,0,0,0,0.0,64,0x7f0922eb8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131084.0,91165.0,91165.0,1410513588363675,1410513588379515 diff --git a/tests/workloads/mem_levels_vL1D/MI200/roofline.csv b/tests/workloads/mem_levels_vL1D/MI200/roofline.csv index c62ce28e12..a8d1daad66 100644 --- a/tests/workloads/mem_levels_vL1D/MI200/roofline.csv +++ b/tests/workloads/mem_levels_vL1D/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.774,1388.2042,1389.3439,5013.9658,5010.894,5017.0376,9222.0215,9221.4297,9222.6133,17640.281,17639.311,17641.252,20928.287,20868.34,20988.234,20261.508,20260.926,20262.09,170370.16,170365.55,170374.77,164870.88,164868.53,164873.22,41420.773,41420.125,41421.422,41475.047,41474.426,41475.668,166308.59,165820.86,166796.33 -1,1389.172,1388.5647,1389.7793,5027.834,5025.8281,5029.8398,9231.8018,9231.1973,9232.4062,18074.664,18073.471,18075.857,20971.307,20905.047,21037.566,20290.383,20289.686,20291.08,170825.28,170820.42,170830.14,165108.06,165103.66,165112.47,41484.043,41483.086,41485,41540.953,41539.992,41541.914,166882.11,166878.66,166885.56 -2,1389.2764,1388.762,1389.7908,5035.0796,5032.9873,5037.1719,9258.1982,9257.3467,9259.0498,18262.547,18261.451,18263.643,21045.26,21044.834,21045.686,20347.381,20346.74,20348.021,171091.45,171087.73,171095.17,165454.7,165450.84,165458.56,41574.445,41573.555,41575.336,41634.172,41633.254,41635.09,166927.89,166341.78,167514 -3,1388.5292,1388.0276,1389.0308,5031.46,5030.0361,5032.8838,9239.3652,9238.793,9239.9375,18326.01,18323.832,18328.188,21030.922,21030.514,21031.33,20312.332,20311.545,20313.119,171002.45,170998.42,171006.48,165224.03,165220.81,165227.25,41442.453,41289.031,41595.875,41579.418,41578.809,41580.027,167011.28,167009.28,167013.28 +0,1388.616,1388.1178,1389.1141,5017.1406,5014.1113,5020.1699,9226.208,9225.5195,9226.8965,17712.131,17709.055,17715.207,20943.641,20883.635,21003.646,20269.473,20268.801,20270.145,170469.12,170465.33,170472.92,164916.28,164912.12,164920.44,41434.73,41434.164,41435.297,41494.422,41493.82,41495.023,166405.31,165917.83,166892.8 +1,1388.7729,1388.1915,1389.3544,5028.4199,5026.3901,5030.4497,9232.6289,9232.0254,9233.2324,18224.762,18223.145,18226.379,20974.744,20908.645,21040.844,20289.529,20288.947,20290.111,170804.94,170801.27,170808.61,165057.94,165053,165062.88,41470.746,41470.113,41471.379,41529.676,41528.973,41530.379,166851.34,166848.95,166853.73 +2,1388.7645,1388.3024,1389.2267,5037.5967,5035.2671,5039.9263,9263.7285,9262.9619,9264.4951,18220.463,18219.436,18221.49,21053.947,21053.279,21054.615,20354.766,20354.281,20355.25,171172.92,171169.25,171176.59,165524.48,165520.69,165528.28,41585.785,41585.051,41586.52,41643.637,41642.48,41644.793,166969.59,166383.36,167555.83 +3,1388.7697,1388.2249,1389.3145,5032.9019,5031.3345,5034.4692,9238.8457,9238.0898,9239.6016,18332.348,18331.402,18333.293,21034.186,21033.865,21034.506,20307.518,20306.873,20308.162,171030.22,171024.08,171036.36,165168.03,165163.98,165172.08,41433.328,41282.078,41584.578,41576.645,41575.348,41577.941,166991.53,166986.89,166996.17 diff --git a/tests/workloads/mem_levels_vL1D/MI200/sysinfo.csv b/tests/workloads/mem_levels_vL1D/MI200/sysinfo.csv index 623cfe3b00..8009e0d1f6 100644 --- a/tests/workloads/mem_levels_vL1D/MI200/sysinfo.csv +++ b/tests/workloads/mem_levels_vL1D/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -mem_levels_vL1D,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 01:58:01 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +mem_levels_vL1D,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 03:59:39 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/mem_levels_vL1D/MI200/timestamps.csv b/tests/workloads/mem_levels_vL1D/MI200/timestamps.csv index c7988dbe42..bc0a5cecc5 100644 --- a/tests/workloads/mem_levels_vL1D/MI200/timestamps.csv +++ b/tests/workloads/mem_levels_vL1D/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,171786,171786,1048576,256,0,0,8,0,16,64,0x0,0x7f68ab214ec0,195435555106293,195435555133441,195435555153921,195435555165996 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,171786,171786,1048576,256,0,0,8,0,16,64,0x0,0x7f68ab214ec0,195435555165405,195435555243361,195435555259681,195435555260976 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,171786,171786,1048576,256,0,0,8,0,16,64,0x0,0x7f68ab214ec0,195435555270544,195435555279681,195435555295521,195435555296753 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4068157,4068157,1048576,256,0,0,8,0,16,64,0x0,0x7f3f01490ec0,1410513588181763,1410513588209915,1410513588230875,1410513588243520 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4068157,4068157,1048576,256,0,0,8,0,16,64,0x0,0x7f3f01490ec0,1410513588242187,1410513588327675,1410513588344315,1410513588345864 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4068157,4068157,1048576,256,0,0,8,0,16,64,0x0,0x7f3f01490ec0,1410513588355602,1410513588363675,1410513588379515,1410513588380960 diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf index e83cfb74b3..7601d4ea17 100644 Binary files a/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf index 41c2653264..1a42941389 100644 Binary files a/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/mem_levels_vL1d_LDS/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/log.txt b/tests/workloads/mem_levels_vL1d_LDS/MI200/log.txt new file mode 100644 index 0000000000..02b104dcae --- /dev/null +++ b/tests/workloads/mem_levels_vL1d_LDS/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/mem_levels_vL1d_LDS/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_165128' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165128_4180924' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165128_4180924/input0_results_240321_165128' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165128_4180924/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165128_4180924/input0_results_240321_165128 + |-> [rocprof] File 'tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_165128' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165128_4181127' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165128_4181127/input0_results_240321_165128' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165128_4181127/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165128_4181127/input0_results_240321_165128 + |-> [rocprof] File 'tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_165129' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165129_4181328' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165129_4181328/input0_results_240321_165129' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165129_4181328/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165129_4181328/input0_results_240321_165129 + |-> [rocprof] File 'tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_165129' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/mem_levels_vL1d_LDS/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165129_4181529' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165129_4181529/input0_results_240321_165129' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165129_4181529/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165129_4181529/input0_results_240321_165129 + |-> [rocprof] File 'tests/workloads/mem_levels_vL1d_LDS/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/mem_levels_vL1d_LDS/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_dispatch_info.csv b/tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_perf.csv b/tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_perf.csv index 4eabe44bc1..f09dc718a3 100644 --- a/tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_perf.csv +++ b/tests/workloads/mem_levels_vL1d_LDS/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7faf910dcec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,131072.0,131072.0,64,0x7fd0601d0ec0,0,0,64,0x7f23dfe3cec0,0,0,0,0,0,0,0,0,0.0,200679947512042,200679947532682 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7faf910dcec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,90832.0,90832.0,64,0x7fd0601d0ec0,0,0,64,0x7f23dfe3cec0,0,0,0,0,0,0,0,0,0.0,200679947551722,200679947567402 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7faf910dcec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,91100.0,91100.0,64,0x7fd0601d0ec0,0,0,64,0x7f23dfe3cec0,0,0,0,0,0,0,0,0,0.0,200679947624842,200679947641322 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f756b6b4ec0,0,0,64,0x7f7dcb41cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,131072.0,131072.0,64,0x7faa67ca8ec0,0,0,0,0,0,0,0,0,0.0,1413622136027114,1413622136047434 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f756b6b4ec0,0,0,64,0x7f7dcb41cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,91408.0,91408.0,64,0x7faa67ca8ec0,0,0,0,0,0,0,0,0,0.0,1413622136136234,1413622136153194 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f756b6b4ec0,0,0,64,0x7f7dcb41cec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,91190.0,91190.0,64,0x7faa67ca8ec0,0,0,0,0,0,0,0,0,0.0,1413622136173514,1413622136189354 diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/roofline.csv b/tests/workloads/mem_levels_vL1d_LDS/MI200/roofline.csv index 66fa86f5b5..12b17b9583 100644 --- a/tests/workloads/mem_levels_vL1d_LDS/MI200/roofline.csv +++ b/tests/workloads/mem_levels_vL1d_LDS/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.2767,1388.6462,1389.9072,5014.7227,5011.7349,5017.7104,9221.1709,9220.46,9221.8818,18047.307,18046.445,18048.168,20931.127,20870.908,20991.346,20261.252,20260.615,20261.889,170383.52,170379.22,170387.81,164839.55,164834.88,164844.22,41411.035,41410.48,41411.59,41469.934,41469.242,41470.625,166292.2,165803.83,166780.58 -1,1389.2551,1388.6827,1389.8275,5026.6777,5024.4463,5028.9092,9234.3623,9233.7871,9234.9375,18094.959,18090.369,18099.549,20975.953,20909.719,21042.188,20296.273,20295.641,20296.906,170855.73,170851.22,170860.25,165128.28,165124,165132.56,41489.871,41488.887,41490.855,41545.156,41544.332,41545.98,166885.02,166881.59,166888.44 -2,1388.7524,1388.175,1389.3298,5035.4204,5033.3643,5037.4766,9262.4863,9261.6982,9263.2744,18109.088,18108.203,18109.973,21050.412,21050.049,21050.775,20352.109,20351.518,20352.701,171123.23,171119.62,171126.84,165507.11,165503.02,165511.2,41588.84,41587.891,41589.789,41642.801,41641.777,41643.824,166938.2,166351.17,167525.23 -3,1388.7568,1388.1588,1389.3549,5033.1357,5031.9126,5034.3589,9240.4658,9239.8291,9241.1025,18023.016,18019.111,18026.92,21040.244,21039.566,21040.922,20317.041,20316.359,20317.723,171074.86,171070.44,171079.28,165251.8,165246.83,165256.77,41442.977,41291.359,41594.594,41583.074,41582.516,41583.633,167029.44,167027.62,167031.25 +0,1388.7032,1388.0962,1389.3103,5018.1338,5015.0938,5021.1738,9227.3535,9226.7061,9228.001,17719.57,17716.58,17722.561,20947.35,20887.102,21007.598,20275.549,20274.951,20276.146,170460.62,170457.11,170464.14,164923.84,164920.03,164927.66,41440.316,41439.664,41440.969,41499.094,41498.543,41499.645,166418.33,165930.5,166906.16 +1,1389.311,1388.7255,1389.8966,5027.9448,5026.0532,5029.8364,9233.3398,9232.7656,9233.9141,18234.23,18232.533,18235.928,20983.635,20917.287,21049.982,20299.912,20299.488,20300.336,170895.45,170890.92,170899.98,165135.55,165131.38,165139.72,41492.727,41491.992,41493.461,41548.484,41547.555,41549.414,166909.77,166905.69,166913.84 +2,1388.4497,1387.8535,1389.0459,5036.6714,5034.3779,5038.9648,9261.6621,9260.9297,9262.3945,18217.625,18216.658,18218.592,21050.568,21050.113,21051.023,20351.369,20350.719,20352.02,171150.09,171145.19,171155,165524.11,165520.48,165527.73,41584.684,41583.73,41585.637,41640.078,41639.418,41640.738,166974.73,166388.17,167561.3 +3,1388.6168,1388.0544,1389.1792,5034.0107,5032.2969,5035.7246,9239.8408,9239.1934,9240.4883,18331.564,18330.801,18332.328,21037.062,21036.752,21037.373,20311.625,20310.969,20312.281,171042.56,171038.53,171046.59,165204.53,165200.02,165209.05,41435.305,41273.992,41596.617,41584.316,41583.273,41585.359,167015.45,167010.88,167020.03 diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/sysinfo.csv b/tests/workloads/mem_levels_vL1d_LDS/MI200/sysinfo.csv index 41a056022f..36d409baaf 100644 --- a/tests/workloads/mem_levels_vL1d_LDS/MI200/sysinfo.csv +++ b/tests/workloads/mem_levels_vL1d_LDS/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -mem_levels_vL1d_LDS,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:55:45 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +mem_levels_vL1d_LDS,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:51:27 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/mem_levels_vL1d_LDS/MI200/timestamps.csv b/tests/workloads/mem_levels_vL1d_LDS/MI200/timestamps.csv index 84acb6664e..76dd810b40 100644 --- a/tests/workloads/mem_levels_vL1d_LDS/MI200/timestamps.csv +++ b/tests/workloads/mem_levels_vL1d_LDS/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,387540,387540,1048576,256,0,0,8,0,16,64,0x0,0x7fa673768ec0,200679947483869,200679947512042,200679947532682,200679947546437 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,387540,387540,1048576,256,0,0,8,0,16,64,0x0,0x7fa673768ec0,200679947544123,200679947551722,200679947567402,200679947621609 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,387540,387540,1048576,256,0,0,8,0,16,64,0x0,0x7fa673768ec0,200679947578367,200679947624842,200679947641322,200679947642659 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4181694,4181694,1048576,256,0,0,8,0,16,64,0x0,0x7f3650974ec0,1413622135997109,1413622136027114,1413622136047434,1413622136060219 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4181694,4181694,1048576,256,0,0,8,0,16,64,0x0,0x7f3650974ec0,1413622136058516,1413622136136234,1413622136153194,1413622136154748 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4181694,4181694,1048576,256,0,0,8,0,16,64,0x0,0x7f3650974ec0,1413622136164777,1413622136173514,1413622136189354,1413622136190766 diff --git a/tests/workloads/no_roof/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/no_roof/MI100/SQ_IFETCH_LEVEL.csv index d9bab0fcf7..1adb1cb8f6 100644 --- a/tests/workloads/no_roof/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/no_roof/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,222260,222260,1048576,256,0,0,8,8,16,64,0x0,0x7fdb41414e80,49184,49184,16384,65536,14457,1842936,194436448445314,194448655968796,194448655993276,194436456954245 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,222260,222260,1048576,256,0,0,8,8,16,64,0x0,0x7fdb41414e80,43487,43487,16384,65536,8172,1048580,194436456975635,194448656081116,194448656100796,194436457327952 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,222260,222260,1048576,256,0,0,8,8,16,64,0x0,0x7fdb41414e80,43103,43103,16384,65536,8252,1048592,194436457361876,194448656120796,194448656139516,194436457561114 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1287304,1287304,1048576,256,0,0,8,8,16,64,0x0,0x7fbfbc6c8ec0,47754,47754,16384,65536,14309,1839660,1410255731725034,1410267415496161,1410267415520481,1410255739453099 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1287304,1287304,1048576,256,0,0,8,8,16,64,0x0,0x7fbfbc6c8ec0,42684,42684,16384,65536,8549,1048576,1410255739477164,1410267415589601,1410267415608321,1410255739810042 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1287304,1287304,1048576,256,0,0,8,8,16,64,0x0,0x7fbfbc6c8ec0,42497,42497,16384,65536,8133,1048588,1410255739842313,1410267415628801,1410267415647841,1410255740026380 diff --git a/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_LDS.csv index 3eae212285..5dfbdb8af7 100644 --- a/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,222445,222445,1048576,256,0,0,8,8,16,64,0x0,0x7f8701308e80,0,0,0,194436947968812,194448655968796,194448655993276,194436955618255 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,222445,222445,1048576,256,0,0,8,8,16,64,0x0,0x7f8701308e80,0,0,0,194436955636940,194448656081116,194448656100796,194436955955373 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,222445,222445,1048576,256,0,0,8,8,16,64,0x0,0x7f8701308e80,0,0,0,194436955983657,194448656120796,194448656139516,194436956167014 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1287487,1287487,1048576,256,0,0,8,8,16,64,0x0,0x7fb3cd6fcec0,0,0,0,1410256214210226,1410267415496161,1410267415520481,1410256221849594 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1287487,1287487,1048576,256,0,0,8,8,16,64,0x0,0x7fb3cd6fcec0,0,0,0,1410256221871004,1410267415589601,1410267415608321,1410256222139540 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1287487,1287487,1048576,256,0,0,8,8,16,64,0x0,0x7fb3cd6fcec0,0,0,0,1410256222167824,1410267415628801,1410267415647841,1410256222313108 diff --git a/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_SMEM.csv index 9855538880..0bc1b8ae9f 100644 --- a/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,222631,222631,1048576,256,0,0,8,8,16,64,0x0,0x7f5561906e80,65536,204562,26227568,194437438358325,194448655968796,194448655993276,194437445968083 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,222631,222631,1048576,256,0,0,8,8,16,64,0x0,0x7f5561906e80,65536,180966,23117272,194437445986999,194448656081116,194448656100796,194437446302727 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,222631,222631,1048576,256,0,0,8,8,16,64,0x0,0x7f5561906e80,65536,160972,20708720,194437446331030,194448656120796,194448656139516,194437446504449 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1287671,1287671,1048576,256,0,0,8,8,16,64,0x0,0x7fa233b34ec0,65536,186382,23891136,1410256690963939,1410267415496161,1410267415520481,1410256698511063 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1287671,1287671,1048576,256,0,0,8,8,16,64,0x0,0x7fa233b34ec0,65536,178670,22834888,1410256698532713,1410267415589601,1410267415608321,1410256698808614 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1287671,1287671,1048576,256,0,0,8,8,16,64,0x0,0x7fa233b34ec0,65536,161808,20724568,1410256698836847,1410267415628801,1410267415647841,1410256698985307 diff --git a/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_VMEM.csv index f61471797f..28912274e5 100644 --- a/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/no_roof/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,222815,222815,1048576,256,0,0,8,8,16,64,0x0,0x7fd5ade08e80,32768,669373,85681792,194437930681048,194448655968796,194448655993276,194437938503940 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,222815,222815,1048576,256,0,0,8,8,16,64,0x0,0x7fd5ade08e80,32768,684499,87614800,194437938523938,194448656081116,194448656100796,194437938913816 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,222815,222815,1048576,256,0,0,8,8,16,64,0x0,0x7fd5ade08e80,32768,670830,85878712,194437938942841,194448656120796,194448656139516,194437939133843 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1287854,1287854,1048576,256,0,0,8,8,16,64,0x0,0x7f02d60a0ec0,32768,626275,80165648,1410257172396315,1410267415496161,1410267415520481,1410257180113249 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1287854,1287854,1048576,256,0,0,8,8,16,64,0x0,0x7f02d60a0ec0,32768,615535,78793748,1410257180133297,1410267415589601,1410267415608321,1410257180445456 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1287854,1287854,1048576,256,0,0,8,8,16,64,0x0,0x7f02d60a0ec0,32768,646440,82738708,1410257180473709,1410267415628801,1410267415647841,1410257180648349 diff --git a/tests/workloads/no_roof/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/no_roof/MI100/SQ_LEVEL_WAVES.csv index 20dfe78832..296ac654cb 100644 --- a/tests/workloads/no_roof/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/no_roof/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,223000,223000,1048576,256,0,0,8,8,16,64,0x0,0x7f3856886e80,48866,48866,16974,390936,16384,25913044,238020,0,104164760,194438422983563,194448655968796,194448655993276,194438430606156 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,223000,223000,1048576,256,0,0,8,8,16,64,0x0,0x7f3856886e80,42240,42240,12806,337928,16384,24702254,234180,0,99292980,194438430636213,194448656081116,194448656100796,194438430957973 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,223000,223000,1048576,256,0,0,8,8,16,64,0x0,0x7f3856886e80,41831,41831,12613,334656,16384,24030686,229316,0,96609076,194438430996866,194448656120796,194448656139516,194438431237201 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1288040,1288040,1048576,256,0,0,8,8,16,64,0x0,0x7f459fdd8ec0,48976,48976,17576,391816,16384,25082917,238738,0,100854596,1410257653120216,1410267415496161,1410267415520481,1410257660726161 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1288040,1288040,1048576,256,0,0,8,8,16,64,0x0,0x7f459fdd8ec0,44360,44360,14273,354888,16384,26163537,243455,0,105188168,1410257660757500,1410267415589601,1410267415608321,1410257661081321 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1288040,1288040,1048576,256,0,0,8,8,16,64,0x0,0x7f459fdd8ec0,43570,43570,13853,348568,16384,24937698,236717,0,100279156,1410257661119312,1410267415628801,1410267415647841,1410257661309260 diff --git a/tests/workloads/no_roof/MI100/log.txt b/tests/workloads/no_roof/MI100/log.txt new file mode 100644 index 0000000000..ab425630d5 --- /dev/null +++ b/tests/workloads/no_roof/MI100/log.txt @@ -0,0 +1,679 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/no_roof/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155521' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155521_1287144' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155521_1287144/input0_results_240321_155521' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155521_1287144/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155521_1287144/input0_results_240321_155521 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155522' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155522_1287327' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155522_1287327/input0_results_240321_155522' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155522_1287327/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155522_1287327/input0_results_240321_155522 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155522' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155522_1287511' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155522_1287511/input0_results_240321_155522' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155522_1287511/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155522_1287511/input0_results_240321_155522 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155523' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155523_1287694' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155523_1287694/input0_results_240321_155523' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155523_1287694/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155523_1287694/input0_results_240321_155523 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155523' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155523_1287880' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155523_1287880/input0_results_240321_155523' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155523_1287880/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155523_1287880/input0_results_240321_155523 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155524' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155524_1288063' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155524_1288063/input0_results_240321_155524' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155524_1288063/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155524_1288063/input0_results_240321_155524 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155524' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155524_1288246' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155524_1288246/input0_results_240321_155524' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155524_1288246/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155524_1288246/input0_results_240321_155524 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155525' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155525_1288431' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155525_1288431/input0_results_240321_155525' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155525_1288431/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155525_1288431/input0_results_240321_155525 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155525' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155525_1288619' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155525_1288619/input0_results_240321_155525' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155525_1288619/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155525_1288619/input0_results_240321_155525 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155526' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155526_1288806' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155526_1288806/input0_results_240321_155526' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155526_1288806/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155526_1288806/input0_results_240321_155526 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155526' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155526_1288990' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155526_1288990/input0_results_240321_155526' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155526_1288990/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155526_1288990/input0_results_240321_155526 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155527' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155527_1289173' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155527_1289173/input0_results_240321_155527' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155527_1289173/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155527_1289173/input0_results_240321_155527 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155528' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155528_1289356' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155528_1289356/input0_results_240321_155528' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155528_1289356/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155528_1289356/input0_results_240321_155528 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155528' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155528_1289540' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155528_1289540/input0_results_240321_155528' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155528_1289540/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155528_1289540/input0_results_240321_155528 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155529' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155529_1289727' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155529_1289727/input0_results_240321_155529' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155529_1289727/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155529_1289727/input0_results_240321_155529 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155530' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155530_1289915' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155530_1289915/input0_results_240321_155530' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155530_1289915/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155530_1289915/input0_results_240321_155530 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155530' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155530_1290098' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155530_1290098/input0_results_240321_155530' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155530_1290098/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155530_1290098/input0_results_240321_155530 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155531' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155531_1290281' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155531_1290281/input0_results_240321_155531' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155531_1290281/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155531_1290281/input0_results_240321_155531 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155531' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155531_1290468' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155531_1290468/input0_results_240321_155531' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155531_1290468/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155531_1290468/input0_results_240321_155531 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155531' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155531_1290652' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155531_1290652/input0_results_240321_155531' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155531_1290652/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155531_1290652/input0_results_240321_155531 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155532' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155532_1290845' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155532_1290845/input0_results_240321_155532' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155532_1290845/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155532_1290845/input0_results_240321_155532 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155532' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155532_1291029' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155532_1291029/input0_results_240321_155532' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155532_1291029/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155532_1291029/input0_results_240321_155532 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155533' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155533_1291213' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155533_1291213/input0_results_240321_155533' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155533_1291213/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155533_1291213/input0_results_240321_155533 + |-> [rocprof] File 'tests/workloads/no_roof/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/no_roof/MI100/pmc_dispatch_info.csv b/tests/workloads/no_roof/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/no_roof/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/no_roof/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/no_roof/MI100/pmc_perf.csv b/tests/workloads/no_roof/MI100/pmc_perf.csv index f48e1cc516..4262830714 100644 --- a/tests/workloads/no_roof/MI100/pmc_perf.csv +++ b/tests/workloads/no_roof/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_4,obj_4,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_5,obj_5,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_6,obj_6,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_7,obj_7,TCC_EA_ATOMIC_LEVEL_sum,wave_size_8,obj_8,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_9,obj_9,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_10,obj_10,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_11,obj_11,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_12,obj_12,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_13,obj_13,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_14,obj_14,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_15,obj_15,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_16,obj_16,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f38c3fece80,1880012,360448,163840,0,0,180224,114688,0,70906085.0,195541566.0,77810933.0,131072.0,0.0,550063.0,0,0,26837,99881.0,0.0,0.0,99881.0,64,0x7f8d65132e80,4096,0,3912,0,4096,0,1047,0,4096,0,994,0,4096,0,0,0,4097,0,1942,0,4096,0,1464,0,4144,0,467,0,4096,0,2025,0,4096,0,770,0,4096,0,6964,0,4096,0,1163,0,4268,0,1265,0,4096,0,4139,0,4096,0,1656,0,4096,0,538,0,4096,0,891,0,4096,0,3417,0,4096,0,423,0,4096,0,1103,0,4096,0,2345,0,4096,0,876,0,4096,0,304,0,4096,0,6583,0,4096,0,0,0,4096,0,127,0,4096,0,666,0,4096,0,1120,0,4096,0,165,0,4096,0,48,0,4096,0,0,0,4216,0,131,0,4096,0,1806,0,64,0x7f40bebace80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46584,0,131503.0,131072.0,0.0,131104.0,64,0x7f1261a4ae80,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,0,48004,0,0,64,0x7eff85d88e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f2c049b2e80,0,0,192,0,65536,64474,48,1264,33252,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,969,118470,3141,0,48.0,345.0,0.0,262288.0,64,0x7f7b68878e80,131072.0,131072.0,0.0,2552732.0,0.0,0.0,116657412.0,59417822.0,64,0x7fd24d8d2e80,0.0,64,0x7fc411684e80,32768,0,0,0,16384,16384,393216,22812546,960.0,513971.0,0.0,524288.0,937148.0,32768.0,0,0,0,16267,131072.0,131072.0,0.0,131072.0,64,0x7f0acf6eae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,58097.0,125566.0,64,0x7f74b2b4ce80,0,8192,4096,8192,0,8282,4186,8282,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f88751b8e80,387144,234374,3419968,16384,24375449,144,48,0,48392,48392,3868271.0,3047477.0,6288.0,1118459.0,2117794.0,0.0,3037600.0,2726894.0,385431,244300,48392,0,48392,0,1548544.0,973942.0,0.0,0.0,64,0x7f928e734e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86595.0,44477.0,131112.0,0.0,64,0x7fc2742c4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131377.0,0.0,602.0,131376.0,64,0x7f1ac8f9ce80,2864,0,0,1913392,1970,0,0,1839288,1789,0,0,1836529,3171,0,0,1904275,2332,0,0,1866608,3163,0,0,1948950,2700,0,0,1892203,4737,0,0,2120447,1700,0,0,1801562,2587,0,0,1856878,3758,0,0,1959049,4149,0,0,2122857,2029,0,0,1872878,1940,0,0,1873179,1987,0,0,1838934,5388,0,0,2105239,3221,0,0,1984418,1644,0,0,1777375,6181,0,0,2226871,3261,0,0,1996735,4296,0,0,2098385,3237,0,0,1979960,4226,0,0,2092123,6509,0,0,2187461,1956,0,0,1823894,1653,0,0,1776773,6717,0,0,2194481,4557,0,0,2023355,3867,0,0,2007889,4820,0,0,2070021,3174,0,0,2033091,3106,0,0,1947942,64,0x7f5ee369ee80,0,3079613,4096,4096,0,2883798,4096,4096,0,2778329,4096,4096,0,3135330,4096,4096,0,3694102,4096,4096,0,4620715,4096,4096,0,3365462,4096,4096,0,3591067,4096,4096,0,3794562,4096,4096,0,3042241,4096,4096,0,3070038,4096,4096,0,3411408,4096,4096,0,2587758,4096,4096,0,3496018,4096,4096,0,3112248,4096,4096,0,4118681,4096,4096,0,3355192,4096,4096,0,3662940,4096,4096,0,5480061,4096,4096,0,3090577,4096,4096,0,2736483,4096,4096,0,3056539,4096,4096,0,4139055,4096,4096,0,3462482,4096,4096,0,2971114,4096,4096,0,2961427,4096,4096,0,3966427,4096,4096,0,3010492,4096,4096,0,4140131,4096,4096,0,4584798,4096,4096,0,2887241,4096,4096,0,3603357,4096,4096,64,0x7ff3b13c6e80,221392,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12418,28802,9871,550,0,46458,262681.0,0.0,188.0,262493.0,194448655968796,194448655993276 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f38c3fece80,256509,360448,163840,0,0,180224,114688,0,73623535.0,199812327.0,75643016.0,131072.0,0.0,549184.0,0,0,23907,64288.0,0.0,0.0,64288.0,64,0x7f8d65132e80,4096,0,2078,0,4096,0,648,0,4096,0,1374,0,4096,0,226,0,4097,0,2116,0,4096,0,2627,0,4144,0,405,0,4096,0,1083,0,4096,0,3997,0,4097,0,2950,0,4096,0,0,0,4268,0,5188,0,4096,0,4470,0,4096,0,3284,0,4096,0,885,0,4097,0,1294,0,4096,0,443,0,4096,0,6067,0,4096,0,60,0,4096,0,558,0,4096,0,3080,0,4096,0,225,0,4096,0,173,0,4096,0,570,0,4096,0,742,0,4096,0,2880,0,4096,0,2100,0,4096,0,0,0,4096,0,888,0,4098,0,2058,0,4216,0,1382,0,4096,0,178,0,64,0x7f40bebace80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3172,39393,0,131334.0,131072.0,0.0,86550.0,64,0x7f1261a4ae80,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,0,42723,0,0,64,0x7eff85d88e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f2c049b2e80,0,0,48,0,65536,65536,0,0,32449,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,603,47768,1702,0,48.0,371.0,0.0,262144.0,64,0x7f7b68878e80,131072.0,131072.0,0.0,2863019.0,0.0,0.0,109113184.0,47234090.0,64,0x7fd24d8d2e80,0.0,64,0x7fc411684e80,32768,0,0,0,16384,16384,393216,23977156,1080.0,512640.0,0.0,524288.0,1703568.0,32768.0,0,0,0,22205,120960.0,120960.0,0.0,120960.0,64,0x7f0acf6eae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,54675.0,119919.0,64,0x7f74b2b4ce80,0,8192,4096,8192,0,8313,4217,8313,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f88751b8e80,359448,234612,3429932,16384,25150283,0,48,0,44930,44930,3809426.0,3151072.0,6817.0,958358.0,2117127.0,0.0,3141104.0,2830141.0,359440,244411,44930,0,44930,0,1437760.0,833773.0,0.0,0.0,64,0x7f928e734e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,50718.0,38183.0,32211.0,0.0,64,0x7fc2742c4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131507.0,0.0,866.0,131505.0,64,0x7f1ac8f9ce80,1939,0,0,1533703,3008,0,0,1546102,3903,0,0,1729417,313,0,0,1269170,4618,0,0,1748475,388,0,0,1225053,6644,0,0,1879065,2134,0,0,1444455,825,0,0,1392323,1480,0,0,1494175,1845,0,0,1448400,753,0,0,1299459,2478,0,0,1548733,4303,0,0,1723324,80,0,0,1215123,3588,0,0,1592524,1931,0,0,1500112,2654,0,0,1620999,1524,0,0,1476516,3180,0,0,1653218,2720,0,0,1608393,2612,0,0,1586429,1232,0,0,1421263,751,0,0,1301776,4204,0,0,1735417,657,0,0,1366003,5406,0,0,1775143,3313,0,0,1624782,5330,0,0,1754882,2254,0,0,1436013,3671,0,0,1722405,679,0,0,1282526,64,0x7f5ee369ee80,0,4491415,2720,2720,0,3358274,2691,2691,0,4070330,2714,2714,0,3759726,2698,2698,0,4161133,2684,2684,0,3741437,2662,2662,0,4107328,2760,2760,0,3906707,2706,2706,0,3746215,2724,2724,0,3064979,2680,2680,0,3667482,2736,2736,0,3413346,2698,2698,0,3874755,2740,2740,0,3735435,2674,2674,0,4531016,2718,2718,0,3055401,2698,2698,0,4259710,2714,2714,0,3969607,2684,2684,0,4413162,2721,2721,0,3996520,2676,2676,0,3403688,2722,2722,0,3293925,2719,2719,0,5261948,2710,2710,0,3131993,2700,2700,0,4014418,2684,2684,0,4087471,2670,2670,0,3197269,2746,2746,0,3419892,2692,2692,0,3441992,2716,2716,0,3255221,2691,2691,0,4129972,2724,2724,0,3457171,2712,2712,64,0x7ff3b13c6e80,176042,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14954,31338,8599,2385,0,42075,262576.0,0.0,47.0,262529.0,194448656081116,194448656100796 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7f38c3fece80,1505430,360448,163840,0,0,180224,114688,0,71889941.0,207538103.0,78345972.0,131072.0,0.0,598881.0,0,0,25347,73567.0,0.0,0.0,73567.0,64,0x7f8d65132e80,4096,0,2027,0,4096,0,46,0,4096,0,155,0,4096,0,1536,0,4097,0,816,0,4096,0,62,0,4144,0,79,0,4096,0,4060,0,4096,0,4185,0,4097,0,2135,0,4096,0,2887,0,4268,0,8093,0,4096,0,957,0,4096,0,344,0,4096,0,8369,0,4097,0,1025,0,4096,0,1317,0,4096,0,1697,0,4096,0,115,0,4096,0,2129,0,4096,0,9,0,4096,0,2051,0,4096,0,766,0,4096,0,688,0,4096,0,965,0,4096,0,450,0,4096,0,15,0,4096,0,784,0,4096,0,1808,0,4098,0,0,0,4216,0,25,0,4096,0,229,0,64,0x7f40bebace80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,3174,39379,0,131348.0,131072.0,0.0,87091.0,64,0x7f1261a4ae80,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,0,42803,0,0,64,0x7eff85d88e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f2c049b2e80,0,0,48,0,65536,65536,0,0,31324,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,432,41599,1712,0,48.0,302.0,0.0,262144.0,64,0x7f7b68878e80,131072.0,131072.0,0.0,2574497.0,0.0,0.0,136763493.0,46867897.0,64,0x7fd24d8d2e80,0.0,64,0x7fc411684e80,32768,0,0,0,16384,16384,393216,22534441,960.0,513960.0,0.0,524288.0,937758.0,32768.0,0,0,0,13543,86410.0,86410.0,0.0,86410.0,64,0x7f0acf6eae80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,82345.0,152475.0,64,0x7f74b2b4ce80,0,8192,4096,8192,0,8274,4178,8274,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8195,4099,8195,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f88751b8e80,346232,231326,3365173,16384,24538687,0,48,0,43278,43278,3759442.0,3085283.0,5968.0,985792.0,2095893.0,0.0,3075397.0,2764381.0,346224,240537,43278,0,43278,0,1384896.0,828879.0,0.0,0.0,64,0x7f928e734e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86846.0,0.0,131112.0,0.0,64,0x7fc2742c4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131346.0,0.0,546.0,131345.0,64,0x7f1ac8f9ce80,1637,0,0,1398871,781,0,0,1228136,152,0,0,1150746,2873,0,0,1600909,1227,0,0,1326360,1859,0,0,1489799,456,0,0,1294333,4365,0,0,1715082,1581,0,0,1430582,4726,0,0,1728234,157,0,0,1213910,2790,0,0,1561192,386,0,0,1177048,1192,0,0,1373684,232,0,0,1177203,4977,0,0,1749434,767,0,0,1174147,1919,0,0,1542869,3151,0,0,1619643,4024,0,0,1732157,1211,0,0,1349542,2429,0,0,1557926,970,0,0,1379687,3197,0,0,1628783,848,0,0,1321820,2186,0,0,1532990,629,0,0,1327904,5032,0,0,1701229,2303,0,0,1466220,4075,0,0,1707254,1142,0,0,1367671,2336,0,0,1494640,64,0x7f5ee369ee80,0,3968087,2750,2750,0,3912182,2682,2682,0,3413489,2688,2688,0,3718866,2742,2742,0,3661073,2729,2729,0,4048375,2716,2716,0,3561813,2738,2738,0,3690328,2754,2754,0,3777092,2720,2720,0,3722062,2652,2652,0,3089528,2744,2744,0,4059637,2756,2756,0,3897395,2727,2727,0,4397486,2702,2702,0,3610139,2722,2722,0,3662208,2718,2718,0,4830578,2736,2736,0,4360263,2704,2704,0,3451117,2686,2686,0,3934768,2760,2760,0,3854097,2718,2718,0,4367355,2699,2699,0,4289698,2736,2736,0,3489921,2716,2716,0,3286817,2709,2709,0,3969554,2680,2680,0,2802230,2758,2758,0,3449627,2748,2748,0,3772965,2705,2705,0,4287735,2686,2686,0,3385615,2720,2720,0,3816211,2726,2726,64,0x7ff3b13c6e80,201462,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14001,30385,9073,2413,0,40440,262580.0,0.0,47.0,262533.0,194448656120796,194448656139516 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_4,obj_4,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_5,obj_5,TCC_EA_ATOMIC_LEVEL_sum,wave_size_6,obj_6,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_7,obj_7,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_8,obj_8,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_9,obj_9,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_10,obj_10,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_11,obj_11,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_12,obj_12,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_13,obj_13,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_14,obj_14,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_15,obj_15,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_16,obj_16,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7e16ff8ec0,131072.0,131072.0,0.0,2554735.0,0.0,0.0,116913066.0,60496500.0,64,0x7f99ce778ec0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,0,48863,0,0,64,0x7f5472514ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47510,0,131600.0,131072.0,0.0,131104.0,64,0x7f792b44cec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb653fd8ec0,4096,0,2455,0,4096,0,1123,0,4096,0,6219,0,4099,0,606,0,4096,0,645,0,4096,0,2965,0,4096,0,108,0,4096,0,4228,0,4096,0,567,0,4096,0,1304,0,4096,0,1706,0,4144,0,3369,0,4096,0,0,0,4096,0,1359,0,4096,0,3517,0,4096,0,971,0,4096,0,164,0,4096,0,4256,0,4391,0,5685,0,4096,0,2122,0,4096,0,4461,0,4096,0,831,0,4096,0,2530,0,4096,0,392,0,4096,0,3409,0,4096,0,1844,0,4216,0,166,0,4097,0,2714,0,4096,0,0,0,4096,0,468,0,4096,0,477,0,4096,0,6647,0,64,0x7f2cedd54ec0,0.0,64,0x7ff4a81d0ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,38422.0,132049.0,64,0x7fac322c8ec0,32768,0,0,0,16384,16384,393216,21845470,960.0,513908.0,0.0,524288.0,914270.0,32768.0,0,0,0,16309,131072.0,131072.0,0.0,131072.0,64,0x7fb523cb4ec0,384720,231787,3388795,16384,24835663,144,48,0,48089,48089,3829092.0,2997486.0,6817.0,1195373.0,2026394.0,0.0,2988395.0,2677604.0,383263,241738,48089,0,48089,0,1538848.0,957400.0,0.0,0.0,64,0x7fcc1245cec0,0,0,192,0,65536,64472,48,1328,31839,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48347,1831,0,48.0,437.0,0.0,262288.0,64,0x7f2d7f184ec0,190196,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,15168,31552,9913,588,0,47316,262789.0,0.0,188.0,262601.0,64,0x7fb14ce7cec0,0,2707818,4096,4096,0,2359315,4096,4096,0,4992079,4096,4096,0,2435030,4096,4096,0,2666027,4096,4096,0,2511436,4096,4096,0,2631207,4096,4096,0,3405588,4096,4096,0,2510445,4096,4096,0,2820195,4096,4096,0,3121713,4096,4096,0,5554202,4096,4096,0,2469755,4096,4096,0,2779420,4096,4096,0,2901409,4096,4096,0,2595005,4096,4096,0,2565875,4096,4096,0,3472642,4096,4096,0,3374518,4096,4096,0,3086844,4096,4096,0,2223914,4096,4096,0,3447468,4096,4096,0,3248870,4096,4096,0,2746499,4096,4096,0,2158453,4096,4096,0,2908615,4096,4096,0,3746480,4096,4096,0,3601964,4096,4096,0,2821394,4096,4096,0,2174136,4096,4096,0,4078539,4096,4096,0,3076895,4096,4096,64,0x7f646a04cec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86864.0,44208.0,131111.0,0.0,64,0x7fb125510ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131481.0,0.0,810.0,131480.0,64,0x7fe0923e8ec0,1782,0,0,1877950,3080,0,0,2003112,4346,0,0,2081533,2007,0,0,1877937,972,0,0,1699130,1308,0,0,1794710,1606,0,0,1768437,2334,0,0,1897305,578,0,0,1613245,730,0,0,1654149,1302,0,0,1814752,2873,0,0,2022757,658,0,0,1641162,916,0,0,1735730,722,0,0,1598498,2499,0,0,1878567,996,0,0,1588358,1955,0,0,1920102,3692,0,0,2068989,1680,0,0,1838862,3363,0,0,1955747,1480,0,0,1744549,3687,0,0,2055692,3029,0,0,1973842,2516,0,0,1946299,279,0,0,1557681,3062,0,0,1938904,3323,0,0,2030489,1439,0,0,1737866,600,0,0,1625394,2506,0,0,1826794,1660,0,0,1828076,64,0x7f729e670ec0,1672486,360448,163840,0,0,180224,114688,0,69482572.0,180670384.0,72545954.0,131072.0,0.0,611734.0,0,0,26474,54561.0,0.0,0.0,54561.0,64,0x7f84dd834ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8314,4218,8314,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,1410267415496161,1410267415520481 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7e16ff8ec0,131072.0,131072.0,0.0,2725847.0,0.0,0.0,112676306.0,38192820.0,64,0x7f99ce778ec0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,0,43144,0,0,64,0x7f5472514ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,240.0,524288.0,0.0,0.0,0,0,5537,44452,1053,131889.0,131072.0,0.0,87334.0,64,0x7f792b44cec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb653fd8ec0,4096,0,538,0,4096,0,1552,0,4096,0,1846,0,4096,0,1297,0,4096,0,1595,0,4096,0,27,0,4096,0,27,0,4096,0,72,0,4096,0,905,0,4096,0,1110,0,4096,0,350,0,4145,0,2659,0,4096,0,542,0,4096,0,359,0,4096,0,1365,0,4096,0,0,0,4096,0,856,0,4097,0,289,0,4357,0,6838,0,4096,0,136,0,4096,0,116,0,4096,0,1735,0,4096,0,1295,0,4097,0,0,0,4096,0,1374,0,4096,0,1266,0,4216,0,163,0,4097,0,1232,0,4096,0,1772,0,4097,0,0,0,4096,0,586,0,4096,0,21,0,64,0x7f2cedd54ec0,0.0,64,0x7ff4a81d0ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,58882.0,159823.0,64,0x7fac322c8ec0,32768,0,0,0,16384,16384,393216,23734484,1194.0,511349.0,0.0,524288.0,1391182.0,32768.0,0,0,0,15232,89392.0,89392.0,0.0,89392.0,64,0x7fb523cb4ec0,339464,227102,3315228,16384,24549987,0,48,0,42432,42432,3696221.0,3027199.0,6750.0,1010463.0,2115084.0,0.0,3018131.0,2706141.0,339456,236893,42432,0,42432,0,1357824.0,806828.0,0.0,0.0,64,0x7fcc1245cec0,0,0,48,0,65536,65536,0,0,31292,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,43206,1684,0,48.0,481.0,0.0,262144.0,64,0x7f2d7f184ec0,127255,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14025,30409,18038,5998,0,40747,262738.0,0.0,47.0,262691.0,64,0x7fb14ce7cec0,0,3315605,2712,2712,0,3528482,2704,2704,0,4861170,2720,2720,0,3627754,2717,2717,0,2752808,2670,2670,0,2770387,2709,2709,0,4486649,2782,2782,0,3279321,2724,2724,0,3966646,2680,2680,0,3219118,2666,2666,0,3825313,2710,2710,0,5254473,2738,2738,0,3500306,2688,2688,0,3076860,2684,2684,0,3865991,2718,2718,0,3358405,2712,2712,0,2964128,2670,2670,0,3834462,2692,2692,0,3495705,2728,2728,0,3849282,2729,2729,0,4099758,2688,2688,0,3468250,2722,2722,0,3905408,2698,2698,0,5158890,2706,2706,0,4032077,2688,2688,0,3391770,2688,2688,0,3700757,2756,2756,0,3116050,2724,2724,0,3394784,2710,2710,0,2970162,2693,2693,0,3549218,2734,2734,0,3816665,2714,2714,64,0x7f646a04cec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87118.0,0.0,131112.0,0.0,64,0x7fb125510ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131533.0,0.0,920.0,131532.0,64,0x7fe0923e8ec0,604,0,0,1227745,1997,0,0,1427067,2287,0,0,1430235,1831,0,0,1453383,2362,0,0,1603339,460,0,0,1283275,910,0,0,1314839,1631,0,0,1393227,950,0,0,1321708,2221,0,0,1578051,1365,0,0,1254500,1179,0,0,1407914,777,0,0,1292158,2235,0,0,1588112,1552,0,0,1427708,1207,0,0,1347829,869,0,0,1318720,1042,0,0,1336372,3109,0,0,1577792,733,0,0,1257827,431,0,0,1184960,796,0,0,1361248,3748,0,0,1660907,999,0,0,1307236,1155,0,0,1383939,162,0,0,1209898,3074,0,0,1630705,2302,0,0,1592760,3329,0,0,1708128,2044,0,0,1408550,1715,0,0,1398871,1377,0,0,1354871,64,0x7f729e670ec0,259213,360448,163840,0,0,180224,114688,0,73329729.0,208451164.0,80319935.0,131072.0,0.0,630850.0,0,0,24064,61320.0,0.0,0.0,61320.0,64,0x7f84dd834ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8314,4218,8314,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,1410267415589601,1410267415608321 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f7e16ff8ec0,131072.0,131072.0,0.0,2511441.0,0.0,0.0,113476170.0,50802851.0,64,0x7f99ce778ec0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,0,42384,0,0,64,0x7f5472514ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2740,40381,0,131456.0,131072.0,0.0,86859.0,64,0x7f792b44cec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7fb653fd8ec0,4096,0,577,0,4096,0,2575,0,4096,0,2458,0,4096,0,291,0,4096,0,6011,0,4096,0,2505,0,4096,0,941,0,4096,0,755,0,4096,0,966,0,4096,0,3551,0,4096,0,2659,0,4145,0,100,0,4096,0,2850,0,4096,0,2238,0,4096,0,2797,0,4096,0,271,0,4096,0,1214,0,4097,0,3096,0,4336,0,3843,0,4096,0,0,0,4096,0,1286,0,4096,0,2418,0,4096,0,1176,0,4097,0,0,0,4096,0,472,0,4096,0,2415,0,4216,0,1442,0,4097,0,0,0,4096,0,149,0,4097,0,387,0,4096,0,2421,0,4096,0,0,0,64,0x7f2cedd54ec0,0.0,64,0x7ff4a81d0ec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,42436.0,140639.0,64,0x7fac322c8ec0,32768,0,0,0,16384,16384,393216,22384835,960.0,513922.0,0.0,524288.0,963142.0,32768.0,0,0,0,13819,86643.0,86643.0,0.0,86643.0,64,0x7fb523cb4ec0,337016,226940,3333509,16384,24495460,0,48,0,42126,42126,3692815.0,2994321.0,5504.0,1020952.0,2079546.0,0.0,2985358.0,2674146.0,337008,236175,42126,0,42126,0,1348032.0,798703.0,0.0,0.0,64,0x7fcc1245cec0,0,0,48,0,65536,65536,0,0,31295,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,457,42662,1684,0,48.0,471.0,0.0,262144.0,64,0x7f2d7f184ec0,187034,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,15680,32064,8457,2389,0,41679,262659.0,0.0,47.0,262612.0,64,0x7fb14ce7cec0,0,3156747,2692,2692,0,3296809,2704,2704,0,3887277,2646,2646,0,3252534,2714,2714,0,3380083,2660,2660,0,3461365,2706,2706,0,3034459,2708,2708,0,4864893,2724,2724,0,3588558,2688,2688,0,3448734,2690,2690,0,2927204,2704,2704,0,4871628,2724,2724,0,4201610,2680,2680,0,4335430,2704,2704,0,3466980,2668,2668,0,3726612,2703,2703,0,4402450,2689,2689,0,4094324,2678,2678,0,3554176,2692,2692,0,3127313,2716,2716,0,3547539,2674,2674,0,4875395,2740,2740,0,3134433,2690,2690,0,4148613,2698,2698,0,2872587,2664,2664,0,3709199,2706,2706,0,4740538,2724,2724,0,3855513,2730,2730,0,3104284,2710,2710,0,3953682,2716,2716,0,3096243,2690,2690,0,4325476,2712,2712,64,0x7f646a04cec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87087.0,0.0,131112.0,0.0,64,0x7fb125510ec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131528.0,0.0,910.0,131527.0,64,0x7fe0923e8ec0,1989,0,0,1542904,2138,0,0,1503775,1198,0,0,1328814,5711,0,0,1810237,657,0,0,1332932,510,0,0,1360601,1459,0,0,1418357,2872,0,0,1588951,1373,0,0,1403758,1928,0,0,1417972,1549,0,0,1436761,1091,0,0,1424378,1329,0,0,1371960,1906,0,0,1482469,764,0,0,1263132,2815,0,0,1548953,724,0,0,1317074,929,0,0,1418554,3777,0,0,1665597,827,0,0,1352179,1756,0,0,1490921,1387,0,0,1428155,984,0,0,1301106,2826,0,0,1499110,1967,0,0,1447557,1393,0,0,1470906,1469,0,0,1479509,3026,0,0,1482223,3443,0,0,1649423,1858,0,0,1507751,1404,0,0,1446517,1960,0,0,1438531,64,0x7f729e670ec0,1209393,360448,163840,0,0,180224,114688,0,70799189.0,198478720.0,78779099.0,131072.0,0.0,634538.0,0,0,25370,52364.0,0.0,0.0,52364.0,64,0x7f84dd834ec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8194,4098,8194,0,8192,4096,8192,0,8193,4097,8193,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8314,4218,8314,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,1410267415628801,1410267415647841 diff --git a/tests/workloads/no_roof/MI100/sysinfo.csv b/tests/workloads/no_roof/MI100/sysinfo.csv index ab89515ba7..8a6148ab1d 100644 --- a/tests/workloads/no_roof/MI100/sysinfo.csv +++ b/tests/workloads/no_roof/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -no_roof,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:11:41 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +no_roof,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:55:21 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/no_roof/MI100/timestamps.csv b/tests/workloads/no_roof/MI100/timestamps.csv index 370f44eab9..42a8ca4c0c 100644 --- a/tests/workloads/no_roof/MI100/timestamps.csv +++ b/tests/workloads/no_roof/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,226316,226316,1048576,256,0,0,8,8,16,64,0x0,0x7f3373120e80,194448655943536,194448655968796,194448655993276,194448656004061 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,226316,226316,1048576,256,0,0,8,8,16,64,0x0,0x7f3373120e80,194448656006014,194448656081116,194448656100796,194448656102216 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,226316,226316,1048576,256,0,0,8,8,16,64,0x0,0x7f3373120e80,194448656113227,194448656120796,194448656139516,194448656140549 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1291373,1291373,1048576,256,0,0,8,8,16,64,0x0,0x7f92074e8ec0,1410267415471673,1410267415496161,1410267415520481,1410267415531036 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1291373,1291373,1048576,256,0,0,8,8,16,64,0x0,0x7f92074e8ec0,1410267415533260,1410267415589601,1410267415608321,1410267415613371 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1291373,1291373,1048576,256,0,0,8,8,16,64,0x0,0x7f92074e8ec0,1410267415620544,1410267415628801,1410267415647841,1410267415649228 diff --git a/tests/workloads/no_roof/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/no_roof/MI200/SQ_IFETCH_LEVEL.csv new file mode 100644 index 0000000000..c09229a193 --- /dev/null +++ b/tests/workloads/no_roof/MI200/SQ_IFETCH_LEVEL.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4184358,4184358,1048576,256,0,0,8,0,16,64,0x0,0x7fc0ead1cec0,28477,28477,16384,65536,14262,1588424,1413814665669215,1413827795608813,1413827795628973,1413814681591646 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4184358,4184358,1048576,256,0,0,8,0,16,64,0x0,0x7fc0ead1cec0,42607,42607,16384,65536,9511,1048724,1413814681612656,1413827795648013,1413827795663693,1413814681922222 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4184358,4184358,1048576,256,0,0,8,0,16,64,0x0,0x7fc0ead1cec0,41802,41802,16384,65536,9736,1048632,1413814681951357,1413827795717293,1413827795733933,1413814682116689 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/no_roof/MI200/SQ_INST_LEVEL_LDS.csv similarity index 52% rename from tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_LDS.csv rename to tests/workloads/no_roof/MI200/SQ_INST_LEVEL_LDS.csv index e61b8446d9..e047771a30 100644 --- a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/no_roof/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,353442,353442,1048576,256,0,0,8,0,16,64,0x0,0x7ff70b594ec0,0,0,0,199843177960026,199855576360179,199855576380339,199843194318883 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,353442,353442,1048576,256,0,0,8,0,16,64,0x0,0x7ff70b594ec0,0,0,0,199843194336376,199855576464819,199855576481459,199843194664897 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,353442,353442,1048576,256,0,0,8,0,16,64,0x0,0x7ff70b594ec0,0,0,0,199843194690786,199855576502899,199855576518579,199843194840179 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4184559,4184559,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18560ec0,0,0,0,1413815155993451,1413827795608813,1413827795628973,1413815172054154 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4184559,4184559,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18560ec0,0,0,0,1413815172071587,1413827795648013,1413827795663693,1413815172387324 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4184559,4184559,1048576,256,0,0,8,0,16,64,0x0,0x7f4f18560ec0,0,0,0,1413815172413954,1413827795717293,1413827795733933,1413815172574277 diff --git a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/no_roof/MI200/SQ_INST_LEVEL_SMEM.csv similarity index 50% rename from tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_SMEM.csv rename to tests/workloads/no_roof/MI200/SQ_INST_LEVEL_SMEM.csv index 828e62e38c..5d69d01c28 100644 --- a/tests/workloads/kernel_verbose_0/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/no_roof/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,193861,193861,1048576,256,0,0,8,8,16,64,0x0,0x7ff8500b4e80,65536,225500,28899672,194342366867588,194353571654480,194353571678800,194342374487095 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,193861,193861,1048576,256,0,0,8,8,16,64,0x0,0x7ff8500b4e80,65536,194502,24913400,194342374506732,194353571699280,194353571718320,194342374802732 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,193861,193861,1048576,256,0,0,8,8,16,64,0x0,0x7ff8500b4e80,65536,192152,24574592,194342374831306,194353571787600,194353571806320,194342375002130 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4184759,4184759,1048576,256,0,0,8,0,16,64,0x0,0x7f55ff5a8ec0,65536,198196,22108264,1413815644179864,1413827795608813,1413827795628973,1413815660495739 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4184759,4184759,1048576,256,0,0,8,0,16,64,0x0,0x7f55ff5a8ec0,65536,303424,34024096,1413815660513342,1413827795648013,1413827795663693,1413815660807549 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4184759,4184759,1048576,256,0,0,8,0,16,64,0x0,0x7f55ff5a8ec0,65536,268926,30243344,1413815660834500,1413827795717293,1413827795733933,1413815660988661 diff --git a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/no_roof/MI200/SQ_INST_LEVEL_VMEM.csv similarity index 50% rename from tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_VMEM.csv rename to tests/workloads/no_roof/MI200/SQ_INST_LEVEL_VMEM.csv index b7945dfdb8..dbe5afd72e 100644 --- a/tests/workloads/kernel_verbose_5/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/no_roof/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,353845,353845,1048576,256,0,0,8,0,16,64,0x0,0x7fd4b4cecec0,32768,297864,33349068,199844136266023,199855576360179,199855576380339,199844152348036 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,353845,353845,1048576,256,0,0,8,0,16,64,0x0,0x7fd4b4cecec0,32768,606519,67931848,199844152365519,199855576464819,199855576481459,199844152661319 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,353845,353845,1048576,256,0,0,8,0,16,64,0x0,0x7fd4b4cecec0,32768,573147,64198532,199844152687678,199855576502899,199855576518579,199844152842461 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4184962,4184962,1048576,256,0,0,8,0,16,64,0x0,0x7f976d220ec0,32768,292794,32792384,1413816128424863,1413827795608813,1413827795628973,1413816144753643 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4184962,4184962,1048576,256,0,0,8,0,16,64,0x0,0x7f976d220ec0,32768,578026,64737004,1413816144770665,1413827795648013,1413827795663693,1413816145060794 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4184962,4184962,1048576,256,0,0,8,0,16,64,0x0,0x7f976d220ec0,32768,581360,65111080,1413816145086913,1413827795717293,1413827795733933,1413816145249741 diff --git a/tests/workloads/no_roof/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/no_roof/MI200/SQ_LEVEL_WAVES.csv new file mode 100644 index 0000000000..588f087204 --- /dev/null +++ b/tests/workloads/no_roof/MI200/SQ_LEVEL_WAVES.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4185145,4185145,1048576,256,0,0,8,0,16,64,0x0,0x7f3404edcec0,28045,28045,11075,224368,16384,11063352,131518,0,44759724,1413816616200950,1413827795608813,1413827795628973,1413816632261973 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4185145,4185145,1048576,256,0,0,8,0,16,64,0x0,0x7f3404edcec0,41735,41735,12866,333888,16384,20594073,233290,0,82860552,1413816632289415,1413827795648013,1413827795663693,1413816632574124 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4185145,4185145,1048576,256,0,0,8,0,16,64,0x0,0x7f3404edcec0,42044,42044,12728,336360,16384,20478340,233297,0,82404904,1413816632609521,1413827795717293,1413827795733933,1413816632845046 diff --git a/tests/workloads/no_roof/MI200/log.txt b/tests/workloads/no_roof/MI200/log.txt new file mode 100644 index 0000000000..ac267318db --- /dev/null +++ b/tests/workloads/no_roof/MI200/log.txt @@ -0,0 +1,738 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/no_roof/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_165442' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165442_4184198' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165442_4184198/input0_results_240321_165442' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165442_4184198/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165442_4184198/input0_results_240321_165442 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_165442' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165442_4184399' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165442_4184399/input0_results_240321_165442' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165442_4184399/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165442_4184399/input0_results_240321_165442 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_165443' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165443_4184599' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165443_4184599/input0_results_240321_165443' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165443_4184599/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165443_4184599/input0_results_240321_165443 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_165443' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165443_4184802' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165443_4184802/input0_results_240321_165443' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165443_4184802/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165443_4184802/input0_results_240321_165443 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_165444' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165444_4184985' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165444_4184985/input0_results_240321_165444' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165444_4184985/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165444_4184985/input0_results_240321_165444 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_165444' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165444_4185181' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165444_4185181/input0_results_240321_165444' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165444_4185181/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165444_4185181/input0_results_240321_165444 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_165445' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165445_4185364' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165445_4185364/input0_results_240321_165445' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165445_4185364/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165445_4185364/input0_results_240321_165445 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_165445' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165445_4185565' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165445_4185565/input0_results_240321_165445' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165445_4185565/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165445_4185565/input0_results_240321_165445 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_165446' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165446_4185767' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165446_4185767/input0_results_240321_165446' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165446_4185767/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165446_4185767/input0_results_240321_165446 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_165446' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165446_4185969' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165446_4185969/input0_results_240321_165446' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165446_4185969/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165446_4185969/input0_results_240321_165446 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_165447' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165447_4186170' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165447_4186170/input0_results_240321_165447' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165447_4186170/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165447_4186170/input0_results_240321_165447 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_165448' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165448_4186356' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165448_4186356/input0_results_240321_165448' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165448_4186356/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165448_4186356/input0_results_240321_165448 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_165448' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165448_4186559' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165448_4186559/input0_results_240321_165448' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165448_4186559/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165448_4186559/input0_results_240321_165448 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_165449' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165449_4186746' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165449_4186746/input0_results_240321_165449' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165449_4186746/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165449_4186746/input0_results_240321_165449 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_165450' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165450_4186929' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165450_4186929/input0_results_240321_165450' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165450_4186929/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165450_4186929/input0_results_240321_165450 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_165451' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165451_4187130' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165451_4187130/input0_results_240321_165451' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165451_4187130/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165451_4187130/input0_results_240321_165451 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_165451' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165451_4187331' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165451_4187331/input0_results_240321_165451' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165451_4187331/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165451_4187331/input0_results_240321_165451 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_165452' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165452_4187533' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165452_4187533/input0_results_240321_165452' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165452_4187533/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165452_4187533/input0_results_240321_165452 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_165452' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165452_4187716' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165452_4187716/input0_results_240321_165452' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165452_4187716/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165452_4187716/input0_results_240321_165452 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_165453' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165453_4187917' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165453_4187917/input0_results_240321_165453' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165453_4187917/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165453_4187917/input0_results_240321_165453 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_165453' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165453_4188118' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165453_4188118/input0_results_240321_165453' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165453_4188118/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165453_4188118/input0_results_240321_165453 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_165454' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165454_4188321' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165454_4188321/input0_results_240321_165454' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165454_4188321/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165454_4188321/input0_results_240321_165454 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_165454' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165454_4188504' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165454_4188504/input0_results_240321_165454' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165454_4188504/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165454_4188504/input0_results_240321_165454 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_165455' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165455_4188691' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165455_4188691/input0_results_240321_165455' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165455_4188691/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165455_4188691/input0_results_240321_165455 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/no_roof/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_165455' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/no_roof/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_165455_4188875' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_165455_4188875/input0_results_240321_165455' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_165455_4188875/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_165455_4188875/input0_results_240321_165455 + |-> [rocprof] File 'tests/workloads/no_roof/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Skipping roofline diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/SQ_IFETCH_LEVEL.txt b/tests/workloads/no_roof/MI200/perfmon/SQ_IFETCH_LEVEL.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI100/perfmon/SQ_IFETCH_LEVEL.txt rename to tests/workloads/no_roof/MI200/perfmon/SQ_IFETCH_LEVEL.txt diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/SQ_INST_LEVEL_LDS.txt b/tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_LDS.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI100/perfmon/SQ_INST_LEVEL_LDS.txt rename to tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_LDS.txt diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt b/tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt rename to tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt b/tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt rename to tests/workloads/no_roof/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt diff --git a/tests/workloads/kernel_summaries/MI100/perfmon/SQ_LEVEL_WAVES.txt b/tests/workloads/no_roof/MI200/perfmon/SQ_LEVEL_WAVES.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI100/perfmon/SQ_LEVEL_WAVES.txt rename to tests/workloads/no_roof/MI200/perfmon/SQ_LEVEL_WAVES.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_0.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_0.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_0.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_0.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_1.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_1.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_1.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_1.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_10.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_10.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_10.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_10.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_11.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_11.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_11.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_11.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_12.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_12.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_12.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_12.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_13.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_13.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_13.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_13.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_14.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_14.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_14.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_14.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_15.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_15.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_15.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_15.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_16.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_16.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_16.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_16.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_17.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_17.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_17.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_17.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_18.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_18.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_18.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_18.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_2.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_2.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_2.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_2.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_3.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_3.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_3.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_3.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_4.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_4.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_4.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_4.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_5.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_5.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_5.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_5.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_6.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_6.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_6.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_6.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_7.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_7.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_7.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_7.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_8.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_8.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_8.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_8.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_9.txt b/tests/workloads/no_roof/MI200/perfmon/pmc_perf_9.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/pmc_perf_9.txt rename to tests/workloads/no_roof/MI200/perfmon/pmc_perf_9.txt diff --git a/tests/workloads/kernel_summaries/MI200/perfmon/timestamps.txt b/tests/workloads/no_roof/MI200/perfmon/timestamps.txt similarity index 100% rename from tests/workloads/kernel_summaries/MI200/perfmon/timestamps.txt rename to tests/workloads/no_roof/MI200/perfmon/timestamps.txt diff --git a/tests/workloads/no_roof/MI200/pmc_dispatch_info.csv b/tests/workloads/no_roof/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/no_roof/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/no_roof/MI200/pmc_perf.csv b/tests/workloads/no_roof/MI200/pmc_perf.csv new file mode 100644 index 0000000000..f486a90b65 --- /dev/null +++ b/tests/workloads/no_roof/MI200/pmc_perf.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_1,obj_1,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_2,obj_2,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_3,obj_3,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_4,obj_4,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_5,obj_5,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_6,obj_6,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_7,obj_7,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_9,obj_9,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_10,obj_10,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_11,obj_11,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_12,obj_12,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_13,obj_13,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_14,obj_14,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_15,obj_15,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_16,obj_16,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_17,obj_17,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_18,obj_18,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f2c5d468ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39253961.0,35213232.0,0.0,64,0x7fa1fea70ec0,6365,0,4096,6434,0,4096,6346,0,4096,6410,0,4096,6401,0,4096,6382,0,4096,6372,0,4096,6392,0,4096,6393,0,4096,6370,0,4096,6437,0,4096,6346,0,4096,6414,0,4096,6407,0,4096,6385,0,4096,6378,0,4096,6394,0,4096,6410,0,4096,6401,0,4096,6404,0,4096,6410,0,4096,6406,0,4096,6334,0,4096,6560,0,4096,6393,0,4096,6396,0,4096,6415,0,4096,6403,0,4096,6408,0,4096,6413,0,4096,6406,0,4096,6336,0,4096,64,0x7f087ea98ec0,1298,117340,0,0,65536,63800,56,1680,64,0x7f4bbf8fcec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,975198.0,64,0x7fb308240ec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,266,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4100,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7f4bf25e4ec0,0,0,0,224,0,65536,64236,56,64,0x7f91bead8ec0,32768,32768,0,64,0x7f4897aa0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10520,0,816,28612,0,73514.0,131072.0,0.0,65568.0,64,0x7f3655978ec0,0,393216,163840,0,0,0,0,0,17739,0.0,0.0,0.0,32768.0,0.0,0.0,375.0,32768.0,4096,16384,352,28322,2013,0,56.0,7.0,0.0,203422.0,64,0x7f68d75f8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,35349.0,46161.0,19375.0,64,0x7f7666930ec0,0,1142487,4096,4096,0,1229074,4096,4096,0,1286730,4096,4096,0,1186682,4096,4096,0,1214538,4096,4096,0,1452747,4096,4096,0,1116622,4096,4096,0,1427244,4096,4096,0,1023388,4096,4096,0,1349795,4096,4096,0,1187612,4096,4096,0,1180743,4096,4096,0,1203726,4096,4096,0,1253545,4096,4096,0,1331822,4096,4096,0,1252342,4096,4096,0,1163116,4096,4096,0,1217274,4096,4096,0,1125853,4096,4096,0,1299207,4096,4096,0,1138773,4096,4096,0,1019506,4096,4096,0,1211606,4096,4096,0,1304581,4096,4096,0,1375961,4096,4096,0,1140304,4096,4096,0,1112153,4096,4096,0,1468582,4096,4096,0,1453198,4096,4096,0,1163585,4096,4096,0,1047285,4096,4096,0,1333634,4096,4096,64,0x7fc92a420ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12804,19568,8089,545,0,26441,204262.0,0.0,73181.0,131081.0,64,0x7fc606e68ec0,2252,4096,2252,6348,2267,4096,2267,6363,2251,4096,2251,6347,2401,4097,2402,6498,2224,4096,2224,6320,2285,4096,2285,6381,2288,4096,2288,6384,2338,4097,2339,6435,2339,4096,2339,6435,2252,4096,2252,6348,2267,4096,2267,6363,2256,4096,2256,6352,2343,4096,2343,6439,2226,4096,2226,6322,2283,4096,2283,6379,2287,4096,2287,6383,2280,4096,2280,6376,2301,4096,2301,6397,2274,4097,2275,6371,2253,4096,2253,6349,2347,4096,2347,6443,2324,4096,2324,6420,2255,4096,2255,6351,2449,4098,2451,6547,2286,4096,2286,6382,2279,4096,2279,6375,2300,4097,2301,6397,2272,4096,2272,6368,2257,4096,2257,6353,2349,4096,2349,6445,2328,4096,2328,6424,2256,4096,2256,6352,64,0x7f1617aecec0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,0,28093,0,0,64,0x7f06b9b18ec0,227592,125929,16384,0,16384,16384,32768,49152,28448,28448,1914606.0,1324797.0,3737.0,160950.0,1031983.0,0.0,1317068.0,1019057.0,225881,134056,28448,0,28448,0,910336.0,483111.0,0.0,0.0,64,0x7ff8b65f8ec0,11066460,9777421,944975,344064,1650503,0,0,163840,832.0,515140.0,0.0,524288.0,254785.0,32768.0,516841,0,0,11227,131072.0,131072.0,0.0,131072.0,64,0x7f133d0c8ec0,114688,0,32768,32768,16384,16384,65536,49152,27662286.0,84151659.0,38864728.0,131072.0,0.0,250759.0,0,0,14614,111.0,131082.0,0.0,12.0,64,0x7f71bedd8ec0,0,0,0,1027304,57,0,0,1156762,0,0,0,1113068,0,0,0,1143141,0,0,0,1101986,39,0,0,1222289,16,0,0,1120098,0,0,0,1164210,0,0,0,985034,60,0,0,1113623,59,0,0,1099586,0,0,0,1106983,0,0,0,1065378,0,0,0,1118486,46,0,0,1158091,0,0,0,1167719,113,0,0,1121198,31,0,0,1111729,243,0,0,1191012,57,0,0,1080700,36,0,0,1161006,55,0,0,1249043,0,0,0,1087152,0,0,0,1085012,0,0,0,1096423,14,0,0,1017630,0,0,0,1104846,98,0,0,1207167,76,0,0,1215619,0,0,0,1117373,38,0,0,1216196,0,0,0,1162268,64,0x7f66e9e98ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,1413827795608813,1413827795628973 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f2c5d468ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,114069729.0,58062823.0,0.0,64,0x7fa1fea70ec0,6300,0,4096,6267,0,4096,6254,0,4096,6244,0,4096,6251,0,4096,6270,0,4096,6242,0,4096,6251,0,4096,6250,0,4096,6299,0,4096,6270,0,4096,6260,0,4096,6243,0,4096,6258,0,4096,6268,0,4096,6244,0,4096,6266,0,4096,6275,0,4096,6287,0,4096,6273,0,4096,6257,0,4096,6260,0,4096,6295,0,4096,6281,0,4096,6283,0,4096,6268,0,4096,6280,0,4096,6289,0,4096,6274,0,4096,6260,0,4096,6261,0,4096,6297,0,4096,64,0x7f087ea98ec0,0,184192,0,0,65536,63800,56,1680,64,0x7f4bbf8fcec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2028771.0,64,0x7fb308240ec0,4096,0,6,0,4096,0,10,0,4096,0,2426,0,4096,0,684,0,4096,0,1603,0,4096,0,339,0,4096,0,0,0,4099,0,241,0,4096,0,133,0,4099,0,241,0,4096,0,0,0,4096,0,74,0,4096,0,1316,0,4096,0,240,0,4096,0,286,0,4096,0,0,0,4096,0,364,0,4096,0,213,0,4097,0,190,0,4096,0,798,0,4096,0,379,0,4096,0,713,0,4096,0,0,0,4097,0,258,0,4096,0,571,0,4096,0,0,0,4096,0,114,0,4096,0,197,0,4096,0,134,0,4096,0,0,0,4097,0,1061,0,4096,0,873,0,64,0x7f4bf25e4ec0,0,0,0,56,0,65536,65536,0,64,0x7f91bead8ec0,32768,32768,0,64,0x7f4897aa0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,15622,0,819,36383,0,68989.0,131072.0,0.0,45426.0,64,0x7f3655978ec0,0,393216,163840,0,0,0,0,0,28912,0.0,0.0,0.0,32768.0,0.0,0.0,224.0,32768.0,4096,16384,302,40866,2086,0,56.0,9.0,0.0,200577.0,64,0x7f68d75f8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,87555.0,45636.0,0.0,64,0x7f7666930ec0,0,3817402,2816,2816,0,3057931,2842,2842,0,3148073,2860,2860,0,5130266,2868,2868,0,3366657,2908,2908,0,3900287,2868,2868,0,3259050,2840,2840,0,3590621,2812,2812,0,3007635,2810,2810,0,3468943,2816,2816,0,3042322,2844,2844,0,3913503,2864,2864,0,3702565,2864,2864,0,3764853,2912,2912,0,3210390,2864,2864,0,3835531,2840,2840,0,3773751,2812,2812,0,3448747,2848,2848,0,3189836,2830,2830,0,3625697,2822,2822,0,3090491,2832,2832,0,3815209,2880,2880,0,4014589,2848,2848,0,5073018,2848,2848,0,4566402,2846,2846,0,2947008,2812,2812,0,3344825,2844,2844,0,3390345,2836,2836,0,4049358,2832,2832,0,4845057,2832,2832,0,4153254,2880,2880,0,3555443,2840,2840,64,0x7fc92a420ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,30514,28147,9536,2903,0,39018,201090.0,0.0,70007.0,131083.0,64,0x7fc606e68ec0,2140,4097,2141,6237,2171,4096,2171,6267,2155,4096,2155,6251,2246,4097,2247,6343,2202,4096,2202,6298,2205,4096,2205,6301,2198,4096,2198,6294,2170,4097,2171,6267,2173,4096,2173,6269,2139,4096,2139,6235,2179,4096,2179,6275,2161,4096,2161,6257,2198,4096,2198,6294,2208,4096,2208,6304,2209,4096,2209,6305,2195,4096,2195,6291,2185,4096,2185,6281,2159,4096,2159,6255,2140,4099,2143,6239,2161,4096,2161,6257,2169,4096,2169,6265,2214,4097,2215,6311,2178,4096,2178,6274,2203,4096,2203,6299,2202,4096,2202,6298,2185,4096,2185,6281,2154,4097,2155,6251,2146,4096,2146,6242,2166,4096,2166,6262,2171,4096,2171,6267,2214,4096,2214,6310,2176,4096,2176,6272,64,0x7f1617aecec0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,0,40392,0,0,64,0x7f06b9b18ec0,324928,218631,16384,0,16384,16384,32768,49152,40615,40615,3115268.0,2405993.0,4041.0,351534.0,1673731.0,0.0,2393856.0,2084390.0,324920,226891,40615,0,40615,0,1299680.0,766390.0,0.0,0.0,64,0x7ff8b65f8ec0,18949042,17706258,898720,344064,2729655,0,0,163840,832.0,515148.0,0.0,524288.0,513645.0,32768.0,913852,0,0,13549,91124.0,91124.0,0.0,91124.0,64,0x7f133d0c8ec0,114688,0,32768,32768,16384,16384,65536,49152,59702636.0,191335600.0,50300706.0,131072.0,0.0,489313.0,0,0,24665,5813.0,131073.0,0.0,0.0,64,0x7f71bedd8ec0,98,0,0,2219003,115,0,0,1800442,0,0,0,1546737,0,0,0,2027002,0,0,0,1708615,421,0,0,2382792,177,0,0,1887090,0,0,0,2098711,102,0,0,2067074,52,0,0,2098447,0,0,0,1838126,0,0,0,1615302,0,0,0,1760277,0,0,0,1780981,0,0,0,1888950,0,0,0,1995306,0,0,0,1598117,0,0,0,1538243,0,0,0,1628528,76,0,0,1928686,0,0,0,1812582,0,0,0,1675537,0,0,0,1730533,0,0,0,2052357,0,0,0,1928895,386,0,0,2164747,0,0,0,1768352,0,0,0,1810076,0,0,0,1985767,0,0,0,1555926,0,0,0,2302655,0,0,0,1889393,64,0x7f66e9e98ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,1413827795648013,1413827795663693 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f2c5d468ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,120631317.0,58749625.0,0.0,64,0x7fa1fea70ec0,6243,0,4096,6287,0,4096,6278,0,4096,6277,0,4096,6265,0,4096,6257,0,4096,6242,0,4096,6247,0,4096,6243,0,4096,6248,0,4096,6287,0,4096,6278,0,4096,6282,0,4096,6265,0,4096,6260,0,4096,6247,0,4096,6262,0,4096,6239,0,4096,6263,0,4096,6260,0,4096,6244,0,4096,6263,0,4096,6248,0,4096,6262,0,4096,6266,0,4096,6260,0,4096,6245,0,4096,6263,0,4096,6260,0,4096,6248,0,4096,6266,0,4096,6255,0,4096,64,0x7f087ea98ec0,0,187466,0,0,65536,63800,56,1680,64,0x7f4bbf8fcec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2031212.0,64,0x7fb308240ec0,4096,0,130,0,4096,0,88,0,4096,0,46,0,4096,0,1032,0,4096,0,122,0,4096,0,296,0,4096,0,41,0,4099,0,432,0,4096,0,0,0,4099,0,278,0,4096,0,149,0,4096,0,538,0,4096,0,524,0,4096,0,78,0,4096,0,0,0,4096,0,0,0,4096,0,342,0,4096,0,100,0,4097,0,185,0,4096,0,422,0,4096,0,785,0,4096,0,507,0,4096,0,247,0,4097,0,91,0,4096,0,0,0,4096,0,158,0,4096,0,103,0,4096,0,45,0,4096,0,592,0,4096,0,79,0,4097,0,243,0,4096,0,0,0,64,0x7f4bf25e4ec0,0,0,0,56,0,65536,65536,0,64,0x7f91bead8ec0,32768,32768,0,64,0x7f4897aa0ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21175,0,2716,39346,0,69881.0,131072.0,0.0,45640.0,64,0x7f3655978ec0,0,393216,163840,0,0,0,0,0,29044,0.0,0.0,0.0,32768.0,0.0,0.0,198.0,32768.0,4096,16384,302,40572,2050,0,56.0,9.0,0.0,200571.0,64,0x7f68d75f8ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131080.0,86170.0,45529.0,0.0,64,0x7f7666930ec0,0,3121915,2846,2846,0,3343959,2892,2892,0,4173289,2880,2880,0,4020415,2880,2880,0,4530011,2888,2888,0,4177127,2854,2854,0,3280655,2852,2852,0,3794503,2812,2812,0,3018000,2812,2812,0,3197890,2848,2848,0,3464976,2892,2892,0,3369812,2880,2880,0,3147361,2884,2884,0,3825851,2892,2892,0,4114503,2852,2852,0,3167547,2856,2856,0,3762102,2804,2804,0,3800522,2824,2824,0,2989675,2860,2860,0,3905679,2884,2884,0,2787161,2852,2852,0,3425174,2908,2908,0,5373882,2840,2840,0,3539954,2848,2848,0,3661571,2856,2856,0,3220649,2808,2808,0,4243443,2826,2826,0,4441318,2860,2860,0,3031166,2880,2880,0,3345058,2860,2860,0,3087765,2908,2908,0,5000882,2846,2846,64,0x7fc92a420ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,31116,28014,9546,2778,0,39002,200948.0,0.0,69867.0,131081.0,64,0x7fc606e68ec0,2174,4097,2175,6271,2164,4096,2164,6260,2160,4096,2160,6256,2238,4097,2239,6335,2128,4096,2128,6224,2155,4096,2155,6251,2170,4096,2170,6266,2192,4097,2193,6289,2194,4096,2194,6290,2174,4096,2174,6270,2172,4096,2172,6268,2156,4096,2156,6252,2184,4096,2184,6280,2129,4096,2129,6225,2160,4096,2160,6256,2172,4096,2172,6268,2165,4096,2165,6261,2181,4096,2181,6277,2161,4099,2164,6260,2181,4096,2181,6277,2192,4096,2192,6288,2163,4097,2164,6260,2147,4096,2147,6243,2145,4096,2145,6241,2148,4096,2148,6244,2165,4096,2165,6261,2181,4097,2182,6278,2162,4096,2162,6258,2183,4096,2183,6279,2196,4096,2196,6292,2163,4096,2163,6259,2148,4096,2148,6244,64,0x7f1617aecec0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,0,41549,0,0,64,0x7f06b9b18ec0,333800,223701,16384,0,16384,16384,32768,49152,41724,41724,3185471.0,2514818.0,4616.0,412078.0,1679449.0,0.0,2503089.0,2196591.0,333792,233001,41724,0,41724,0,1335168.0,788483.0,0.0,0.0,64,0x7ff8b65f8ec0,19924267,18401680,1178523,344064,2868279,0,0,163840,832.0,515150.0,0.0,524288.0,578430.0,32768.0,1071715,0,0,13175,91226.0,91226.0,0.0,91226.0,64,0x7f133d0c8ec0,114688,0,32768,32768,16384,16384,65536,49152,55637354.0,197622583.0,45590753.0,131072.0,0.0,507638.0,0,0,24600,35206.0,131081.0,0.0,16.0,64,0x7f71bedd8ec0,51,0,0,1748831,224,0,0,2260937,749,0,0,2342828,343,0,0,2293545,2150,0,0,2360878,877,0,0,2163162,0,0,0,1527304,643,0,0,2438893,87,0,0,1823290,172,0,0,1842056,0,0,0,1621751,1336,0,0,2035212,600,0,0,2105664,526,0,0,2140025,509,0,0,1828422,0,0,0,1528346,0,0,0,1382608,0,0,0,1470461,0,0,0,1677202,564,0,0,2327795,160,0,0,2011773,185,0,0,1660625,275,0,0,1694512,537,0,0,2097679,470,0,0,2014009,0,0,0,1601614,0,0,0,1631859,0,0,0,1843906,464,0,0,2235413,340,0,0,1879917,40,0,0,1598936,481,0,0,2109215,64,0x7f66e9e98ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,1413827795717293,1413827795733933 diff --git a/tests/workloads/kernel_verbose_0/MI100/sysinfo.csv b/tests/workloads/no_roof/MI200/sysinfo.csv similarity index 52% rename from tests/workloads/kernel_verbose_0/MI100/sysinfo.csv rename to tests/workloads/no_roof/MI200/sysinfo.csv index 4a04b073c6..1b5f2167ea 100644 --- a/tests/workloads/kernel_verbose_0/MI100/sysinfo.csv +++ b/tests/workloads/no_roof/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -kernel_verbose_0,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:10:06 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +no_roof,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 04:54:41 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/kernel_verbose_0/MI200/timestamps.csv b/tests/workloads/no_roof/MI200/timestamps.csv similarity index 50% rename from tests/workloads/kernel_verbose_0/MI200/timestamps.csv rename to tests/workloads/no_roof/MI200/timestamps.csv index 4c39091298..72ea181ee5 100644 --- a/tests/workloads/kernel_verbose_0/MI200/timestamps.csv +++ b/tests/workloads/no_roof/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,363060,363060,1048576,256,0,0,8,0,16,64,0x0,0x7f803b148ec0,199961732731122,199961732754864,199961732775184,199961732787559 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,363060,363060,1048576,256,0,0,8,0,16,64,0x0,0x7f803b148ec0,199961732786176,199961732860464,199961732876784,199961732878270 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,363060,363060,1048576,256,0,0,8,0,16,64,0x0,0x7f803b148ec0,199961732888169,199961732897264,199961732913104,199961732914238 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4189035,4189035,1048576,256,0,0,8,0,16,64,0x0,0x7f31ebb78ec0,1413827795584234,1413827795608813,1413827795628973,1413827795643766 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4189035,4189035,1048576,256,0,0,8,0,16,64,0x0,0x7f31ebb78ec0,1413827795639959,1413827795648013,1413827795663693,1413827795714741 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4189035,4189035,1048576,256,0,0,8,0,16,64,0x0,0x7f31ebb78ec0,1413827795673894,1413827795717293,1413827795733933,1413827795734979 diff --git a/tests/workloads/path/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/path/MI100/SQ_IFETCH_LEVEL.csv index b33635977f..d892e2fcd5 100644 --- a/tests/workloads/path/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/path/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130205,130205,1048576,256,0,0,8,8,16,64,0x0,0x7f1e188c0e80,49176,49176,16384,65536,12923,1629704,194140706168662,194153002188417,194153002212257,194140713966136 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130205,130205,1048576,256,0,0,8,8,16,64,0x0,0x7f1e188c0e80,43143,43143,16384,65536,8155,1048584,194140713987878,194153002382497,194153002401697,194140714336267 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130205,130205,1048576,256,0,0,8,8,16,64,0x0,0x7f1e188c0e80,43319,43319,16384,65536,8275,1048584,194140714368438,194153002423297,194153002442177,194140714551494 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,48280,48280,16384,65536,12983,1679996,1410066882102360,1410078545959517,1410078545984317,1410066889784789 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,42583,42583,16384,65536,8224,1048592,1410066889807272,1410078546083997,1410078546102877,1410066890267580 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,42228,42228,16384,65536,8413,1048584,1410066890299460,1410078546122717,1410078546141597,1410066890460213 diff --git a/tests/workloads/path/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/path/MI100/SQ_INST_LEVEL_LDS.csv index 702c7fd8fa..7bb92ef543 100644 --- a/tests/workloads/path/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/path/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130394,130394,1048576,256,0,0,8,8,16,64,0x0,0x7f47c7d0ee80,0,0,0,194141205843407,194153002188417,194153002212257,194141213761619 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130394,130394,1048576,256,0,0,8,8,16,64,0x0,0x7f47c7d0ee80,0,0,0,194141213779673,194153002382497,194153002401697,194141214095882 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130394,130394,1048576,256,0,0,8,8,16,64,0x0,0x7f47c7d0ee80,0,0,0,194141214124606,194153002423297,194153002442177,194141214303445 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067370617243,1410078545959517,1410078545984317,1410067378299552 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067378319499,1410078546083997,1410078546102877,1410067378620818 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067378648971,1410078546122717,1410078546141597,1410067378823961 diff --git a/tests/workloads/path/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/path/MI100/SQ_INST_LEVEL_SMEM.csv index 867a52000b..ae79254d0a 100644 --- a/tests/workloads/path/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/path/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130583,130583,1048576,256,0,0,8,8,16,64,0x0,0x7ffa81e48e80,65536,207770,26636360,194141699115738,194153002188417,194153002212257,194141706852657 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130583,130583,1048576,256,0,0,8,8,16,64,0x0,0x7ffa81e48e80,65536,172514,22100544,194141706871934,194153002382497,194153002401697,194141707163035 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130583,130583,1048576,256,0,0,8,8,16,64,0x0,0x7ffa81e48e80,65536,173222,22213280,194141707191379,194153002423297,194153002442177,194141707358225 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,216912,27721752,1410067844907387,1410078545959517,1410078545984317,1410067852593644 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,174742,22439080,1410067852616707,1410078546083997,1410078546102877,1410067852942802 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,198278,25317408,1410067852970845,1410078546122717,1410078546141597,1410067853139804 diff --git a/tests/workloads/path/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/path/MI100/SQ_INST_LEVEL_VMEM.csv index 53814011d4..dd1f25ff77 100644 --- a/tests/workloads/path/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/path/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130770,130770,1048576,256,0,0,8,8,16,64,0x0,0x7f2b68738e80,32768,666828,85347504,194142193797318,194153002188417,194153002212257,194142201496365 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130770,130770,1048576,256,0,0,8,8,16,64,0x0,0x7f2b68738e80,32768,685493,87733280,194142201516323,194153002382497,194153002401697,194142201816672 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130770,130770,1048576,256,0,0,8,8,16,64,0x0,0x7f2b68738e80,32768,682699,87381264,194142201844274,194153002423297,194153002442177,194142202018574 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,660786,84583280,1410068324788176,1410078545959517,1410078545984317,1410068332535197 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,671026,85878140,1410068332555144,1410078546083997,1410078546102877,1410068332853858 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,632212,80916468,1410068332882612,1410078546122717,1410078546141597,1410068333052552 diff --git a/tests/workloads/path/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/path/MI100/SQ_LEVEL_WAVES.csv index 121d9a7d4f..419592ce68 100644 --- a/tests/workloads/path/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/path/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,130957,130957,1048576,256,0,0,8,8,16,64,0x0,0x7f1fb6b00e80,48043,48043,16838,384352,16384,23962213,233085,0,96351644,194142688404657,194153002188417,194153002212257,194142696446684 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,130957,130957,1048576,256,0,0,8,8,16,64,0x0,0x7f1fb6b00e80,42690,42690,13932,341528,16384,24486089,227571,0,98428804,194142696476260,194153002382497,194153002401697,194142696816625 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,130957,130957,1048576,256,0,0,8,8,16,64,0x0,0x7f1fb6b00e80,42213,42213,14088,337712,16384,24121330,225136,0,96970788,194142696855067,194153002423297,194153002442177,194142697041180 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,49066,49066,17535,392536,16384,25278471,238150,0,101647680,1410068786184713,1410078545959517,1410078545984317,1410068793791259 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,42938,42938,13608,343512,16384,24688741,232286,0,99287100,1410068793822348,1410078546083997,1410078546102877,1410068794118977 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,43314,43314,13851,346520,16384,25149283,234233,0,101130872,1410068794157149,1410078546122717,1410078546141597,1410068794339493 diff --git a/tests/workloads/path/MI100/log.txt b/tests/workloads/path/MI100/log.txt new file mode 100644 index 0000000000..41d601bea5 --- /dev/null +++ b/tests/workloads/path/MI100/log.txt @@ -0,0 +1,679 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/path/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155212' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155212_1225807' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155212_1225807/input0_results_240321_155212' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155212_1225807/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155212_1225807/input0_results_240321_155212 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155213' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155213_1225993' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155213_1225993/input0_results_240321_155213' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155213_1225993/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155213_1225993/input0_results_240321_155213 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155213' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155213_1226177' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155213_1226177/input0_results_240321_155213' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155213_1226177/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155213_1226177/input0_results_240321_155213 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155214' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155214_1226362' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155214_1226362/input0_results_240321_155214' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155214_1226362/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155214_1226362/input0_results_240321_155214 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155214' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155214_1226550' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155214_1226550/input0_results_240321_155214' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155214_1226550/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155214_1226550/input0_results_240321_155214 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155215' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155215_1226735' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155215_1226735/input0_results_240321_155215' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155215_1226735/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155215_1226735/input0_results_240321_155215 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155215' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155215_1226918' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155215_1226918/input0_results_240321_155215' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155215_1226918/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155215_1226918/input0_results_240321_155215 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155216' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155216_1227103' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155216_1227103/input0_results_240321_155216' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155216_1227103/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155216_1227103/input0_results_240321_155216 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155216' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155216_1227289' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155216_1227289/input0_results_240321_155216' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155216_1227289/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155216_1227289/input0_results_240321_155216 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155217' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155217_1227490' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155217_1227490/input0_results_240321_155217' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155217_1227490/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155217_1227490/input0_results_240321_155217 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155218' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155218_1227691' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155218_1227691/input0_results_240321_155218' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155218_1227691/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155218_1227691/input0_results_240321_155218 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155218' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155218_1227878' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155218_1227878/input0_results_240321_155218' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155218_1227878/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155218_1227878/input0_results_240321_155218 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155219' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155219_1228062' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155219_1228062/input0_results_240321_155219' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155219_1228062/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155219_1228062/input0_results_240321_155219 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155220' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155220_1228263' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155220_1228263/input0_results_240321_155220' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155220_1228263/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155220_1228263/input0_results_240321_155220 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155220' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155220_1228465' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155220_1228465/input0_results_240321_155220' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155220_1228465/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155220_1228465/input0_results_240321_155220 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155221' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155221_1228650' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155221_1228650/input0_results_240321_155221' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155221_1228650/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155221_1228650/input0_results_240321_155221 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155221' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155221_1228834' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155221_1228834/input0_results_240321_155221' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155221_1228834/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155221_1228834/input0_results_240321_155221 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155222' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155222_1229018' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155222_1229018/input0_results_240321_155222' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155222_1229018/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155222_1229018/input0_results_240321_155222 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155222' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155222_1229202' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155222_1229202/input0_results_240321_155222' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155222_1229202/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155222_1229202/input0_results_240321_155222 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155223' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155223_1229386' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155223_1229386/input0_results_240321_155223' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155223_1229386/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155223_1229386/input0_results_240321_155223 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155223' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155223_1229572' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155223_1229572/input0_results_240321_155223' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155223_1229572/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155223_1229572/input0_results_240321_155223 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155224' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155224_1229760' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155224_1229760/input0_results_240321_155224' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155224_1229760/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155224_1229760/input0_results_240321_155224 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155224' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155224_1229944' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155224_1229944/input0_results_240321_155224' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155224_1229944/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155224_1229944/input0_results_240321_155224 + |-> [rocprof] File 'tests/workloads/path/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/path/MI100/pmc_dispatch_info.csv b/tests/workloads/path/MI100/pmc_dispatch_info.csv index 17300ae9af..2166cd6fad 100644 --- a/tests/workloads/path/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/path/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int) ",2 -1,"vecCopy(double*, double*, double*, int, int) ",2 -2,"vecCopy(double*, double*, double*, int, int) ",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/path/MI100/pmc_perf.csv b/tests/workloads/path/MI100/pmc_perf.csv index 04d4a8a859..2908704350 100644 --- a/tests/workloads/path/MI100/pmc_perf.csv +++ b/tests/workloads/path/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_1,obj_1,TCC_EA_ATOMIC_LEVEL_sum,wave_size_2,obj_2,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_5,obj_5,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_6,obj_6,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_7,obj_7,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_8,obj_8,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_9,obj_9,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_10,obj_10,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_11,obj_11,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_12,obj_12,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_13,obj_13,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_16,obj_16,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fed6a764e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131298.0,0.0,444.0,131297.0,64,0x7fbb3c094e80,0.0,64,0x7f1ab5a94e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47080,0,131531.0,131072.0,0.0,131104.0,64,0x7fe0bb890e80,0,0,192,0,65536,64463,48,1410,32340,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48401,1752,0,48.0,239.0,0.0,262288.0,64,0x7f652e0a4e80,4096,0,2688,0,4096,0,2595,0,4099,0,0,0,4096,0,3252,0,4096,0,744,0,4096,0,1446,0,4226,0,1936,0,4096,0,1233,0,4096,0,597,0,4096,0,3227,0,4144,0,35,0,4144,0,5727,0,4096,0,421,0,4096,0,697,0,4096,0,1120,0,4096,0,63,0,4096,0,2439,0,4096,0,988,0,4096,0,1027,0,4096,0,118,0,4096,0,746,0,4096,0,6884,0,4096,0,1528,0,4096,0,1186,0,4096,0,1129,0,4096,0,1603,0,4097,0,312,0,4096,0,645,0,4096,0,770,0,4096,0,0,0,4096,0,0,0,4096,0,628,0,64,0x7f068681ce80,32768,0,0,0,16384,16384,393216,22726723,960.0,513894.0,0.0,524288.0,946940.0,32768.0,0,0,0,17602,131072.0,131072.0,0.0,131072.0,64,0x7f173f900e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,41705.0,104719.0,64,0x7f3f8f660e80,1426925,360448,163840,0,0,180224,114688,0,69570598.0,191177329.0,69715415.0,131072.0,0.0,741461.0,0,0,25861,90393.0,0.0,0.0,90393.0,64,0x7f0d3add8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86498.0,44574.0,131112.0,0.0,64,0x7fc165596e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8401,4305,8401,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7ff7e1030e80,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,0,48747,0,0,64,0x7ff91ee02e80,380232,230659,3376730,16384,25202841,144,48,0,47528,47528,3812906.0,2988819.0,5981.0,1067726.0,2091546.0,0.0,2979697.0,2669974.0,378519,240610,47528,0,47528,0,1520896.0,958674.0,0.0,0.0,64,0x7fae724f8e80,2123,0,0,1888464,2127,0,0,1819592,4596,0,0,2031179,5315,0,0,2040309,2770,0,0,1923009,2966,0,0,1840438,6636,0,0,2227117,4305,0,0,2055700,4652,0,0,2100696,1461,0,0,1669690,5348,0,0,2031993,3528,0,0,1901009,2103,0,0,1825534,4772,0,0,2059773,3429,0,0,1973279,5380,0,0,2032270,1778,0,0,1831314,1232,0,0,1758690,3465,0,0,1955916,5721,0,0,2054655,3191,0,0,1916016,3015,0,0,1931327,5687,0,0,2025228,5573,0,0,2176210,4845,0,0,1996543,1825,0,0,1784456,6011,0,0,2122496,4472,0,0,1932929,4986,0,0,2039207,1711,0,0,1756254,5388,0,0,2025644,4123,0,0,2011270,64,0x7f813c208e80,151696,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14630,31014,9796,550,0,46749,262602.0,0.0,188.0,262414.0,64,0x7f162d8a6e80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f537c4d8e80,131072.0,131072.0,0.0,2473447.0,0.0,0.0,114819646.0,62674933.0,64,0x7ff49fbe8e80,0,4923144,4096,4096,0,4402798,4096,4096,0,3620839,4096,4096,0,4065685,4096,4096,0,5206175,4096,4096,0,3417531,4096,4096,0,3796269,4096,4096,0,3655441,4096,4096,0,3449657,4096,4096,0,4188710,4096,4096,0,3759907,4096,4096,0,5195287,4096,4096,0,3967007,4096,4096,0,3832843,4096,4096,0,3553799,4096,4096,0,2466602,4096,4096,0,3278545,4096,4096,0,5029193,4096,4096,0,4079152,4096,4096,0,3169332,4096,4096,0,3927256,4096,4096,0,3160045,4096,4096,0,3880489,4096,4096,0,2822406,4096,4096,0,3670994,4096,4096,0,3328051,4096,4096,0,3834656,4096,4096,0,2978151,4096,4096,0,4562941,4096,4096,0,3295471,4096,4096,0,4043550,4096,4096,0,4072820,4096,4096,194153002188417,194153002212257 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fed6a764e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131644.0,0.0,1140.0,131642.0,64,0x7fbb3c094e80,0.0,64,0x7f1ab5a94e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2773,40068,0,131414.0,131072.0,0.0,86591.0,64,0x7fe0bb890e80,0,0,48,0,65536,65536,0,0,29505,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,435,39020,1708,0,48.0,0.0,0.0,262144.0,64,0x7f652e0a4e80,4096,0,0,0,4096,0,992,0,4096,0,338,0,4096,0,3671,0,4096,0,657,0,4097,0,0,0,4248,0,4246,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4144,0,1568,0,4145,0,3042,0,4096,0,0,0,4096,0,0,0,4096,0,8595,0,4096,0,192,0,4096,0,0,0,4099,0,0,0,4096,0,929,0,4096,0,1254,0,4096,0,0,0,4096,0,0,0,4096,0,4886,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,2487,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,118,0,4096,0,0,0,64,0x7f068681ce80,32768,0,0,0,16384,16384,393216,22977409,960.0,513934.0,0.0,524288.0,974031.0,32768.0,0,0,0,22517,131072.0,131072.0,0.0,131072.0,64,0x7f173f900e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,35769.0,103674.0,64,0x7f3f8f660e80,3152398,360448,163840,0,0,180224,114688,0,66700982.0,186292211.0,74141321.0,131072.0,0.0,792400.0,0,0,28656,125445.0,0.0,0.0,125445.0,64,0x7f0d3add8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86679.0,44393.0,131110.0,0.0,64,0x7fc165596e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8409,4313,8409,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,64,0x7ff7e1030e80,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,0,42995,0,0,64,0x7ff91ee02e80,345576,233997,3416968,16384,25325336,0,48,0,43196,43196,3799402.0,3067745.0,6932.0,998074.0,2151772.0,0.0,3058824.0,2748485.0,345568,243201,43196,0,43196,0,1382272.0,819528.0,0.0,0.0,64,0x7fae724f8e80,2047,0,0,1537350,2351,0,0,1478611,695,0,0,1200512,4623,0,0,1618861,2484,0,0,1510129,899,0,0,1299250,4825,0,0,1761981,3286,0,0,1673187,1375,0,0,1421988,1624,0,0,1377787,1494,0,0,1465306,1663,0,0,1427913,1280,0,0,1357406,3426,0,0,1646026,367,0,0,1105119,1990,0,0,1450761,3433,0,0,1697235,4109,0,0,1718658,260,0,0,1128526,3803,0,0,1661201,880,0,0,1320944,4768,0,0,1794014,438,0,0,1252681,1831,0,0,1455914,1589,0,0,1346065,3407,0,0,1630979,1801,0,0,1545474,5769,0,0,1717627,1340,0,0,1399902,1414,0,0,1319032,2151,0,0,1489731,6312,0,0,1877994,64,0x7f813c208e80,193067,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13150,29534,15647,5071,0,42018,262483.0,0.0,47.0,262436.0,64,0x7f162d8a6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f537c4d8e80,131072.0,131072.0,0.0,2552326.0,0.0,0.0,137063138.0,48215499.0,64,0x7ff49fbe8e80,0,5025750,2720,2720,0,3483260,2731,2731,0,3380332,2690,2690,0,2727097,2711,2711,0,4113302,2706,2706,0,4776726,2718,2718,0,4109753,2700,2700,0,4183564,2722,2722,0,4358148,2684,2684,0,4755714,2671,2671,0,5173327,2696,2696,0,5445056,2722,2722,0,4015798,2714,2714,0,4280039,2696,2696,0,3816184,2676,2676,0,2999494,2692,2692,0,3863940,2696,2696,0,5326872,2720,2720,0,4018570,2682,2682,0,3726585,2724,2724,0,3381886,2693,2693,0,4586705,2718,2718,0,3009635,2678,2678,0,3305187,2692,2692,0,3797420,2700,2700,0,4705251,2704,2704,0,4438751,2714,2714,0,3254300,2708,2708,0,3553184,2722,2722,0,4068125,2712,2712,0,3634034,2702,2702,0,4164784,2688,2688,194153002382497,194153002401697 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,8,16,64,0x7fed6a764e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131252.0,0.0,358.0,131251.0,64,0x7fbb3c094e80,0.0,64,0x7f1ab5a94e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2773,40234,0,131390.0,131072.0,0.0,86574.0,64,0x7fe0bb890e80,0,0,48,0,65536,65536,0,0,31455,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,432,41999,1744,0,48.0,276.0,0.0,262144.0,64,0x7f652e0a4e80,4096,0,1402,0,4096,0,0,0,4096,0,1258,0,4096,0,1556,0,4096,0,35,0,4097,0,0,0,4330,0,4609,0,4096,0,768,0,4096,0,754,0,4096,0,536,0,4144,0,0,0,4145,0,0,0,4096,0,1334,0,4096,0,0,0,4096,0,294,0,4096,0,109,0,4096,0,547,0,4099,0,778,0,4096,0,966,0,4096,0,214,0,4096,0,97,0,4096,0,8007,0,4096,0,0,0,4096,0,10,0,4096,0,348,0,4096,0,0,0,4097,0,672,0,4096,0,0,0,4096,0,205,0,4096,0,0,0,4096,0,5073,0,4096,0,617,0,64,0x7f068681ce80,32768,0,0,0,16384,16384,393216,22863042,960.0,513898.0,0.0,524288.0,1050123.0,32768.0,0,0,0,14361,86315.0,86315.0,0.0,86315.0,64,0x7f173f900e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,44498.0,110648.0,64,0x7f3f8f660e80,946178,360448,163840,0,0,180224,114688,0,66099733.0,189011811.0,77990549.0,131072.0,0.0,737617.0,0,0,25383,121379.0,0.0,0.0,121379.0,64,0x7f0d3add8e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86541.0,0.0,131112.0,0.0,64,0x7fc165596e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8470,4374,8470,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,64,0x7ff7e1030e80,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,0,44155,0,0,64,0x7ff91ee02e80,341144,229244,3348943,16384,24714401,0,48,0,42642,42642,3728246.0,3046873.0,5043.0,911268.0,2117555.0,0.0,3037216.0,2727310.0,341136,238633,42642,0,42642,0,1364544.0,813033.0,0.0,0.0,64,0x7fae724f8e80,2690,0,0,1636740,1686,0,0,1483894,591,0,0,1253048,3030,0,0,1577627,240,0,0,1299543,2221,0,0,1503734,1331,0,0,1341909,2334,0,0,1563976,1396,0,0,1405202,1216,0,0,1376889,572,0,0,1328686,2290,0,0,1549415,2025,0,0,1510602,4776,0,0,1724784,458,0,0,1271321,3469,0,0,1644875,1463,0,0,1445135,1966,0,0,1488348,327,0,0,1258169,2901,0,0,1544743,2780,0,0,1470952,1831,0,0,1446263,3721,0,0,1635889,5464,0,0,1812586,3789,0,0,1651817,1922,0,0,1445323,3126,0,0,1667460,4193,0,0,1624751,2673,0,0,1541339,2854,0,0,1568037,1876,0,0,1420699,1319,0,0,1410354,64,0x7f813c208e80,199950,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12324,28708,8497,2351,0,40776,262461.0,0.0,47.0,262414.0,64,0x7f162d8a6e80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f537c4d8e80,131072.0,131072.0,0.0,2575139.0,0.0,0.0,135934431.0,46899947.0,64,0x7ff49fbe8e80,0,3961443,2744,2744,0,4489618,2704,2704,0,3115848,2654,2654,0,3146938,2698,2698,0,4138197,2686,2686,0,4247607,2738,2738,0,3710379,2650,2650,0,4822202,2695,2695,0,3820446,2712,2712,0,3827831,2676,2676,0,4614029,2686,2686,0,4807172,2736,2736,0,4549838,2732,2732,0,3669443,2680,2680,0,4951578,2686,2686,0,4021424,2688,2688,0,4755595,2720,2720,0,4787032,2728,2728,0,3604344,2696,2696,0,3753749,2705,2705,0,4242810,2719,2719,0,3780553,2728,2728,0,3478934,2664,2664,0,2890917,2698,2698,0,4687688,2688,2688,0,4751625,2700,2700,0,3907085,2700,2700,0,3027891,2696,2696,0,4679627,2736,2736,0,3835709,2697,2697,0,3774256,2692,2692,0,3082499,2684,2684,194153002423297,194153002442177 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_1,obj_1,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_2,obj_2,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_3,obj_3,TCC_EA_ATOMIC_LEVEL_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_7,obj_7,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_8,obj_8,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_9,obj_9,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_12,obj_12,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_13,obj_13,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_14,obj_14,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_15,obj_15,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_16,obj_16,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f93318b0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47948,0,131635.0,131072.0,0.0,131104.0,64,0x7f6520174ec0,131072.0,131072.0,0.0,2468054.0,0.0,0.0,130637271.0,62580356.0,64,0x7fc1bb190ec0,0,3758427,4096,4096,0,3798111,4096,4096,0,4569791,4096,4096,0,3045375,4096,4096,0,3438696,4096,4096,0,3286226,4096,4096,0,3554084,4096,4096,0,3187589,4096,4096,0,3387454,4096,4096,0,4526085,4096,4096,0,3850674,4096,4096,0,3458361,4096,4096,0,3896139,4096,4096,0,3263039,4096,4096,0,3306787,4096,4096,0,3260016,4096,4096,0,3852118,4096,4096,0,3826088,4096,4096,0,4085757,4096,4096,0,3440700,4096,4096,0,3292840,4096,4096,0,3815494,4096,4096,0,3363564,4096,4096,0,3503837,4096,4096,0,3452033,4096,4096,0,3889077,4096,4096,0,3527859,4096,4096,0,3408758,4096,4096,0,3899456,4096,4096,0,3503895,4096,4096,0,3478538,4096,4096,0,3321259,4096,4096,64,0x7f6563d10ec0,0.0,64,0x7fde430ccec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8364,4268,8364,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fa3cf54cec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131340.0,0.0,528.0,131339.0,64,0x7ff0ae264ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9057c04ec0,32768,0,0,0,16384,16384,393216,20804030,960.0,513911.0,0.0,524288.0,1263996.0,32768.0,0,0,0,17962,131072.0,131072.0,0.0,131072.0,64,0x7f373b5a4ec0,3855,0,0,2007893,3979,0,0,2023914,1755,0,0,1773107,3831,0,0,2012186,2683,0,0,1891672,4489,0,0,2119634,2844,0,0,1945034,3629,0,0,2080366,2038,0,0,1846181,1363,0,0,1749187,1752,0,0,1747710,3025,0,0,1917495,2432,0,0,1936303,2466,0,0,1913736,1139,0,0,1733539,5649,0,0,2151887,3499,0,0,2084270,2308,0,0,1902496,821,0,0,1659360,4758,0,0,2009154,3225,0,0,1952555,5489,0,0,2206465,1243,0,0,1755009,6192,0,0,2143419,3103,0,0,1955316,530,0,0,1586926,2652,0,0,1928228,4650,0,0,1984375,5839,0,0,2171175,7417,0,0,2230052,1046,0,0,1740672,3823,0,0,1990735,64,0x7f28320acec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87142.0,43930.0,131112.0,0.0,64,0x7f69c262cec0,395472,244656,3505482,16384,25459008,144,48,0,49433,49433,4022066.0,3134245.0,5432.0,1026242.0,2398244.0,0.0,3125141.0,2816478.0,393759,254586,49433,0,49433,0,1581856.0,1002365.0,0.0,0.0,64,0x7f548f7c0ec0,0,0,192,0,65536,64526,48,1339,31967,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48104,1893,0,48.0,264.0,0.0,262288.0,64,0x7f66423c8ec0,2064881,360448,163840,0,0,180224,114688,0,71296906.0,198153096.0,77211339.0,131072.0,0.0,591550.0,0,0,26664,74413.0,0.0,0.0,74413.0,64,0x7faf88820ec0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,64,0x7fe31868cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,30688.0,121747.0,64,0x7f991e830ec0,255719,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14494,30878,10106,588,0,47818,262603.0,0.0,188.0,262415.0,64,0x7f270f378ec0,4096,0,7729,0,4096,0,1029,0,4264,0,1568,0,4099,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,154,0,4096,0,0,0,4096,0,25,0,4096,0,224,0,4144,0,1035,0,4096,0,923,0,4096,0,455,0,4096,0,0,0,4096,0,23,0,4096,0,0,0,4096,0,3447,0,4096,0,528,0,4096,0,1204,0,4096,0,1733,0,4096,0,321,0,4096,0,23,0,4096,0,0,0,4096,0,0,0,4096,0,58,0,4096,0,2,0,4096,0,493,0,4096,0,0,0,4096,0,113,0,4096,0,0,0,4096,0,1529,0,1410078545959517,1410078545984317 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f93318b0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,4554,39422,0,131523.0,131072.0,0.0,86735.0,64,0x7f6520174ec0,131072.0,131072.0,0.0,2660010.0,0.0,0.0,108882266.0,47254132.0,64,0x7fc1bb190ec0,0,4064646,2746,2746,0,3931319,2716,2716,0,4125411,2686,2686,0,3850328,2698,2698,0,4147834,2706,2706,0,3512720,2728,2728,0,4809833,2687,2687,0,3625161,2714,2714,0,3751964,2698,2698,0,4802407,2700,2700,0,4299926,2722,2722,0,3576014,2712,2712,0,3610314,2730,2730,0,3749225,2688,2688,0,4119915,2706,2706,0,3674591,2693,2693,0,3771532,2718,2718,0,4001994,2710,2710,0,4144650,2708,2708,0,3775138,2719,2719,0,3644697,2710,2710,0,4319346,2721,2721,0,3890017,2693,2693,0,3385091,2706,2706,0,3488719,2694,2694,0,4096297,2684,2684,0,3903700,2720,2720,0,3253383,2718,2718,0,3869719,2700,2700,0,4090585,2696,2696,0,3336174,2718,2718,0,3632097,2728,2728,64,0x7f6563d10ec0,0.0,64,0x7fde430ccec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8361,4265,8361,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,64,0x7fa3cf54cec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131341.0,0.0,536.0,131340.0,64,0x7ff0ae264ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9057c04ec0,32768,0,0,0,16384,16384,393216,21896604,960.0,513935.0,0.0,524288.0,1236842.0,32768.0,0,0,0,13958,86546.0,86546.0,0.0,86546.0,64,0x7f373b5a4ec0,1360,0,0,1431224,1708,0,0,1366661,2032,0,0,1461214,3173,0,0,1580427,1508,0,0,1464623,19,0,0,1054571,6702,0,0,1921320,5155,0,0,1737278,2614,0,0,1600594,1054,0,0,1240503,1564,0,0,1509586,1580,0,0,1402223,327,0,0,1216362,450,0,0,1212336,3458,0,0,1626656,809,0,0,1322071,1314,0,0,1416180,206,0,0,1196756,4424,0,0,1770993,1345,0,0,1361095,696,0,0,1272579,435,0,0,1238605,7429,0,0,1921935,1621,0,0,1365859,2311,0,0,1486692,595,0,0,1341662,4653,0,0,1738557,1044,0,0,1352899,852,0,0,1337287,1078,0,0,1254085,2734,0,0,1609936,274,0,0,1315191,64,0x7f28320acec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86959.0,0.0,131112.0,0.0,64,0x7f69c262cec0,346256,235189,3376483,16384,24351024,0,48,0,43281,43281,3817346.0,3098319.0,6801.0,892874.0,2381845.0,0.0,3088893.0,2777860.0,346248,244971,43281,0,43281,0,1384992.0,842437.0,0.0,0.0,64,0x7f548f7c0ec0,0,0,48,0,65536,65536,0,0,30785,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,456,42783,1676,0,48.0,269.0,0.0,262144.0,64,0x7f66423c8ec0,3985618,360448,163840,0,0,180224,114688,0,62336305.0,168537726.0,81296325.0,131072.0,0.0,784607.0,0,0,29663,40804.0,0.0,0.0,40804.0,64,0x7faf88820ec0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,64,0x7fe31868cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,41962.0,134156.0,64,0x7f991e830ec0,242669,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11393,27777,18697,6790,0,40589,262477.0,0.0,47.0,262430.0,64,0x7f270f378ec0,4096,0,1100,0,4096,0,3546,0,4264,0,1858,0,4096,0,2950,0,4097,0,2387,0,4097,0,352,0,4096,0,150,0,4096,0,2332,0,4096,0,3709,0,4096,0,2593,0,4096,0,5862,0,4144,0,1274,0,4096,0,1158,0,4096,0,1192,0,4096,0,1049,0,4098,0,1135,0,4096,0,3587,0,4096,0,4468,0,4096,0,2524,0,4096,0,437,0,4096,0,5730,0,4096,0,114,0,4096,0,575,0,4096,0,927,0,4096,0,3436,0,4096,0,3221,0,4096,0,2127,0,4097,0,247,0,4096,0,938,0,4096,0,2554,0,4096,0,107,0,4096,0,257,0,1410078546083997,1410078546102877 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f93318b0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2672,39629,0,131492.0,131072.0,0.0,86617.0,64,0x7f6520174ec0,131072.0,131072.0,0.0,2501838.0,0.0,0.0,124384310.0,48863827.0,64,0x7fc1bb190ec0,0,3655566,2746,2746,0,3657420,2727,2727,0,3319939,2676,2676,0,3582788,2708,2708,0,3611923,2712,2712,0,3665391,2715,2715,0,3746135,2689,2689,0,3579885,2692,2692,0,3625934,2718,2718,0,4673020,2708,2708,0,3543463,2696,2696,0,3545898,2714,2714,0,3563971,2760,2760,0,4312808,2699,2699,0,4192389,2688,2688,0,3894620,2726,2726,0,3807788,2690,2690,0,4022399,2691,2691,0,4079021,2702,2702,0,3500957,2714,2714,0,3772870,2708,2708,0,3637429,2748,2748,0,3827738,2681,2681,0,3753057,2684,2684,0,3851612,2697,2697,0,3620784,2700,2700,0,3476930,2712,2712,0,3717357,2706,2706,0,3519234,2740,2740,0,4062782,2745,2745,0,3421259,2701,2701,0,3138888,2721,2721,64,0x7f6563d10ec0,0.0,64,0x7fde430ccec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8371,4275,8371,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,64,0x7fa3cf54cec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131341.0,0.0,536.0,131340.0,64,0x7ff0ae264ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9057c04ec0,32768,0,0,0,16384,16384,393216,22259661,960.0,513939.0,0.0,524288.0,1244746.0,32768.0,0,0,0,13813,86724.0,86724.0,0.0,86724.0,64,0x7f373b5a4ec0,2109,0,0,1501443,2679,0,0,1434691,1021,0,0,1300124,1580,0,0,1362653,972,0,0,1308853,1323,0,0,1501215,3007,0,0,1525920,2335,0,0,1490745,669,0,0,1359012,3335,0,0,1651853,665,0,0,1215463,1791,0,0,1451151,1608,0,0,1387095,933,0,0,1327929,1741,0,0,1418966,892,0,0,1270453,1566,0,0,1406452,0,0,0,1197089,3239,0,0,1522909,1717,0,0,1332195,2516,0,0,1575566,1863,0,0,1476634,1755,0,0,1402685,2568,0,0,1613100,2684,0,0,1501581,3779,0,0,1619111,1687,0,0,1377061,3872,0,0,1614542,5418,0,0,1820403,1356,0,0,1395742,3544,0,0,1596771,1628,0,0,1419759,64,0x7f28320acec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86797.0,0.0,131112.0,0.0,64,0x7f69c262cec0,346192,231394,3300937,16384,24251006,0,48,0,43273,43273,3760208.0,3025837.0,7589.0,798252.0,2357193.0,0.0,3016291.0,2705405.0,346184,240863,43273,0,43273,0,1384736.0,825227.0,0.0,0.0,64,0x7f548f7c0ec0,0,0,48,0,65536,65536,0,0,30772,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42069,1684,0,48.0,269.0,0.0,262144.0,64,0x7f66423c8ec0,1858118,360448,163840,0,0,180224,114688,0,70715791.0,202374168.0,78271154.0,131072.0,0.0,585407.0,0,0,25357,63792.0,0.0,0.0,63792.0,64,0x7faf88820ec0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,64,0x7fe31868cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,34781.0,128833.0,64,0x7f991e830ec0,196245,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14229,30613,8612,2551,0,41725,262462.0,0.0,47.0,262415.0,64,0x7f270f378ec0,4096,0,540,0,4096,0,1258,0,4264,0,7048,0,4096,0,0,0,4097,0,337,0,4097,0,3201,0,4096,0,743,0,4096,0,14,0,4096,0,62,0,4096,0,2031,0,4096,0,1842,0,4144,0,2247,0,4096,0,1764,0,4096,0,356,0,4096,0,1586,0,4098,0,0,0,4096,0,101,0,4096,0,1923,0,4096,0,1523,0,4096,0,728,0,4096,0,577,0,4096,0,3307,0,4096,0,1188,0,4096,0,24,0,4096,0,3986,0,4096,0,2067,0,4096,0,1024,0,4097,0,0,0,4096,0,0,0,4096,0,32,0,4096,0,589,0,4096,0,1371,0,1410078546122717,1410078546141597 diff --git a/tests/workloads/path/MI100/sysinfo.csv b/tests/workloads/path/MI100/sysinfo.csv index 6e18d4031e..4278075525 100644 --- a/tests/workloads/path/MI100/sysinfo.csv +++ b/tests/workloads/path/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:06:45 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:52:12 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/path/MI100/timestamps.csv b/tests/workloads/path/MI100/timestamps.csv index 898db3affd..352aa23aa1 100644 --- a/tests/workloads/path/MI100/timestamps.csv +++ b/tests/workloads/path/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,134351,134351,1048576,256,0,0,8,8,16,64,0x0,0x7f7e012a4e80,194153002162090,194153002188417,194153002212257,194153002225981 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,134351,134351,1048576,256,0,0,8,8,16,64,0x0,0x7f7e012a4e80,194153002224879,194153002382497,194153002401697,194153002402936 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,134351,134351,1048576,256,0,0,8,8,16,64,0x0,0x7f7e012a4e80,194153002414157,194153002423297,194153002442177,194153002443232 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078545933634,1410078545959517,1410078545984317,1410078545996272 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078545996933,1410078546083997,1410078546102877,1410078546104276 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078546114776,1410078546122717,1410078546141597,1410078546142898 diff --git a/tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv index 422410969a..d41441648f 100644 --- a/tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,282537,282537,1048576,256,0,0,8,0,16,64,0x0,0x7fe3cb2f4ec0,27474,27474,16384,65536,14001,1557960,198053593279677,198066321926096,198066321946896,198053609365457 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,282537,282537,1048576,256,0,0,8,0,16,64,0x0,0x7fe3cb2f4ec0,39998,39998,16384,65536,9140,1048648,198053609385856,198066321965776,198066321981616,198053609679742 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,282537,282537,1048576,256,0,0,8,0,16,64,0x0,0x7fe3cb2f4ec0,39794,39794,16384,65536,9293,1048652,198053609709659,198066322044816,198066322061136,198053609866545 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,27003,27003,16384,65536,13592,1540604,1411538900424691,1411551767635712,1411551767656192,1411538916711551 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,41252,41252,16384,65536,9433,1048652,1411538916734635,1411551767749472,1411551767765792,1411538916994887 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,40493,40493,16384,65536,9496,1048672,1411538917024403,1411551767786592,1411551767802112,1411538917176591 diff --git a/tests/workloads/path/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/path/MI200/SQ_INST_LEVEL_LDS.csv index 3eadafbb6a..a5fea0bc5d 100644 --- a/tests/workloads/path/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/path/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,282723,282723,1048576,256,0,0,8,0,16,64,0x0,0x7f0d7e5c0ec0,0,0,0,198054073410791,198066321926096,198066321946896,198054089119128 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,282723,282723,1048576,256,0,0,8,0,16,64,0x0,0x7f0d7e5c0ec0,0,0,0,198054089144676,198066321965776,198066321981616,198054089454743 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,282723,282723,1048576,256,0,0,8,0,16,64,0x0,0x7f0d7e5c0ec0,0,0,0,198054089482736,198066322044816,198066322061136,198054089647788 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539386407497,1411551767635712,1411551767656192,1411539402298088 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539402313307,1411551767749472,1411551767765792,1411539402615388 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539402642058,1411551767786592,1411551767802112,1411539402793835 diff --git a/tests/workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv index 9b62e1d019..09b6207ef4 100644 --- a/tests/workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,282921,282921,1048576,256,0,0,8,0,16,64,0x0,0x7fa9cdc04ec0,65536,175020,19680912,198054547411278,198066321926096,198066321946896,198054563493783 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,282921,282921,1048576,256,0,0,8,0,16,64,0x0,0x7fa9cdc04ec0,65536,244314,27249496,198054563514422,198066321965776,198066321981616,198054563781747 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,282921,282921,1048576,256,0,0,8,0,16,64,0x0,0x7fa9cdc04ec0,65536,244834,27367848,198054563808789,198066322044816,198066322061136,198054563962109 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,172104,19399360,1411539868015720,1411551767635712,1411551767656192,1411539884298563 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,225136,25260328,1411539884315856,1411551767749472,1411551767765792,1411539884617747 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,237466,26615144,1411539884643485,1411551767786592,1411551767802112,1411539884796224 diff --git a/tests/workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv index 5bb643a561..d7a0583ce1 100644 --- a/tests/workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,283105,283105,1048576,256,0,0,8,0,16,64,0x0,0x7f68d7030ec0,32768,291935,32692868,198055031064325,198066321926096,198066321946896,198055046931984 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,283105,283105,1048576,256,0,0,8,0,16,64,0x0,0x7f68d7030ec0,32768,595936,66739628,198055046949266,198066321965776,198066321981616,198055047260485 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,283105,283105,1048576,256,0,0,8,0,16,64,0x0,0x7f68d7030ec0,32768,578290,64773016,198055047286755,198066322044816,198066322061136,198055047446537 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,296920,33259784,1411540349957093,1411551767635712,1411551767656192,1411540365771640 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,589718,66068516,1411540365791388,1411551767749472,1411551767765792,1411540366061018 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,602871,67508252,1411540366087468,1411551767786592,1411551767802112,1411540366250446 diff --git a/tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv index 96bac7be77..9878ed357f 100644 --- a/tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) ",2,0,0,283306,283306,1048576,256,0,0,8,0,16,64,0x0,0x7f054fe6cec0,28117,28117,11276,224944,16384,11085318,130224,0,44837220,198055510373355,198066321926096,198066321946896,198055526236264 -1,"vecCopy(double*, double*, double*, int, int) ",2,0,2,283306,283306,1048576,256,0,0,8,0,16,64,0x0,0x7f054fe6cec0,41558,41558,14306,332472,16384,19035692,220378,0,76620008,198055526262163,198066321965776,198066321981616,198055526579233 -2,"vecCopy(double*, double*, double*, int, int) ",2,0,4,283306,283306,1048576,256,0,0,8,0,16,64,0x0,0x7f054fe6cec0,41505,41505,14250,332048,16384,19350813,221811,0,77885816,198055526614049,198066322044816,198066322061136,198055526777638 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,27964,27964,11091,223720,16384,11075620,130670,0,44799316,1411540838121846,1411551767635712,1411551767656192,1411540853905555 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,40878,40878,12739,327032,16384,19248292,223753,0,77475332,1411540853935701,1411551767749472,1411551767765792,1411540854159996 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,40812,40812,13091,326504,16384,19800227,224876,0,79703012,1411540854195663,1411551767786592,1411551767802112,1411540854346158 diff --git a/tests/workloads/path/MI200/log.txt b/tests/workloads/path/MI200/log.txt new file mode 100644 index 0000000000..598b465e56 --- /dev/null +++ b/tests/workloads/path/MI200/log.txt @@ -0,0 +1,739 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/path/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_161646' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161646_4105900' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161646_4105900/input0_results_240321_161646' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161646_4105900/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161646_4105900/input0_results_240321_161646 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_161647' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161647_4106093' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161647_4106093/input0_results_240321_161647' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161647_4106093/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161647_4106093/input0_results_240321_161647 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_161647' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161647_4106276' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161647_4106276/input0_results_240321_161647' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161647_4106276/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161647_4106276/input0_results_240321_161647 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_161648' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161648_4106468' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161648_4106468/input0_results_240321_161648' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161648_4106468/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161648_4106468/input0_results_240321_161648 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_161648' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161648_4106670' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161648_4106670/input0_results_240321_161648' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161648_4106670/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161648_4106670/input0_results_240321_161648 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_161649' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161649_4106855' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161649_4106855/input0_results_240321_161649' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161649_4106855/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161649_4106855/input0_results_240321_161649 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_161649' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161649_4107038' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161649_4107038/input0_results_240321_161649' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161649_4107038/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161649_4107038/input0_results_240321_161649 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_161650' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161650_4107221' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161650_4107221/input0_results_240321_161650' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161650_4107221/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161650_4107221/input0_results_240321_161650 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_161650' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161650_4107404' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161650_4107404/input0_results_240321_161650' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161650_4107404/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161650_4107404/input0_results_240321_161650 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_161651' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161651_4107588' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161651_4107588/input0_results_240321_161651' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161651_4107588/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161651_4107588/input0_results_240321_161651 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_161651' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161651_4107786' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161651_4107786/input0_results_240321_161651' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161651_4107786/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161651_4107786/input0_results_240321_161651 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_161652' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161652_4107970' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161652_4107970/input0_results_240321_161652' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161652_4107970/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161652_4107970/input0_results_240321_161652 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_161652' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161652_4108161' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161652_4108161/input0_results_240321_161652' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161652_4108161/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161652_4108161/input0_results_240321_161652 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_161653' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161653_4108344' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161653_4108344/input0_results_240321_161653' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161653_4108344/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161653_4108344/input0_results_240321_161653 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_161654' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161654_4108547' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161654_4108547/input0_results_240321_161654' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161654_4108547/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161654_4108547/input0_results_240321_161654 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_161655' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161655_4108730' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161655_4108730/input0_results_240321_161655' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161655_4108730/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161655_4108730/input0_results_240321_161655 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_161655' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161655_4108920' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161655_4108920/input0_results_240321_161655' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161655_4108920/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161655_4108920/input0_results_240321_161655 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_161656' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161656_4109119' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161656_4109119/input0_results_240321_161656' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161656_4109119/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161656_4109119/input0_results_240321_161656 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_161656' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161656_4109302' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161656_4109302/input0_results_240321_161656' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161656_4109302/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161656_4109302/input0_results_240321_161656 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_161657' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161657_4109485' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161657_4109485/input0_results_240321_161657' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161657_4109485/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161657_4109485/input0_results_240321_161657 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_161657' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161657_4109668' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161657_4109668/input0_results_240321_161657' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161657_4109668/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161657_4109668/input0_results_240321_161657 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_161658' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161658_4109851' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161658_4109851/input0_results_240321_161658' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161658_4109851/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161658_4109851/input0_results_240321_161658 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_161658' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161658_4110053' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161658_4110053/input0_results_240321_161658' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161658_4110053/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161658_4110053/input0_results_240321_161658 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_161659' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161659_4110244' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161659_4110244/input0_results_240321_161659' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161659_4110244/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161659_4110244/input0_results_240321_161659 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_161659' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161659_4110431' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161659_4110431/input0_results_240321_161659' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161659_4110431/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161659_4110431/input0_results_240321_161659 + |-> [rocprof] File 'tests/workloads/path/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/path/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/path/MI200/pmc_dispatch_info.csv b/tests/workloads/path/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/path/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/path/MI200/pmc_perf.csv b/tests/workloads/path/MI200/pmc_perf.csv index 2884135eaf..1c1f02b367 100644 --- a/tests/workloads/path/MI200/pmc_perf.csv +++ b/tests/workloads/path/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_3,obj_3,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_4,obj_4,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_5,obj_5,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_8,obj_8,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_9,obj_9,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_10,obj_10,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_11,obj_11,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_12,obj_12,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_13,obj_13,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_14,obj_14,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_15,obj_15,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_16,obj_16,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_17,obj_17,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_18,obj_18,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5586690ec0,0,0,0,1009613,0,0,0,1210421,0,0,0,1020607,0,0,0,1128348,0,0,0,1121396,0,0,0,1170810,0,0,0,1190615,0,0,0,1195998,0,0,0,1053274,0,0,0,1132469,0,0,0,1065292,0,0,0,1104783,0,0,0,1104256,0,0,0,1082836,0,0,0,1096052,0,0,0,1183851,0,0,0,1013346,0,0,0,1096776,0,0,0,1033298,70,0,0,1412694,0,0,0,1104457,0,0,0,1076884,0,0,0,1190548,0,0,0,1072945,0,0,0,1042655,0,0,0,1016368,0,0,0,1028047,0,0,0,1093274,120,0,0,1290753,0,0,0,1151143,0,0,0,1073576,34,0,0,1247284,64,0x7fc8dfd14ec0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,0,27776,0,0,64,0x7f66353a4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,12048,19512,7999,545,0,26110,204779.0,0.0,73698.0,131081.0,64,0x7fd132dccec0,0,393216,163840,0,0,0,0,0,18304,0.0,0.0,0.0,32768.0,0.0,0.0,384.0,32768.0,4096,16384,352,28867,2036,0,56.0,6.0,0.0,203954.0,64,0x7f7622100ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,34827.0,46079.0,19457.0,64,0x7fc24eab0ec0,114688,0,32768,32768,16384,16384,65536,49152,27900749.0,87525958.0,38815333.0,131072.0,0.0,195404.0,0,0,15055,483.0,131082.0,0.0,12.0,64,0x7f05f6cb4ec0,1223,115917,0,0,65536,63800,56,1680,64,0x7f7979944ec0,32768,32768,0,64,0x7f8b36f4cec0,0,0,0,224,0,65536,64208,56,64,0x7f7f8fd68ec0,0,1154934,4096,4096,0,1340147,4096,4096,0,1260032,4096,4096,0,1397661,4096,4096,0,1303303,4096,4096,0,1436622,4096,4096,0,1163591,4096,4096,0,1413520,4096,4096,0,1190092,4096,4096,0,1174336,4096,4096,0,1251898,4096,4096,0,1219411,4096,4096,0,1540832,4096,4096,0,1327608,4096,4096,0,1498472,4096,4096,0,1304506,4096,4096,0,1122818,4096,4096,0,1207949,4096,4096,0,1170089,4096,4096,0,1380481,4096,4096,0,1791325,4096,4096,0,1273765,4096,4096,0,1369542,4096,4096,0,1300406,4096,4096,0,1330419,4096,4096,0,1147903,4096,4096,0,1229230,4096,4096,0,1352574,4096,4096,0,1358736,4096,4096,0,1187941,4096,4096,0,1201096,4096,4096,0,1500028,4096,4096,64,0x7f86da894ec0,11336020,9895548,1096408,344064,1695425,0,0,163840,832.0,515136.0,0.0,524288.0,250243.0,32768.0,554799,0,0,11197,131072.0,131072.0,0.0,131072.0,64,0x7fdcd059cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,9888,0,814,27667,0,73331.0,131072.0,0.0,65568.0,64,0x7f77830c8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f293e384ec0,2309,4096,2309,6405,2323,4096,2323,6419,2248,4096,2248,6344,2332,4096,2332,6428,2254,4096,2254,6350,2325,4096,2325,6421,2256,4096,2256,6352,2243,4096,2243,6339,2246,4096,2246,6342,2310,4096,2310,6406,2327,4096,2327,6423,2248,4097,2249,6345,2342,4096,2342,6438,2254,4096,2254,6350,2329,4096,2329,6425,2260,4096,2260,6356,2264,4096,2264,6360,2337,4097,2338,6434,2293,4096,2293,6389,2325,4096,2325,6421,2270,4096,2270,6366,2292,4097,2293,6389,2294,4097,2295,6391,2469,4098,2471,6567,2305,4096,2305,6401,2263,4096,2263,6359,2284,4096,2284,6380,2293,4096,2293,6389,2325,4096,2325,6421,2271,4096,2271,6367,2301,4096,2301,6397,2295,4096,2295,6391,64,0x7ffbbdbe4ec0,6350,0,4096,6378,0,4096,6365,0,4096,6427,0,4096,6320,0,4096,6342,0,4096,6360,0,4096,6388,0,4096,6390,0,4096,6351,0,4096,6379,0,4096,6365,0,4096,6425,0,4096,6321,0,4096,6346,0,4096,6362,0,4096,6374,0,4096,6406,0,4096,6347,0,4096,6372,0,4096,6379,0,4096,6411,0,4096,6358,0,4096,6505,0,4096,6342,0,4096,6377,0,4096,6408,0,4096,6349,0,4096,6376,0,4096,6381,0,4096,6412,0,4096,6364,0,4096,64,0x7ff50cc30ec0,4096,0,0,0,4096,0,106,0,4096,0,0,0,4096,0,4,0,4096,0,0,0,4096,0,0,0,4096,0,31,0,4096,0,419,0,4098,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,25,0,4097,0,54,0,4096,0,0,0,4097,0,9,0,4096,0,17,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,208,0,4096,0,15,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,1,0,4096,0,0,0,4096,0,0,0,4096,0,6,0,4102,0,34,0,64,0x7ffb644dcec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,937283.0,64,0x7f6ddd954ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39353520.0,35049108.0,0.0,64,0x7fd4bab78ec0,234688,130013,16384,0,16384,16384,32768,49152,29335,29335,1967880.0,1359889.0,3535.0,162265.0,1050686.0,0.0,1352059.0,1055289.0,232977,138138,29335,0,29335,0,938720.0,491751.0,0.0,0.0,198066321926096,198066321946896 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5586690ec0,0,0,0,1879799,193,0,0,2059321,0,0,0,1667888,236,0,0,1836956,406,0,0,2153597,158,0,0,2269512,0,0,0,1611624,0,0,0,1841775,0,0,0,1781362,0,0,0,1824172,593,0,0,2533833,0,0,0,1778493,170,0,0,1581261,36,0,0,1801445,115,0,0,1983703,0,0,0,1563556,0,0,0,2020646,0,0,0,1656319,0,0,0,1383819,0,0,0,2118498,126,0,0,1970622,0,0,0,1714280,0,0,0,1777168,0,0,0,2029443,0,0,0,1740216,0,0,0,1824736,0,0,0,1804029,0,0,0,1783379,91,0,0,2382721,0,0,0,1588253,179,0,0,1963037,0,0,0,1973011,64,0x7fc8dfd14ec0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,0,40924,0,0,64,0x7f66353a4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,26333,27320,8554,550,0,34758,200168.0,0.0,69093.0,131075.0,64,0x7fd132dccec0,0,393216,163840,0,0,0,0,0,30625,0.0,0.0,0.0,32768.0,0.0,0.0,237.0,32768.0,4096,16384,302,42260,1974,0,56.0,11.0,0.0,200675.0,64,0x7f7622100ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,110600.0,45558.0,0.0,64,0x7fc24eab0ec0,114688,0,32768,32768,16384,16384,65536,49152,57376816.0,199314100.0,45113202.0,131072.0,0.0,539568.0,0,0,25183,1990.0,131085.0,0.0,24.0,64,0x7f05f6cb4ec0,0,186876,0,0,65536,63800,56,1680,64,0x7f7979944ec0,32768,32768,0,64,0x7f8b36f4cec0,0,0,0,56,0,65536,65536,0,64,0x7f7f8fd68ec0,0,4122076,2832,2832,0,3346983,2872,2872,0,3715584,2856,2856,0,3820385,2872,2872,0,3413891,2861,2861,0,5284638,2824,2824,0,2980631,2852,2852,0,3936768,2824,2824,0,3533388,2820,2820,0,3553601,2832,2832,0,3803751,2872,2872,0,3580135,2858,2858,0,3894600,2876,2876,0,3391898,2860,2860,0,4392189,2824,2824,0,3780819,2852,2852,0,3646066,2806,2806,0,3727763,2820,2820,0,3782899,2860,2860,0,3681675,2868,2868,0,3942662,2840,2840,0,4340688,2880,2880,0,3691052,2818,2818,0,4473114,2826,2826,0,3464598,2828,2828,0,3139625,2796,2796,0,3652578,2808,2808,0,3844260,2860,2860,0,3137652,2862,2862,0,3965136,2836,2836,0,4628713,2876,2876,0,3653513,2820,2820,64,0x7f86da894ec0,20407512,18434719,1628729,344064,2941662,0,0,163840,832.0,515136.0,0.0,524288.0,569230.0,32768.0,1120885,0,0,13514,91302.0,91302.0,0.0,91302.0,64,0x7fdcd059cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21290,0,3009,39056,0,69699.0,131072.0,0.0,45755.0,64,0x7f77830c8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f293e384ec0,2162,4096,2162,6258,2157,4096,2157,6253,2177,4096,2177,6273,2193,4098,2195,6291,2169,4096,2169,6265,2165,4097,2166,6262,2171,4096,2171,6267,2174,4096,2174,6270,2175,4096,2175,6271,2162,4096,2162,6258,2160,4096,2160,6256,2178,4097,2179,6275,2199,4096,2199,6295,2169,4096,2169,6265,2172,4096,2172,6268,2170,4096,2170,6266,2173,4096,2173,6269,2257,4097,2258,6354,2179,4096,2179,6275,2165,4096,2165,6261,2160,4097,2161,6257,2163,4097,2164,6260,2164,4097,2165,6261,2202,4096,2202,6298,2210,4096,2210,6306,2174,4096,2174,6270,2206,4096,2206,6302,2182,4096,2182,6278,2170,4096,2170,6266,2162,4096,2162,6258,2164,4096,2164,6260,2164,4096,2164,6260,64,0x7ffbbdbe4ec0,6278,0,4096,6275,0,4096,6300,0,4096,6270,0,4096,6273,0,4096,6275,0,4096,6249,0,4096,6298,0,4096,6300,0,4096,6281,0,4096,6280,0,4096,6307,0,4096,6268,0,4096,6272,0,4096,6278,0,4096,6250,0,4096,6266,0,4096,6246,0,4096,6295,0,4096,6301,0,4096,6266,0,4096,6284,0,4096,6249,0,4096,6281,0,4096,6279,0,4096,6271,0,4096,6249,0,4096,6295,0,4096,6299,0,4096,6267,0,4096,6284,0,4096,6250,0,4096,64,0x7ff50cc30ec0,4098,0,371,0,4096,0,79,0,4096,0,302,0,4096,0,291,0,4096,0,84,0,4096,0,299,0,4096,0,0,0,4096,0,432,0,4097,0,69,0,4096,0,116,0,4096,0,132,0,4096,0,2,0,4096,0,820,0,4097,0,0,0,4096,0,0,0,4097,0,40,0,4096,0,225,0,4096,0,1251,0,4098,0,354,0,4096,0,11,0,4096,0,2142,0,4096,0,11,0,4096,0,95,0,4096,0,1498,0,4096,0,337,0,4096,0,1,0,4096,0,123,0,4096,0,36,0,4096,0,10,0,4096,0,178,0,4097,0,0,0,4100,0,24,0,64,0x7ffb644dcec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2023963.0,64,0x7f6ddd954ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,118970920.0,56874571.0,0.0,64,0x7fd4bab78ec0,333384,229274,16384,0,16384,16384,32768,49152,41672,41672,3257957.0,2523106.0,3874.0,392885.0,1701516.0,0.0,2512487.0,2206848.0,333376,238727,41672,0,41672,0,1333504.0,792321.0,0.0,0.0,198066321965776,198066321981616 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f5586690ec0,0,0,0,1565799,159,0,0,1851390,0,0,0,1624876,0,0,0,1989193,0,0,0,2106924,0,0,0,1738605,0,0,0,1451545,36,0,0,1846101,20,0,0,1861366,0,0,0,1433783,266,0,0,1833004,278,0,0,1864721,0,0,0,1734065,0,0,0,1821516,0,0,0,1676158,0,0,0,1689892,0,0,0,1609089,0,0,0,2202284,10,0,0,1608959,0,0,0,2076188,0,0,0,1688492,400,0,0,2376883,316,0,0,2057724,0,0,0,1812743,0,0,0,1614915,0,0,0,1692468,0,0,0,1545768,0,0,0,1586132,0,0,0,2062759,0,0,0,1757420,0,0,0,1826147,0,0,0,1878706,64,0x7fc8dfd14ec0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,0,41184,0,0,64,0x7f66353a4ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,29923,27350,9629,2477,0,38229,200782.0,0.0,69699.0,131083.0,64,0x7fd132dccec0,0,393216,163840,0,0,0,0,0,31069,0.0,0.0,0.0,32768.0,0.0,0.0,245.0,32768.0,4096,16384,302,42010,1972,0,56.0,9.0,0.0,201123.0,64,0x7f7622100ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131084.0,81947.0,45589.0,0.0,64,0x7fc24eab0ec0,114688,0,32768,32768,16384,16384,65536,49152,58830502.0,198598781.0,52503940.0,131072.0,0.0,552263.0,0,0,26334,9941.0,131084.0,0.0,22.0,64,0x7f05f6cb4ec0,0,184329,0,0,65536,63800,56,1680,64,0x7f7979944ec0,32768,32768,0,64,0x7f8b36f4cec0,0,0,0,56,0,65536,65536,0,64,0x7f7f8fd68ec0,0,2859174,2824,2824,0,5922048,2868,2868,0,4038699,2848,2848,0,3464207,2846,2846,0,2762943,2916,2916,0,2984922,2872,2872,0,3340493,2858,2858,0,3517330,2824,2824,0,3965921,2824,2824,0,2767921,2828,2828,0,3016307,2864,2864,0,3692943,2846,2846,0,3193630,2844,2844,0,2881939,2916,2916,0,2944922,2872,2872,0,3064831,2864,2864,0,3663324,2772,2772,0,3501582,2848,2848,0,3303647,2840,2840,0,4194113,2880,2880,0,3289818,2816,2816,0,3527719,2836,2836,0,3103674,2844,2844,0,3433666,2852,2852,0,3328802,2852,2852,0,3410767,2772,2772,0,4371152,2850,2850,0,3061701,2840,2840,0,3350193,2880,2880,0,3781300,2816,2816,0,2689555,2832,2832,0,4523522,2842,2842,64,0x7f86da894ec0,19813603,18446486,1023053,344064,2829785,0,0,163840,832.0,515140.0,0.0,524288.0,659654.0,32768.0,1061136,0,0,12691,91020.0,91020.0,0.0,91020.0,64,0x7fdcd059cec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20017,0,2658,38559,0,69309.0,131072.0,0.0,45674.0,64,0x7f77830c8ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65554.0,0.0,0.0,0.0,64,0x7f293e384ec0,2153,4096,2153,6249,2192,4096,2192,6288,2189,4096,2189,6285,2207,4098,2209,6305,2161,4096,2161,6257,2163,4097,2164,6260,2187,4096,2187,6283,2191,4096,2191,6287,2195,4096,2195,6291,2154,4096,2154,6250,2195,4096,2195,6291,2188,4097,2189,6285,2214,4096,2214,6310,2165,4096,2165,6261,2161,4096,2161,6257,2180,4096,2180,6276,2209,4096,2209,6305,2222,4097,2223,6319,2155,4096,2155,6251,2167,4096,2167,6263,2173,4097,2174,6270,2208,4097,2209,6305,2174,4097,2175,6271,2176,4096,2176,6272,2179,4096,2179,6275,2207,4096,2207,6303,2173,4096,2173,6269,2161,4096,2161,6257,2171,4096,2171,6267,2175,4096,2175,6271,2208,4096,2208,6304,2176,4096,2176,6272,64,0x7ffbbdbe4ec0,6259,0,4096,6256,0,4096,6230,0,4096,6257,0,4096,6256,0,4096,6268,0,4096,6240,0,4096,6258,0,4096,6258,0,4096,6259,0,4096,6264,0,4096,6229,0,4096,6255,0,4096,6259,0,4096,6267,0,4096,6247,0,4096,6233,0,4096,6240,0,4096,6272,0,4096,6274,0,4096,6236,0,4096,6266,0,4096,6255,0,4096,6254,0,4096,6253,0,4096,6235,0,4096,6242,0,4096,6272,0,4096,6274,0,4096,6236,0,4096,6261,0,4096,6257,0,4096,64,0x7ff50cc30ec0,4098,0,182,0,4096,0,566,0,4096,0,605,0,4096,0,217,0,4096,0,947,0,4096,0,546,0,4096,0,0,0,4096,0,532,0,4097,0,0,0,4096,0,149,0,4096,0,32,0,4096,0,0,0,4096,0,44,0,4097,0,1028,0,4096,0,605,0,4097,0,27,0,4096,0,238,0,4096,0,356,0,4098,0,1223,0,4096,0,804,0,4096,0,384,0,4096,0,256,0,4096,0,1958,0,4096,0,1438,0,4096,0,441,0,4096,0,21,0,4096,0,0,0,4096,0,0,0,4096,0,332,0,4096,0,194,0,4097,0,12,0,4101,0,329,0,64,0x7ffb644dcec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2063337.0,64,0x7f6ddd954ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,115536914.0,57383341.0,0.0,64,0x7fd4bab78ec0,328120,219675,16384,0,16384,16384,32768,49152,41014,41014,3132692.0,2417506.0,5270.0,340382.0,1662652.0,0.0,2405700.0,2096975.0,328112,228813,41014,0,41014,0,1312448.0,775461.0,0.0,0.0,198066322044816,198066322061136 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_8,obj_8,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_11,obj_11,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_12,obj_12,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_13,obj_13,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_14,obj_14,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_15,obj_15,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_16,obj_16,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_17,obj_17,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_18,obj_18,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f719d074ec0,0,1280294,4096,4096,0,1016298,4096,4096,0,1173736,4096,4096,0,1331612,4096,4096,0,1104334,4096,4096,0,1203531,4096,4096,0,1008753,4096,4096,0,1292385,4096,4096,0,1190225,4096,4096,0,1227828,4096,4096,0,1131202,4096,4096,0,1203672,4096,4096,0,1138456,4096,4096,0,1183327,4096,4096,0,1394894,4096,4096,0,1277117,4096,4096,0,1253645,4096,4096,0,1265595,4096,4096,0,1071387,4096,4096,0,1761815,4096,4096,0,1356100,4096,4096,0,1511464,4096,4096,0,1122717,4096,4096,0,1268678,4096,4096,0,1126448,4096,4096,0,1062773,4096,4096,0,1041707,4096,4096,0,1233636,4096,4096,0,1492365,4096,4096,0,1237295,4096,4096,0,1420029,4096,4096,0,1217238,4096,4096,64,0x7f5871864ec0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,64,0x7f842c814ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10074,0,816,27715,0,73251.0,131072.0,0.0,65568.0,64,0x7f64e75d8ec0,1276,114416,0,0,65536,63800,56,1680,64,0x7f01f2d00ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39527436.0,35354785.0,0.0,64,0x7f6ecb88cec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,946191.0,64,0x7fc1d67f8ec0,4096,0,0,0,4096,0,129,0,4096,0,0,0,4096,0,147,0,4098,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,355,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,207,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7feb1c338ec0,2253,4099,2256,6352,2274,4096,2274,6370,2292,4096,2292,6388,2317,4096,2317,6413,2232,4096,2232,6328,2266,4096,2266,6362,2275,4096,2275,6371,2286,4096,2286,6382,2287,4096,2287,6383,2249,4096,2249,6345,2279,4096,2279,6375,2295,4096,2295,6391,2315,4096,2315,6411,2238,4096,2238,6334,2270,4096,2270,6366,2277,4096,2277,6373,2263,4096,2263,6359,2285,4096,2285,6381,2196,4098,2198,6294,2265,4096,2265,6361,2327,4097,2328,6424,2304,4096,2304,6400,2280,4096,2280,6376,2435,4098,2437,6533,2270,4096,2270,6366,2262,4096,2262,6358,2286,4096,2286,6382,2204,4096,2204,6300,2266,4096,2266,6362,2270,4096,2270,6366,2308,4096,2308,6404,2280,4096,2280,6376,64,0x7f0c851d0ec0,114688,0,32768,32768,16384,16384,65536,49152,27530242.0,84637584.0,37276646.0,131072.0,0.0,221242.0,0,0,15056,687.0,131086.0,0.0,20.0,64,0x7f2a26314ec0,0,0,0,1027825,74,0,0,1131751,0,0,0,1057543,0,0,0,1097462,0,0,0,1120029,55,0,0,1246251,0,0,0,1072885,0,0,0,1216521,0,0,0,1086561,0,0,0,1064423,0,0,0,1004711,0,0,0,1108645,0,0,0,1024831,0,0,0,1142102,0,0,0,1177389,22,0,0,1214656,0,0,0,1014701,0,0,0,1107805,0,0,0,1131637,0,0,0,1218413,0,0,0,1074604,0,0,0,1079222,60,0,0,1246159,0,0,0,1124479,0,0,0,1077444,0,0,0,1099417,145,0,0,1205829,41,0,0,1224358,0,0,0,1128386,0,0,0,1121967,0,0,0,1026123,69,0,0,1279568,64,0x7f980b700ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,33891.0,46047.0,19489.0,64,0x7f9e9e168ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13604,19334,8300,545,0,27266,204016.0,0.0,72935.0,131081.0,64,0x7f80e4520ec0,0,0,0,224,0,65536,64132,56,64,0x7fbd96bb4ec0,10620646,9564806,711776,344064,1594430,0,0,163840,832.0,515136.0,0.0,524288.0,277686.0,32768.0,458925,0,0,10761,131072.0,131072.0,0.0,131072.0,64,0x7fa1d1cb0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f9a5f924ec0,0,393216,163840,0,0,0,0,0,18078,0.0,0.0,0.0,32768.0,0.0,0.0,416.0,32768.0,4096,16384,352,28633,2150,0,56.0,6.0,0.0,204556.0,64,0x7ff854d0cec0,235728,131018,16384,0,16384,16384,32768,49152,29465,29465,1980828.0,1398275.0,3488.0,200607.0,1093079.0,0.0,1390463.0,1092398.0,234017,139150,29465,0,29465,0,942880.0,503329.0,0.0,0.0,64,0x7f6ca7ed0ec0,6374,0,4096,6393,0,4096,6379,0,4096,6357,0,4096,6399,0,4096,6418,0,4096,6391,0,4096,6360,0,4096,6365,0,4096,6370,0,4096,6395,0,4096,6379,0,4096,6353,0,4096,6399,0,4096,6420,0,4096,6395,0,4096,6363,0,4096,6356,0,4096,6403,0,4096,6401,0,4096,6386,0,4096,6350,0,4096,6397,0,4096,6587,0,4096,6419,0,4096,6365,0,4096,6360,0,4096,6400,0,4096,6404,0,4096,6387,0,4096,6353,0,4096,6401,0,4096,64,0x7f52604a0ec0,32768,32768,0,1411551767635712,1411551767656192 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f719d074ec0,0,3635368,2844,2844,0,3358869,2868,2868,0,4507800,2836,2836,0,4427655,2872,2872,0,3528702,2908,2908,0,4042385,2856,2856,0,3222489,2848,2848,0,4461160,2804,2804,0,3796362,2800,2800,0,3636483,2848,2848,0,4079095,2868,2868,0,4022898,2832,2832,0,3688662,2872,2872,0,3878807,2908,2908,0,3509431,2856,2856,0,3142952,2850,2850,0,3168535,2804,2804,0,3760235,2832,2832,0,3390587,2860,2860,0,4033999,2860,2860,0,3370259,2830,2830,0,3976984,2878,2878,0,3924020,2834,2834,0,4706973,2840,2840,0,4308399,2840,2840,0,3268498,2808,2808,0,3235184,2836,2836,0,3606911,2860,2860,0,4164092,2860,2860,0,3140833,2828,2828,0,3982134,2872,2872,0,4308084,2828,2828,64,0x7f5871864ec0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,64,0x7f842c814ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21863,0,2857,39450,0,70312.0,131072.0,0.0,45621.0,64,0x7f64e75d8ec0,0,184431,0,0,65536,63800,56,1680,64,0x7f01f2d00ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,116463987.0,59127715.0,0.0,64,0x7f6ecb88cec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,1983462.0,64,0x7fc1d67f8ec0,4096,0,456,0,4096,0,291,0,4096,0,2176,0,4096,0,727,0,4098,0,725,0,4097,0,1024,0,4096,0,71,0,4096,0,925,0,4096,0,0,0,4096,0,332,0,4096,0,729,0,4098,0,911,0,4096,0,185,0,4096,0,548,0,4096,0,1181,0,4096,0,155,0,4096,0,771,0,4096,0,828,0,4097,0,87,0,4098,0,541,0,4096,0,259,0,4096,0,295,0,4096,0,1833,0,4096,0,1038,0,4096,0,1152,0,4096,0,752,0,4097,0,372,0,4096,0,515,0,4096,0,66,0,4096,0,55,0,4096,0,21,0,4096,0,932,0,64,0x7feb1c338ec0,2167,4099,2170,6266,2163,4098,2165,6261,2166,4096,2166,6262,2131,4096,2131,6227,2155,4096,2155,6251,2126,4096,2126,6222,2198,4096,2198,6294,2205,4096,2205,6301,2205,4096,2205,6301,2167,4096,2167,6263,2167,4096,2167,6263,2170,4096,2170,6266,2131,4096,2131,6227,2157,4096,2157,6253,2128,4096,2128,6224,2200,4096,2200,6296,2197,4096,2197,6293,2192,4096,2192,6288,2191,4098,2193,6289,2165,4096,2165,6261,2224,4098,2226,6322,2159,4096,2159,6255,2142,4096,2142,6238,2143,4096,2143,6239,2141,4096,2141,6237,2196,4096,2196,6292,2191,4096,2191,6287,2194,4096,2194,6290,2163,4097,2164,6260,2166,4096,2166,6262,2156,4096,2156,6252,2148,4096,2148,6244,64,0x7f0c851d0ec0,114688,0,32768,32768,16384,16384,65536,49152,57344038.0,201189675.0,49212604.0,131072.0,0.0,469527.0,0,0,24792,3406.0,131086.0,0.0,26.0,64,0x7f2a26314ec0,0,0,0,1951688,0,0,0,2040120,1375,0,0,2515290,388,0,0,1924121,0,0,0,1959773,0,0,0,2144087,0,0,0,1601755,0,0,0,2227649,0,0,0,1515823,0,0,0,1712370,747,0,0,2281309,0,0,0,1754410,0,0,0,1631638,0,0,0,1959634,0,0,0,1945745,0,0,0,2101434,0,0,0,1485087,0,0,0,1663642,0,0,0,1597442,361,0,0,2320340,0,0,0,1479920,0,0,0,1769753,0,0,0,1643637,0,0,0,2016612,0,0,0,1590062,0,0,0,1353961,0,0,0,1457530,0,0,0,1782668,1,0,0,1962887,0,0,0,1575942,0,0,0,1874338,0,0,0,2035352,64,0x7f980b700ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,92644.0,45484.0,0.0,64,0x7f9e9e168ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32251,27914,9640,2417,0,39435,200735.0,0.0,69652.0,131083.0,64,0x7f80e4520ec0,0,0,0,56,0,65536,65536,0,64,0x7fbd96bb4ec0,19460332,18326981,789287,344064,2808219,0,0,163840,832.0,515136.0,0.0,524288.0,662213.0,32768.0,1020891,0,0,13732,91072.0,91072.0,0.0,91072.0,64,0x7fa1d1cb0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f9a5f924ec0,0,393216,163840,0,0,0,0,0,29953,0.0,0.0,0.0,32768.0,0.0,0.0,211.0,32768.0,4096,16384,302,41182,2074,0,56.0,11.0,0.0,200382.0,64,0x7ff854d0cec0,332936,217335,16384,0,16384,16384,32768,49152,41616,41616,3122366.0,2426905.0,4865.0,361077.0,1765505.0,0.0,2413768.0,2104530.0,332928,227334,41616,0,41616,0,1331712.0,770089.0,0.0,0.0,64,0x7f6ca7ed0ec0,6275,0,4096,6265,0,4096,6270,0,4096,6315,0,4096,6256,0,4096,6282,0,4096,6280,0,4096,6295,0,4096,6297,0,4096,6284,0,4096,6266,0,4096,6267,0,4096,6316,0,4096,6258,0,4096,6284,0,4096,6278,0,4096,6276,0,4096,6303,0,4096,6319,0,4096,6272,0,4096,6287,0,4096,6292,0,4096,6259,0,4096,6244,0,4096,6247,0,4096,6279,0,4096,6308,0,4096,6325,0,4096,6270,0,4096,6288,0,4096,6301,0,4096,6264,0,4096,64,0x7f52604a0ec0,32768,32768,0,1411551767749472,1411551767765792 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f719d074ec0,0,4893434,2842,2842,0,3008209,2884,2884,0,3693531,2840,2840,0,4755946,2844,2844,0,3066626,2916,2916,0,3804873,2868,2868,0,3252142,2864,2864,0,4476300,2820,2820,0,2954350,2820,2820,0,4062496,2840,2840,0,3474505,2880,2880,0,3357615,2840,2840,0,4920610,2840,2840,0,3165935,2920,2920,0,3358292,2868,2868,0,3102609,2864,2864,0,3416702,2784,2784,0,3889266,2832,2832,0,3431023,2872,2872,0,3536202,2872,2872,0,3319281,2848,2848,0,3611600,2872,2872,0,4564855,2852,2852,0,3948416,2848,2848,0,4021456,2846,2846,0,3292413,2784,2784,0,2882639,2832,2832,0,3946100,2860,2860,0,3749723,2872,2872,0,2710590,2848,2848,0,3573893,2872,2872,0,4205309,2860,2860,64,0x7f5871864ec0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,64,0x7f842c814ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20454,0,2734,38217,0,70013.0,131072.0,0.0,45741.0,64,0x7f64e75d8ec0,0,182947,0,0,65536,63800,56,1680,64,0x7f01f2d00ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119691070.0,60044646.0,0.0,64,0x7f6ecb88cec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2007495.0,64,0x7fc1d67f8ec0,4096,0,1430,0,4096,0,786,0,4096,0,706,0,4096,0,110,0,4098,0,877,0,4097,0,422,0,4096,0,723,0,4096,0,701,0,4096,0,605,0,4096,0,935,0,4096,0,516,0,4098,0,596,0,4096,0,203,0,4096,0,464,0,4096,0,1484,0,4096,0,281,0,4096,0,593,0,4096,0,646,0,4097,0,208,0,4098,0,1107,0,4096,0,0,0,4096,0,460,0,4096,0,440,0,4096,0,744,0,4096,0,2052,0,4096,0,322,0,4097,0,568,0,4096,0,659,0,4096,0,431,0,4096,0,719,0,4096,0,0,0,4096,0,767,0,64,0x7feb1c338ec0,2191,4099,2194,6290,2198,4098,2200,6296,2227,4096,2227,6323,2207,4096,2207,6303,2195,4096,2195,6291,2175,4096,2175,6271,2169,4096,2169,6265,2181,4096,2181,6277,2183,4096,2183,6279,2196,4096,2196,6292,2203,4096,2203,6299,2229,4096,2229,6325,2209,4096,2209,6305,2198,4096,2198,6294,2174,4096,2174,6270,2168,4096,2168,6264,2192,4096,2192,6288,2193,4096,2193,6289,2166,4098,2168,6264,2187,4096,2187,6283,2250,4098,2252,6348,2209,4096,2209,6305,2185,4096,2185,6281,2197,4096,2197,6293,2195,4096,2195,6291,2192,4096,2192,6288,2191,4096,2191,6287,2169,4096,2169,6265,2189,4097,2190,6286,2201,4096,2201,6297,2210,4096,2210,6306,2187,4096,2187,6283,64,0x7f0c851d0ec0,114688,0,32768,32768,16384,16384,65536,49152,57372751.0,203209514.0,46896816.0,131072.0,0.0,520441.0,0,0,24918,6541.0,131087.0,0.0,28.0,64,0x7f2a26314ec0,0,0,0,1925466,4,0,0,1901532,0,0,0,1769391,78,0,0,2063862,49,0,0,1996144,1302,0,0,2244795,0,0,0,1567085,69,0,0,1956879,1,0,0,1666303,0,0,0,1671082,0,0,0,1509605,0,0,0,1696856,1076,0,0,2560896,0,0,0,1888969,724,0,0,2078267,0,0,0,1859150,0,0,0,1746326,0,0,0,1616154,0,0,0,1541765,0,0,0,1842461,0,0,0,1516028,108,0,0,2160627,7,0,0,1691966,0,0,0,1716188,0,0,0,1637841,0,0,0,1746015,0,0,0,1918312,0,0,0,1645271,0,0,0,1677917,0,0,0,1485077,0,0,0,1510985,0,0,0,1731264,64,0x7f980b700ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,99736.0,45511.0,0.0,64,0x7f9e9e168ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32796,28321,9652,2427,0,39845,201111.0,0.0,70029.0,131082.0,64,0x7f80e4520ec0,0,0,0,56,0,65536,65536,0,64,0x7fbd96bb4ec0,18674882,17567758,763060,344064,2706223,0,0,163840,832.0,515148.0,0.0,524288.0,630567.0,32768.0,915443,0,0,13879,91113.0,91113.0,0.0,91113.0,64,0x7fa1d1cb0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f9a5f924ec0,0,393216,163840,0,0,0,0,0,30614,0.0,0.0,0.0,32768.0,0.0,0.0,207.0,32768.0,4096,16384,302,41805,1941,0,56.0,11.0,0.0,200333.0,64,0x7ff854d0cec0,332832,226984,16384,0,16384,16384,32768,49152,41603,41603,3227887.0,2522631.0,4209.0,383730.0,1781211.0,0.0,2511870.0,2205061.0,332824,236399,41603,0,41603,0,1331296.0,778074.0,0.0,0.0,64,0x7f6ca7ed0ec0,6283,0,4096,6303,0,4096,6273,0,4096,6293,0,4096,6279,0,4096,6274,0,4096,6280,0,4096,6297,0,4096,6295,0,4096,6287,0,4096,6307,0,4096,6278,0,4096,6299,0,4096,6280,0,4096,6279,0,4096,6277,0,4096,6285,0,4096,6283,0,4096,6281,0,4096,6284,0,4096,6295,0,4096,6306,0,4096,6263,0,4096,6303,0,4096,6306,0,4096,6283,0,4096,6280,0,4096,6277,0,4096,6283,0,4096,6298,0,4096,6311,0,4096,6267,0,4096,64,0x7f52604a0ec0,32768,32768,0,1411551767786592,1411551767802112 diff --git a/tests/workloads/path/MI200/roofline.csv b/tests/workloads/path/MI200/roofline.csv index 4979628d3e..e2e8aae3f9 100644 --- a/tests/workloads/path/MI200/roofline.csv +++ b/tests/workloads/path/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.7817,1388.1997,1389.3638,5016.855,5014.0708,5019.6392,9224.9346,9224.2139,9225.6553,18053.436,18052.646,18054.225,20938.699,20878.232,20999.166,20268.699,20268.057,20269.342,170460.84,170457.16,170464.53,164873.41,164867.12,164879.69,41422.461,41421.953,41422.969,41480.082,41479.18,41480.984,166350.34,165858.92,166841.77 -1,1389.3734,1388.8273,1389.9196,5028.918,5026.8179,5031.0181,9235.2432,9234.6104,9235.876,18095.488,18092.15,18098.826,20976.51,20909.572,21043.447,20296.172,20295.555,20296.789,170853.42,170849.64,170857.2,165136.66,165132.58,165140.73,41487.176,41486.426,41487.926,41538.578,41537.527,41539.629,166883.66,166880.98,166886.33 -2,1388.9829,1388.427,1389.5388,5036.1621,5033.7979,5038.5264,9260.1328,9259.2217,9261.0439,18102.061,18101.113,18103.008,21049.436,21049.027,21049.844,20356.162,20355.494,20356.83,171141.34,171137.19,171145.5,165517.05,165513.59,165520.5,41585.727,41584.75,41586.703,41645.672,41644.688,41646.656,166960.33,166359.64,167561.02 -3,1389.2076,1388.5834,1389.8319,5031.7515,5030.3901,5033.1128,9241.3428,9240.71,9241.9756,18027.682,18024.373,18030.99,21037.742,21037.279,21038.205,20317.59,20317.133,20318.047,171067.7,171062.72,171072.69,165250.77,165246.25,165255.28,41443.941,41287.488,41600.395,41585.484,41584.891,41586.078,167028.16,167025.73,167030.58 +0,1388.9302,1388.3835,1389.4768,5018.2891,5015.416,5021.1621,9226.7266,9226.168,9227.2852,17717.834,17714.895,17720.773,20941.971,20881.785,21002.156,20272.537,20271.938,20273.137,170483.16,170480.25,170486.06,164938.17,164933.98,164942.36,41438.68,41438.27,41439.09,41497.562,41496.836,41498.289,166402.27,165911.17,166893.36 +1,1389.3043,1388.6895,1389.9192,5029.6997,5027.6914,5031.708,9239.2627,9238.5391,9239.9863,18243.783,18241.363,18246.203,20985.506,20918.434,21052.578,20301.832,20301.094,20302.57,170928.06,170923.66,170932.47,165162.06,165158.09,165166.03,41494.691,41493.625,41495.758,41550.176,41549.141,41551.211,166923.81,166920.55,166927.08 +2,1389.0227,1388.4105,1389.6349,5036.6968,5034.5093,5038.8843,9263.2725,9262.6641,9263.8809,18220.432,18219.43,18221.434,21053.373,21052.924,21053.822,20354.846,20354.256,20355.436,171150.41,171147,171153.81,165537.12,165534.03,165540.22,41587.383,41586.57,41588.195,41645.191,41644.094,41646.289,166970.84,166374.36,167567.33 +3,1389.0236,1388.4886,1389.5585,5033.541,5031.9014,5035.1807,9237.8057,9237.0996,9238.5117,18326.717,18325.787,18327.646,21032.83,21032.598,21033.062,20308.371,20307.881,20308.861,171040.98,171036.05,171045.92,165174.33,165170.09,165178.56,41430.328,41276.879,41583.777,41578.465,41577.258,41579.672,166994.86,166991.23,166998.48 diff --git a/tests/workloads/path/MI200/sysinfo.csv b/tests/workloads/path/MI200/sysinfo.csv index 556709c23a..a382607e3d 100644 --- a/tests/workloads/path/MI200/sysinfo.csv +++ b/tests/workloads/path/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -path,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:12:00 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:16:46 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/path/MI200/timestamps.csv b/tests/workloads/path/MI200/timestamps.csv index e680f7bc6f..c7262b43a5 100644 --- a/tests/workloads/path/MI200/timestamps.csv +++ b/tests/workloads/path/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,287126,287126,1048576,256,0,0,8,0,16,64,0x0,0x7f94deec4ec0,198066321901358,198066321926096,198066321946896,198066321960290 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,287126,287126,1048576,256,0,0,8,0,16,64,0x0,0x7f94deec4ec0,198066321957876,198066321965776,198066321981616,198066322042245 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,287126,287126,1048576,256,0,0,8,0,16,64,0x0,0x7f94deec4ec0,198066321992060,198066322044816,198066322061136,198066322062123 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767610475,1411551767635712,1411551767656192,1411551767669456 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767667252,1411551767749472,1411551767765792,1411551767767061 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767776669,1411551767786592,1411551767802112,1411551767803299 diff --git a/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_fp32.pdf index 821864171d..039da46410 100644 Binary files a/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_int8_fp16.pdf index 5dd56ac8bf..d3067d22aa 100644 Binary files a/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/sort_dispatches/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/sort_dispatches/MI200/log.txt b/tests/workloads/sort_dispatches/MI200/log.txt new file mode 100644 index 0000000000..b27b2ea8aa --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/sort_dispatches/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_160618' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160618_4078157' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160618_4078157/input0_results_240321_160618' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160618_4078157/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160618_4078157/input0_results_240321_160618 + |-> [rocprof] File 'tests/workloads/sort_dispatches/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_160618' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160618_4078342' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160618_4078342/input0_results_240321_160618' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160618_4078342/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160618_4078342/input0_results_240321_160618 + |-> [rocprof] File 'tests/workloads/sort_dispatches/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_160619' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/sort_dispatches/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160619_4078545' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160619_4078545/input0_results_240321_160619' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160619_4078545/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160619_4078545/input0_results_240321_160619 + |-> [rocprof] File 'tests/workloads/sort_dispatches/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/sort_dispatches/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_160619' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/sort_dispatches/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_160619_4078743' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_160619_4078743/input0_results_240321_160619' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_160619_4078743/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_160619_4078743/input0_results_240321_160619 + |-> [rocprof] File 'tests/workloads/sort_dispatches/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/sort_dispatches/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/sort_dispatches/MI200/pmc_dispatch_info.csv b/tests/workloads/sort_dispatches/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/sort_dispatches/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/sort_dispatches/MI200/pmc_perf.csv b/tests/workloads/sort_dispatches/MI200/pmc_perf.csv index a4aaf64899..ee6373fac9 100644 --- a/tests/workloads/sort_dispatches/MI200/pmc_perf.csv +++ b/tests/workloads/sort_dispatches/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_1,obj_1,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f0b0ff2cec0,0,0,64,0x7fe14e710ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,131072.0,131072.0,64,0x7fb733968ec0,0,0,0,0,0,0,0,0,0.0,195833840619598,195833840639758 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f0b0ff2cec0,0,0,64,0x7fe14e710ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,90884.0,90884.0,64,0x7fb733968ec0,0,0,0,0,0,0,0,0,0.0,195833840727598,195833840744078 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7f0b0ff2cec0,0,0,64,0x7fe14e710ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,91096.0,91096.0,64,0x7fb733968ec0,0,0,0,0,0,0,0,0,0.0,195833840764718,195833840780238 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f55f75d8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131080.0,131072.0,131072.0,64,0x7f318e8d8ec0,0,0,64,0x7f54083e8ec0,0,0,0,0,0,0,0,0,0.0,1410911916078829,1410911916099469 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f55f75d8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,90800.0,90800.0,64,0x7f318e8d8ec0,0,0,64,0x7f54083e8ec0,0,0,0,0,0,0,0,0,0.0,1410911916191309,1410911916207629 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f55f75d8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,91298.0,91298.0,64,0x7f318e8d8ec0,0,0,64,0x7f54083e8ec0,0,0,0,0,0,0,0,0,0.0,1410911916229389,1410911916244909 diff --git a/tests/workloads/sort_dispatches/MI200/roofline.csv b/tests/workloads/sort_dispatches/MI200/roofline.csv index d1ae54a28e..664e93cd86 100644 --- a/tests/workloads/sort_dispatches/MI200/roofline.csv +++ b/tests/workloads/sort_dispatches/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1389.1193,1388.5117,1389.7268,5015.0068,5011.9907,5018.0229,9221.998,9221.3828,9222.6133,17639.686,17638.672,17640.699,20928.205,20867.84,20988.57,20262.287,20261.715,20262.859,170396.5,170391.77,170401.23,164866.34,164862.11,164870.58,41419.062,41418.352,41419.773,41476.004,41475.344,41476.664,166322.31,165832.64,166811.98 -1,1388.9008,1388.3511,1389.4504,5027.5708,5025.5728,5029.5688,9229.8926,9229.2207,9230.5645,18065.086,18063.896,18066.275,20967.1,20900.262,21033.938,20287.465,20286.975,20287.955,170787.73,170783.19,170792.28,165052.28,165047.59,165056.97,41463.211,41462.293,41464.129,41526.121,41525.238,41527.004,166812.8,166807.95,166817.64 -2,1389.2667,1388.7651,1389.7683,5035.5039,5033.2363,5037.7715,9258.3965,9257.6201,9259.1729,18263.133,18262.299,18263.967,21044.596,21044.225,21044.967,20349.471,20348.801,20350.141,171117.73,171113.25,171122.22,165495.05,165491.34,165498.75,41580.641,41579.605,41581.676,41633.578,41632.25,41634.906,166904.03,166310.52,167497.55 -3,1389.0205,1388.4252,1389.6158,5032.0649,5030.7285,5033.4014,9240.1006,9239.5449,9240.6562,18325.539,18323.268,18327.811,21029.975,21029.445,21030.504,20310.877,20310.246,20311.508,171008.78,171004.34,171013.22,165225.19,165221.83,165228.55,41441.34,41286.738,41595.941,41586.016,41585.27,41586.762,167043.02,167041.42,167044.61 +0,1388.8945,1388.3401,1389.449,5017.1187,5014.147,5020.0903,9226.9463,9226.3076,9227.585,17716.205,17713.113,17719.297,20942.73,20882.547,21002.914,20273.014,20272.486,20273.541,170483.86,170479.92,170487.8,164916.7,164912.91,164920.5,41433.73,41433.27,41434.191,41494.02,41493.422,41494.617,166394.12,165902.52,166885.73 +1,1389.0057,1388.4355,1389.5759,5028.5698,5026.3857,5030.7539,9236.3408,9235.6191,9237.0625,18236.148,18235.035,18237.262,20982.08,20915.066,21049.094,20297.359,20296.768,20297.951,170874.95,170870.89,170879.02,165128.47,165123.88,165133.06,41493.141,41492.258,41494.023,41548.73,41547.848,41549.613,166900.02,166897.2,166902.83 +2,1388.8661,1388.3425,1389.3896,5037.0093,5034.6519,5039.3667,9263.1514,9262.4375,9263.8652,18221.111,18220.066,18222.156,21053.016,21052.539,21053.492,20352.568,20351.951,20353.186,171136.36,171133.19,171139.53,165533.98,165530.41,165537.56,41587.602,41586.855,41588.348,41645.258,41644.535,41645.98,166955.81,166361.33,167550.3 +3,1388.9897,1388.4364,1389.5431,5032.126,5030.5762,5033.6758,9237.1162,9236.2871,9237.9453,18326.25,18325.508,18326.992,21032.137,21031.832,21032.441,20305.037,20304.525,20305.549,171005.62,171001.17,171010.08,165116.06,165111.56,165120.56,41420.133,41266.98,41573.285,41571.484,41570.562,41572.406,166991.22,166985.86,166996.58 diff --git a/tests/workloads/sort_dispatches/MI200/sysinfo.csv b/tests/workloads/sort_dispatches/MI200/sysinfo.csv index 1feeb577c2..7a9980829d 100644 --- a/tests/workloads/sort_dispatches/MI200/sysinfo.csv +++ b/tests/workloads/sort_dispatches/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -sort_dispatches,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:03:05 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +sort_dispatches,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:06:17 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/sort_dispatches/MI200/timestamps.csv b/tests/workloads/sort_dispatches/MI200/timestamps.csv index 06ff364328..19a8b341ff 100644 --- a/tests/workloads/sort_dispatches/MI200/timestamps.csv +++ b/tests/workloads/sort_dispatches/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,182586,182586,1048576,256,0,0,8,0,16,64,0x0,0x7f60edf4cec0,195833840595837,195833840619598,195833840639758,195833840652003 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,182586,182586,1048576,256,0,0,8,0,16,64,0x0,0x7f60edf4cec0,195833840650831,195833840727598,195833840744078,195833840745339 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,182586,182586,1048576,256,0,0,8,0,16,64,0x0,0x7f60edf4cec0,195833840755068,195833840764718,195833840780238,195833840781368 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4078903,4078903,1048576,256,0,0,8,0,16,64,0x0,0x7fbb61ed4ec0,1410911916052824,1410911916078829,1410911916099469,1410911916110573 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4078903,4078903,1048576,256,0,0,8,0,16,64,0x0,0x7fbb61ed4ec0,1410911916110322,1410911916191309,1410911916207629,1410911916208949 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4078903,4078903,1048576,256,0,0,8,0,16,64,0x0,0x7fbb61ed4ec0,1410911916218587,1410911916229389,1410911916244909,1410911916245919 diff --git a/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_fp32.pdf b/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_fp32.pdf index 87c5bdb502..e64127a6f8 100644 Binary files a/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_fp32.pdf and b/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_fp32.pdf differ diff --git a/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_int8_fp16.pdf b/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_int8_fp16.pdf index 4f3255ff4b..154dfd8435 100644 Binary files a/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_int8_fp16.pdf and b/tests/workloads/sort_kernels/MI200/empirRoof_gpu-0_int8_fp16.pdf differ diff --git a/tests/workloads/sort_kernels/MI200/log.txt b/tests/workloads/sort_kernels/MI200/log.txt new file mode 100644 index 0000000000..8892df941e --- /dev/null +++ b/tests/workloads/sort_kernels/MI200/log.txt @@ -0,0 +1,132 @@ +[roofline] Generating pmc_perf.csv (roofline counters only). +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/sort_kernels/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_163635' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163635_4159601' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163635_4159601/input0_results_240321_163635' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163635_4159601/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 16 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, TCP_TCC_READ_REQ_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RDREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WRREQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163635_4159601/input0_results_240321_163635 + |-> [rocprof] File 'tests/workloads/sort_kernels/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_163635' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163635_4159785' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163635_4159785/input0_results_240321_163635' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163635_4159785/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163635_4159785/input0_results_240321_163635 + |-> [rocprof] File 'tests/workloads/sort_kernels/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_163636' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/sort_kernels/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163636_4159971' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163636_4159971/input0_results_240321_163636' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163636_4159971/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 2 metrics + |-> [rocprof] SQ_LDS_IDX_ACTIVE, SQ_LDS_BANK_CONFLICT + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163636_4159971/input0_results_240321_163636 + |-> [rocprof] File 'tests/workloads/sort_kernels/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/sort_kernels/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_163636' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/sort_kernels/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_163636_4160158' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_163636_4160158/input0_results_240321_163636' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_163636_4160158/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_163636_4160158/input0_results_240321_163636 + |-> [rocprof] File 'tests/workloads/sort_kernels/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/sort_kernels/MI200 +[roofline] No roofline data found. Generating... +[roofline] Empirical Roofline PDFs saved! diff --git a/tests/workloads/sort_kernels/MI200/pmc_dispatch_info.csv b/tests/workloads/sort_kernels/MI200/pmc_dispatch_info.csv new file mode 100644 index 0000000000..2166cd6fad --- /dev/null +++ b/tests/workloads/sort_kernels/MI200/pmc_dispatch_info.csv @@ -0,0 +1,4 @@ +Dispatch_ID,Kernel_Name,GPU_ID +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/sort_kernels/MI200/pmc_perf.csv b/tests/workloads/sort_kernels/MI200/pmc_perf.csv index e5e5c5650c..bf03cd1bb1 100644 --- a/tests/workloads/sort_kernels/MI200/pmc_perf.csv +++ b/tests/workloads/sort_kernels/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,wave_size_1,obj_1,SQ_LDS_IDX_ACTIVE,SQ_LDS_BANK_CONFLICT,wave_size_2,obj_2,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,TCP_TCC_READ_REQ_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RDREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WRREQ_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc43245cec0,0,0,0,0,0,0,0,0,0.0,64,0x7f8e30790ec0,0,0,64,0x7f3100404ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131083.0,131072.0,131072.0,199148231834526,199148231855006 -1,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc43245cec0,0,0,0,0,0,0,0,0,0.0,64,0x7f8e30790ec0,0,0,64,0x7f3100404ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131085.0,91176.0,91176.0,199148231874206,199148231889886 -2,"vecCopy(double*, double*, double*, int, int) ",2,1048576,256,0,0,8,0,16,64,0x7fc43245cec0,0,0,0,0,0,0,0,0,0.0,64,0x7f8e30790ec0,0,0,64,0x7f3100404ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131085.0,90976.0,90976.0,199148231956286,199148231972286 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa62b720ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fcf1e658ec0,0,0,64,0x7f19a45d8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131081.0,131072.0,131072.0,1412728954551781,1412728954572261 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa62b720ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fcf1e658ec0,0,0,64,0x7f19a45d8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131073.0,90720.0,90720.0,1412728954592101,1412728954607781 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7fa62b720ec0,0,0,0,0,0,0,0,0,0.0,64,0x7fcf1e658ec0,0,0,64,0x7f19a45d8ec0,0,0,0,0,0,0,0,0,131072.0,524288.0,131072.0,0.0,0.0,131082.0,90966.0,90966.0,1412728954663141,1412728954679621 diff --git a/tests/workloads/sort_kernels/MI200/roofline.csv b/tests/workloads/sort_kernels/MI200/roofline.csv index 9ddb28b69a..85199db809 100644 --- a/tests/workloads/sort_kernels/MI200/roofline.csv +++ b/tests/workloads/sort_kernels/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.817,1388.1855,1389.4485,5012.6865,5009.5811,5015.792,9220.6367,9220.0068,9221.2666,18045.574,18044.607,18046.541,20922.65,20862.299,20983.002,20255.824,20255.203,20256.445,170366.09,170360.36,170371.83,164790.75,164786.69,164794.81,41401.891,41400.898,41402.883,41459.949,41459.016,41460.883,166269.62,165773.78,166765.47 -1,1388.777,1388.2977,1389.2562,5028.2456,5026.2231,5030.2681,9234.8936,9234.1396,9235.6475,18095.113,18090.842,18099.385,20973.869,20906.225,21041.514,20293.096,20292.455,20293.736,170831.62,170827.34,170835.91,165106.66,165103.06,165110.25,41486.219,41485.355,41487.082,41542.781,41542.02,41543.543,166885.89,166882.86,166888.92 -2,1388.8604,1388.2374,1389.4833,5037.2046,5034.9478,5039.4614,9261.4053,9260.6631,9262.1475,18107.312,18106.568,18108.057,21049.461,21049.072,21049.85,20353.656,20353.066,20354.246,171148.52,171144.45,171152.58,165531.92,165527.5,165536.34,41590.082,41588.914,41591.25,41652.598,41651.301,41653.895,166988.36,166396.97,167579.75 -3,1389.4712,1388.8257,1390.1167,5033.3506,5032.0864,5034.6147,9241.7871,9241.1338,9242.4404,18025.9,18022.322,18029.479,21038.676,21038.127,21039.225,20316.174,20315.494,20316.854,171045.52,171041.98,171049.05,165247.22,165242.25,165252.19,41445.641,41290.402,41600.879,41588.078,41587.602,41588.555,167041.83,167039.48,167044.17 +0,1389.4083,1388.7252,1390.0914,5014.7871,5011.627,5017.9473,9224.3047,9223.6523,9224.957,17712.869,17709.898,17715.84,20936.605,20876.209,20997.002,20269.707,20269.135,20270.279,170468.42,170463.95,170472.89,164898.81,164894.66,164902.97,41428.293,41427.617,41428.969,41490.922,41490.02,41491.824,166374.97,165884.23,166865.7 +1,1388.8337,1388.2723,1389.3951,5029.3052,5027.2275,5031.3828,9233.3262,9232.6865,9233.9658,18231.748,18229.787,18233.709,20975.846,20908.631,21043.061,20295.293,20294.738,20295.848,170862.05,170857.84,170866.25,165094.06,165088.2,165099.92,41476.398,41475.715,41477.082,41534.691,41533.684,41535.699,166860.27,166857.86,166862.67 +2,1388.8483,1388.2845,1389.412,5037.0698,5034.7798,5039.3599,9264.0791,9263.3887,9264.7695,18222.602,18221.697,18223.506,21054.76,21054.275,21055.244,20354.398,20353.938,20354.859,171178.19,171173.42,171182.95,165571.77,165567.75,165575.78,41597.168,41596.406,41597.93,41649.617,41648.801,41650.434,167007.92,166413.14,167602.7 +3,1388.8545,1388.2826,1389.4264,5034.8096,5033.1797,5036.4395,9242.9199,9242.2529,9243.5869,18339.264,18338.279,18340.248,21041.057,21040.711,21041.402,20317.131,20316.738,20317.523,171099.56,171093.95,171105.17,165232.48,165228.45,165236.52,41444.078,41289.859,41598.297,41598.164,41597.406,41598.922,167054.95,167051.16,167058.75 diff --git a/tests/workloads/sort_kernels/MI200/sysinfo.csv b/tests/workloads/sort_kernels/MI200/sysinfo.csv index 9a0a34c771..3cadeb5cc9 100644 --- a/tests/workloads/sort_kernels/MI200/sysinfo.csv +++ b/tests/workloads/sort_kernels/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -sort_kernels,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 02:30:13 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +sort_kernels,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:36:34 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/sort_kernels/MI200/timestamps.csv b/tests/workloads/sort_kernels/MI200/timestamps.csv index 92054e32b1..e78954c684 100644 --- a/tests/workloads/sort_kernels/MI200/timestamps.csv +++ b/tests/workloads/sort_kernels/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,335825,335825,1048576,256,0,0,8,0,16,64,0x0,0x7f0145064ec0,199148231809224,199148231834526,199148231855006,199148231871421 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,335825,335825,1048576,256,0,0,8,0,16,64,0x0,0x7f0145064ec0,199148231865981,199148231874206,199148231889886,199148231953617 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,335825,335825,1048576,256,0,0,8,0,16,64,0x0,0x7f0145064ec0,199148231900226,199148231956286,199148231972286,199148231973294 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4160318,4160318,1048576,256,0,0,8,0,16,64,0x0,0x7f86958dcec0,1412728954526582,1412728954551781,1412728954572261,1412728954587256 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4160318,4160318,1048576,256,0,0,8,0,16,64,0x0,0x7f86958dcec0,1412728954583699,1412728954592101,1412728954607781,1412728954660344 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4160318,4160318,1048576,256,0,0,8,0,16,64,0x0,0x7f86958dcec0,1412728954618104,1412728954663141,1412728954679621,1412728954680522 diff --git a/tests/workloads/vcopy/MI100/SQ_IFETCH_LEVEL.csv b/tests/workloads/vcopy/MI100/SQ_IFETCH_LEVEL.csv index c88381f03d..d892e2fcd5 100644 --- a/tests/workloads/vcopy/MI100/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/vcopy/MI100/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,226609,226609,1048576,256,0,0,8,8,16,64,0x0,0x7fb44b588e80,48538,48538,16384,65536,12877,1624136,194455470989307,194467450121772,194467450145932,194455478828920 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,226609,226609,1048576,256,0,0,8,8,16,64,0x0,0x7fb44b588e80,42537,42537,16384,65536,8117,1048584,194455478852825,194467450225612,194467450244652,194455479147884 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,226609,226609,1048576,256,0,0,8,8,16,64,0x0,0x7fb44b588e80,42665,42665,16384,65536,8224,1048580,194455479178452,194467450265772,194467450284492,194455479336521 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,48280,48280,16384,65536,12983,1679996,1410066882102360,1410078545959517,1410078545984317,1410066889784789 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,42583,42583,16384,65536,8224,1048592,1410066889807272,1410078546083997,1410078546102877,1410066890267580 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1225967,1225967,1048576,256,0,0,8,8,16,64,0x0,0x7f1a76c30ec0,42228,42228,16384,65536,8413,1048584,1410066890299460,1410078546122717,1410078546141597,1410066890460213 diff --git a/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_LDS.csv b/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_LDS.csv index 62334da2b6..7bb92ef543 100644 --- a/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,226811,226811,1048576,256,0,0,8,8,16,64,0x0,0x7f9616f62e80,0,0,0,194455960598181,194467450121772,194467450145932,194455968194895 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,226811,226811,1048576,256,0,0,8,8,16,64,0x0,0x7f9616f62e80,0,0,0,194455968212488,194467450225612,194467450244652,194455968532003 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,226811,226811,1048576,256,0,0,8,8,16,64,0x0,0x7f9616f62e80,0,0,0,194455968560296,194467450265772,194467450284492,194455968727573 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067370617243,1410078545959517,1410078545984317,1410067378299552 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067378319499,1410078546083997,1410078546102877,1410067378620818 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226153,1226153,1048576,256,0,0,8,8,16,64,0x0,0x7feaeff04ec0,0,0,0,1410067378648971,1410078546122717,1410078546141597,1410067378823961 diff --git a/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_SMEM.csv index 16bd322542..ae79254d0a 100644 --- a/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,227014,227014,1048576,256,0,0,8,8,16,64,0x0,0x7fe96b10ee80,65536,189124,24173112,194456442214233,194467450121772,194467450145932,194456449987921 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,227014,227014,1048576,256,0,0,8,8,16,64,0x0,0x7fe96b10ee80,65536,169880,21617640,194456450005544,194467450225612,194467450244652,194456450333596 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,227014,227014,1048576,256,0,0,8,8,16,64,0x0,0x7fe96b10ee80,65536,165968,21318104,194456450361970,194467450265772,194467450284492,194456450537281 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,216912,27721752,1410067844907387,1410078545959517,1410078545984317,1410067852593644 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,174742,22439080,1410067852616707,1410078546083997,1410078546102877,1410067852942802 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226337,1226337,1048576,256,0,0,8,8,16,64,0x0,0x7f43adec4ec0,65536,198278,25317408,1410067852970845,1410078546122717,1410078546141597,1410067853139804 diff --git a/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_VMEM.csv index bc9053129e..dd1f25ff77 100644 --- a/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/vcopy/MI100/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,227214,227214,1048576,256,0,0,8,8,16,64,0x0,0x7f8e1c788e80,32768,649688,83156252,194456926059876,194467450121772,194467450145932,194456933836710 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,227214,227214,1048576,256,0,0,8,8,16,64,0x0,0x7f8e1c788e80,32768,672924,86136476,194456933855646,194467450225612,194467450244652,194456934273147 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,227214,227214,1048576,256,0,0,8,8,16,64,0x0,0x7f8e1c788e80,32768,673008,86143768,194456934300989,194467450265772,194467450284492,194456934480729 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,660786,84583280,1410068324788176,1410078545959517,1410078545984317,1410068332535197 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,671026,85878140,1410068332555144,1410078546083997,1410078546102877,1410068332853858 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226522,1226522,1048576,256,0,0,8,8,16,64,0x0,0x7fb95f3b0ec0,32768,632212,80916468,1410068332882612,1410078546122717,1410078546141597,1410068333052552 diff --git a/tests/workloads/vcopy/MI100/SQ_LEVEL_WAVES.csv b/tests/workloads/vcopy/MI100/SQ_LEVEL_WAVES.csv index 215f374528..419592ce68 100644 --- a/tests/workloads/vcopy/MI100/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/vcopy/MI100/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,227415,227415,1048576,256,0,0,8,8,16,64,0x0,0x7f4755960e80,48150,48150,17009,385208,16384,25742850,237985,0,103461844,194457417430176,194467450121772,194467450145932,194457425294145 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,227415,227415,1048576,256,0,0,8,8,16,64,0x0,0x7f4755960e80,112053,112053,11262,896432,16384,24750038,228687,0,99498348,194457425322959,194467450225612,194467450244652,194457425683342 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,227415,227415,1048576,256,0,0,8,8,16,64,0x0,0x7f4755960e80,45085,45085,16556,360688,16384,24371228,227315,0,97975408,194457425721003,194467450265772,194467450284492,194457425907586 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,49066,49066,17535,392536,16384,25278471,238150,0,101647680,1410068786184713,1410078545959517,1410078545984317,1410068793791259 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,42938,42938,13608,343512,16384,24688741,232286,0,99287100,1410068793822348,1410078546083997,1410078546102877,1410068794118977 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1226710,1226710,1048576,256,0,0,8,8,16,64,0x0,0x7efd2e720ec0,43314,43314,13851,346520,16384,25149283,234233,0,101130872,1410068794157149,1410078546122717,1410078546141597,1410068794339493 diff --git a/tests/workloads/vcopy/MI100/log.txt b/tests/workloads/vcopy/MI100/log.txt new file mode 100644 index 0000000000..41d601bea5 --- /dev/null +++ b/tests/workloads/vcopy/MI100/log.txt @@ -0,0 +1,679 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/path/MI100 +Target: MI100 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_155212' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155212_1225807' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155212_1225807/input0_results_240321_155212' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155212_1225807/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155212_1225807/input0_results_240321_155212 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_155213' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155213_1225993' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155213_1225993/input0_results_240321_155213' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155213_1225993/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155213_1225993/input0_results_240321_155213 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_155213' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155213_1226177' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155213_1226177/input0_results_240321_155213' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155213_1226177/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155213_1226177/input0_results_240321_155213 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_155214' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155214_1226362' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155214_1226362/input0_results_240321_155214' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155214_1226362/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155214_1226362/input0_results_240321_155214 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_155214' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155214_1226550' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155214_1226550/input0_results_240321_155214' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155214_1226550/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155214_1226550/input0_results_240321_155214 + |-> [rocprof] File 'tests/workloads/path/MI100/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_155215' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155215_1226735' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155215_1226735/input0_results_240321_155215' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155215_1226735/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155215_1226735/input0_results_240321_155215 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_155215' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155215_1226918' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155215_1226918/input0_results_240321_155215' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155215_1226918/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_COALESCABLE_WAVEFRONT_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155215_1226918/input0_results_240321_155215 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_155216' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155216_1227103' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155216_1227103/input0_results_240321_155216' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155216_1227103/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 1 metrics + |-> [rocprof] TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155216_1227103/input0_results_240321_155216 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_155216' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155216_1227289' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155216_1227289/input0_results_240321_155216' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155216_1227289/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155216_1227289/input0_results_240321_155216 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_155217' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155217_1227490' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155217_1227490/input0_results_240321_155217' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155217_1227490/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155217_1227490/input0_results_240321_155217 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_155218' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155218_1227691' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155218_1227691/input0_results_240321_155218' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155218_1227691/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155218_1227691/input0_results_240321_155218 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_155218' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155218_1227878' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155218_1227878/input0_results_240321_155218' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155218_1227878/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155218_1227878/input0_results_240321_155218 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_155219' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155219_1228062' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155219_1228062/input0_results_240321_155219' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155219_1228062/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155219_1228062/input0_results_240321_155219 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_155220' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155220_1228263' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155220_1228263/input0_results_240321_155220' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155220_1228263/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155220_1228263/input0_results_240321_155220 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_155220' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155220_1228465' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155220_1228465/input0_results_240321_155220' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155220_1228465/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155220_1228465/input0_results_240321_155220 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_155221' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155221_1228650' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155221_1228650/input0_results_240321_155221' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155221_1228650/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 23 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155221_1228650/input0_results_240321_155221 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_155221' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155221_1228834' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155221_1228834/input0_results_240321_155221' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155221_1228834/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAIT_ANY, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155221_1228834/input0_results_240321_155221 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_155222' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155222_1229018' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155222_1229018/input0_results_240321_155222' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155222_1229018/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_WRREQ_IO_CREDIT_STALL_sum, TCC_EA_WRREQ_GMI_CREDIT_STALL_sum, TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155222_1229018/input0_results_240321_155222 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_155222' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155222_1229202' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155222_1229202/input0_results_240321_155222' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155222_1229202/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, SQ_THREAD_CYCLES_VALU, SQ_IFETCH, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum, TCC_EA_RDREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155222_1229202/input0_results_240321_155222 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_155223' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155223_1229386' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155223_1229386/input0_results_240321_155223' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155223_1229386/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_EA_RDREQ_IO_CREDIT_STALL_sum, TCC_EA_RDREQ_GMI_CREDIT_STALL_sum, TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum, TCC_TAG_STALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155223_1229386/input0_results_240321_155223 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_155223' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155223_1229572' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155223_1229572/input0_results_240321_155223' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155223_1229572/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155223_1229572/input0_results_240321_155223 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_155224' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155224_1229760' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155224_1229760/input0_results_240321_155224' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155224_1229760/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155224_1229760/input0_results_240321_155224 + |-> [rocprof] File 'tests/workloads/path/MI100/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI100/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_155224' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI100/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155224_1229944' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155224_1229944/input0_results_240321_155224' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155224_1229944/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155224_1229944/input0_results_240321_155224 + |-> [rocprof] File 'tests/workloads/path/MI100/timestamps.csv' is generating + |-> [rocprof] diff --git a/tests/workloads/vcopy/MI100/pmc_dispatch_info.csv b/tests/workloads/vcopy/MI100/pmc_dispatch_info.csv index 963116dcd7..2166cd6fad 100644 --- a/tests/workloads/vcopy/MI100/pmc_dispatch_info.csv +++ b/tests/workloads/vcopy/MI100/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int)",2 -1,"vecCopy(double*, double*, double*, int, int)",2 -2,"vecCopy(double*, double*, double*, int, int)",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/vcopy/MI100/pmc_perf.csv b/tests/workloads/vcopy/MI100/pmc_perf.csv index 9c3398d6ec..2908704350 100644 --- a/tests/workloads/vcopy/MI100/pmc_perf.csv +++ b/tests/workloads/vcopy/MI100/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_1,obj_1,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_2,obj_2,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_3,obj_3,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_4,obj_4,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_5,obj_5,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_6,obj_6,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_7,obj_7,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_8,obj_8,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_9,obj_9,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_10,obj_10,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_11,obj_11,TCC_EA_ATOMIC_LEVEL_sum,wave_size_12,obj_12,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_13,obj_13,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_14,obj_14,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_15,obj_15,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_16,obj_16,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int)",2,1048576,256,0,0,8,8,16,64,0x7fa114eb6e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86587.0,44485.0,131112.0,0.0,64,0x7f5268092e80,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8195,4099,8195,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7f0aa4228e80,32768,0,0,0,16384,16384,393216,23231186,960.0,513884.0,0.0,524288.0,878820.0,32768.0,0,0,0,15909,131072.0,131072.0,0.0,131072.0,64,0x7ff04a802e80,4096,0,1860,0,4096,0,1789,0,4099,0,845,0,4096,0,1248,0,4245,0,4615,0,4096,0,4497,0,4096,0,472,0,4096,0,66,0,4144,0,2579,0,4096,0,4281,0,4096,0,1253,0,4144,0,2693,0,4096,0,4877,0,4096,0,92,0,4096,0,630,0,4096,0,4,0,4096,0,3012,0,4096,0,5350,0,4096,0,3729,0,4096,0,1388,0,4096,0,3567,0,4096,0,0,0,4096,0,1247,0,4096,0,802,0,4096,0,1181,0,4096,0,2001,0,4096,0,5417,0,4096,0,1545,0,4096,0,524,0,4096,0,968,0,4096,0,246,0,4096,0,4876,0,64,0x7f8f88412e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,34637.0,102706.0,64,0x7f8457ebae80,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f40ea9d4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131287.0,0.0,422.0,131286.0,64,0x7f16c71f8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,46862,0,131687.0,131072.0,0.0,131104.0,64,0x7fd86d54ee80,192027,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,9926,26310,9599,550,0,47272,262691.0,0.0,188.0,262503.0,64,0x7fce20e02e80,383304,233733,3431076,16384,25056572,144,48,0,47912,47912,3859046.0,3048862.0,5723.0,1007296.0,2127231.0,0.0,3040186.0,2729662.0,381591,243686,47912,0,47912,0,1533184.0,969455.0,0.0,0.0,64,0x7fa7c9910e80,0,0,192,0,65536,64481,48,1318,31444,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,47280,1633,0,48.0,327.0,0.0,262288.0,64,0x7ff3bfa70e80,0.0,64,0x7f17b1718e80,2019111,360448,163840,0,0,180224,114688,0,70536718.0,199192008.0,72521884.0,131072.0,0.0,641370.0,0,0,25999,82227.0,0.0,0.0,82227.0,64,0x7f058dfcee80,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,0,46976,0,0,64,0x7ffbc6c38e80,131072.0,131072.0,0.0,2573647.0,0.0,0.0,113664696.0,63465268.0,64,0x7f95719dce80,6279,0,0,2226525,3809,0,0,2019558,2160,0,0,1759904,4860,0,0,2103599,4104,0,0,2021325,3419,0,0,2008617,1110,0,0,1661737,1457,0,0,1745061,2228,0,0,1840433,4374,0,0,2112184,1907,0,0,1796647,1480,0,0,1739053,2175,0,0,1745751,6037,0,0,2134703,3018,0,0,1941768,2004,0,0,1807086,2915,0,0,1832386,1283,0,0,1685872,2796,0,0,1890935,4591,0,0,2022103,2495,0,0,1846311,2482,0,0,1830416,2412,0,0,1853631,5163,0,0,2168806,4893,0,0,2066079,2196,0,0,1775911,1146,0,0,1639327,5900,0,0,2135438,2976,0,0,1974632,2080,0,0,1822596,2754,0,0,1838302,1276,0,0,1632988,64,0x7fc09c83ae80,0,4205963,4096,4096,0,3708023,4096,4096,0,2865598,4096,4096,0,4342197,4096,4096,0,4201011,4096,4096,0,4866230,4096,4096,0,3886719,4096,4096,0,4730974,4096,4096,0,4393746,4096,4096,0,3308560,4096,4096,0,4351106,4096,4096,0,4794320,4096,4096,0,4134011,4096,4096,0,3951156,4096,4096,0,3512795,4096,4096,0,3576566,4096,4096,0,4022676,4096,4096,0,4784406,4096,4096,0,3467685,4096,4096,0,4128076,4096,4096,0,3456433,4096,4096,0,4881711,4096,4096,0,3921674,4096,4096,0,4519375,4096,4096,0,3311201,4096,4096,0,3640699,4096,4096,0,4019215,4096,4096,0,4295799,4096,4096,0,3319807,4096,4096,0,3848134,4096,4096,0,4285701,4096,4096,0,4269130,4096,4096,194467450121772,194467450145932 -1,"vecCopy(double*, double*, double*, int, int)",2,1048576,256,0,0,8,8,16,64,0x7fa114eb6e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,85356.0,43196.0,128666.0,0.0,64,0x7f5268092e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8215,4119,8215,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,64,0x7f0aa4228e80,32768,0,0,0,16384,16384,393216,23198743,960.0,513931.0,0.0,524288.0,868697.0,32768.0,0,0,0,14189,86648.0,86648.0,0.0,86648.0,64,0x7ff04a802e80,4096,0,538,0,4096,0,5731,0,4096,0,0,0,4096,0,1706,0,4231,0,2738,0,4096,0,119,0,4096,0,0,0,4096,0,1584,0,4144,0,3431,0,4096,0,4631,0,4096,0,0,0,4144,0,3604,0,4096,0,636,0,4096,0,150,0,4096,0,0,0,4096,0,1549,0,4096,0,3157,0,4096,0,9079,0,4096,0,0,0,4098,0,833,0,4096,0,0,0,4096,0,939,0,4096,0,19,0,4096,0,961,0,4096,0,182,0,4096,0,3547,0,4096,0,107,0,4096,0,317,0,4096,0,701,0,4097,0,26,0,4096,0,0,0,4097,0,2690,0,64,0x7f8f88412e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,78274.0,146228.0,64,0x7f8457ebae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f40ea9d4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131357.0,0.0,568.0,131356.0,64,0x7f16c71f8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,37624,0,131126.0,131072.0,0.0,86517.0,64,0x7fd86d54ee80,170065,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13792,30176,8429,2429,0,40626,262495.0,0.0,47.0,262448.0,64,0x7fce20e02e80,311536,216279,3149582,16384,22472522,0,48,0,38941,38941,3534146.0,2992241.0,6827.0,1215229.0,2013659.0,0.0,2983148.0,2671298.0,311528,226059,38941,0,38941,0,1246112.0,809929.0,0.0,0.0,64,0x7fa7c9910e80,0,0,48,0,65536,65536,0,0,31041,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,456,42275,1606,0,48.0,378.0,0.0,262144.0,64,0x7ff3bfa70e80,0.0,64,0x7f17b1718e80,1350481,360448,163840,0,0,180224,114688,0,69628122.0,187060686.0,70531233.0,131072.0,0.0,635149.0,0,0,25226,78844.0,0.0,0.0,78844.0,64,0x7f058dfcee80,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,0,42606,0,0,64,0x7ffbc6c38e80,131072.0,131072.0,0.0,2454185.0,0.0,0.0,108208423.0,37486768.0,64,0x7f95719dce80,3801,0,0,1665273,660,0,0,1277595,3149,0,0,1545073,1310,0,0,1394302,1236,0,0,1345511,414,0,0,1288793,4908,0,0,1768649,955,0,0,1369050,968,0,0,1384485,1107,0,0,1318629,5202,0,0,1783473,722,0,0,1312547,1040,0,0,1419823,732,0,0,1319000,2899,0,0,1627144,3984,0,0,1733078,1760,0,0,1471304,702,0,0,1335514,2544,0,0,1572526,802,0,0,1314524,1739,0,0,1441149,624,0,0,1242623,2040,0,0,1493100,1574,0,0,1491432,2953,0,0,1558202,425,0,0,1248388,1832,0,0,1413200,4889,0,0,1639064,1172,0,0,1367656,1653,0,0,1395814,959,0,0,1382025,422,0,0,1289095,64,0x7fc09c83ae80,0,4381662,2750,2750,0,3812784,2720,2720,0,3821061,2688,2688,0,3530533,2702,2702,0,4963882,2716,2716,0,2591752,2722,2722,0,2815796,2692,2692,0,2889611,2697,2697,0,4958411,2744,2744,0,5207748,2676,2676,0,3991626,2696,2696,0,3311358,2712,2712,0,4221878,2714,2714,0,2489713,2681,2681,0,5113387,2680,2680,0,3411734,2674,2674,0,4107901,2712,2712,0,3535452,2692,2692,0,3488370,2678,2678,0,4813286,2704,2704,0,4100690,2734,2734,0,3651372,2728,2728,0,4964715,2666,2666,0,3197353,2682,2682,0,3248934,2704,2704,0,3974057,2696,2696,0,3288394,2712,2712,0,3418945,2700,2700,0,2642528,2752,2752,0,3839920,2696,2696,0,3826029,2707,2707,0,2779706,2692,2692,194467450225612,194467450244652 -2,"vecCopy(double*, double*, double*, int, int)",2,1048576,256,0,0,8,8,16,64,0x7fa114eb6e80,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86617.0,0.0,131112.0,0.0,64,0x7f5268092e80,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8360,4264,8360,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8205,4109,8205,0,8192,4096,8192,0,8194,4098,8194,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,64,0x7f0aa4228e80,32768,0,0,0,16384,16384,393216,22563731,960.0,513937.0,0.0,524288.0,856940.0,32768.0,0,0,0,13437,86408.0,86408.0,0.0,86408.0,64,0x7ff04a802e80,4096,0,2954,0,4096,0,2414,0,4096,0,1282,0,4096,0,1617,0,4279,0,7345,0,4096,0,1876,0,4096,0,2038,0,4096,0,1880,0,4144,0,959,0,4096,0,6569,0,4096,0,1443,0,4144,0,2435,0,4096,0,3378,0,4096,0,2295,0,4096,0,1535,0,4096,0,0,0,4096,0,2857,0,4096,0,5985,0,4096,0,4017,0,4098,0,0,0,4096,0,1885,0,4096,0,4696,0,4096,0,1633,0,4096,0,0,0,4096,0,5042,0,4096,0,2637,0,4096,0,869,0,4096,0,0,0,4096,0,2683,0,4097,0,2647,0,4096,0,1390,0,4097,0,4939,0,64,0x7f8f88412e80,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,52842.0,118502.0,64,0x7f8457ebae80,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f40ea9d4e80,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131272.0,0.0,398.0,131271.0,64,0x7f16c71f8e80,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2714,38439,0,131558.0,131072.0,0.0,86620.0,64,0x7fd86d54ee80,193252,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13377,29761,8289,2830,0,40965,262528.0,0.0,47.0,262481.0,64,0x7fce20e02e80,332304,230002,3358389,16384,24810841,0,48,0,41537,41537,3748436.0,3050786.0,8479.0,1116464.0,2086428.0,0.0,3042334.0,2730090.0,332296,239837,41537,0,41537,0,1329184.0,811024.0,0.0,0.0,64,0x7fa7c9910e80,0,0,48,0,65536,65536,0,0,31041,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42640,1633,0,48.0,318.0,0.0,262144.0,64,0x7ff3bfa70e80,0.0,64,0x7f17b1718e80,1213140,360448,163840,0,0,180224,114688,0,68277545.0,193871407.0,73477943.0,131072.0,0.0,528075.0,0,0,24963,75933.0,0.0,0.0,75933.0,64,0x7f058dfcee80,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,0,42622,0,0,64,0x7ffbc6c38e80,131072.0,131072.0,0.0,2578873.0,0.0,0.0,110870433.0,46321200.0,64,0x7f95719dce80,1587,0,0,1472291,1282,0,0,1415863,288,0,0,1182511,1621,0,0,1351688,1682,0,0,1407192,461,0,0,1208431,1221,0,0,1367569,558,0,0,1260881,84,0,0,1265717,2096,0,0,1477834,780,0,0,1300392,1208,0,0,1288552,2549,0,0,1496025,360,0,0,1226438,106,0,0,1204083,1240,0,0,1322501,1939,0,0,1462096,1070,0,0,1323580,3883,0,0,1741490,281,0,0,1239380,3452,0,0,1634218,1123,0,0,1342767,1687,0,0,1424085,5299,0,0,1821116,520,0,0,1281251,1734,0,0,1434000,538,0,0,1290480,2744,0,0,1436192,3165,0,0,1605515,2473,0,0,1422916,686,0,0,1273348,1085,0,0,1325885,64,0x7fc09c83ae80,0,3987132,2723,2723,0,3614234,2724,2724,0,3808201,2668,2668,0,4090592,2700,2700,0,4620001,2700,2700,0,4387121,2706,2706,0,4425462,2710,2710,0,3921929,2683,2683,0,4643223,2718,2718,0,4405461,2662,2662,0,4372191,2709,2709,0,4171829,2706,2706,0,4111816,2706,2706,0,3410281,2698,2698,0,4117683,2685,2685,0,3398868,2666,2666,0,4175916,2702,2702,0,4721285,2700,2700,0,3880295,2692,2692,0,4385728,2698,2698,0,4024065,2710,2710,0,4397129,2735,2735,0,5097854,2702,2702,0,4894068,2668,2668,0,3594147,2702,2702,0,4048021,2690,2690,0,3847356,2739,2739,0,3863081,2688,2688,0,3897153,2734,2734,0,3971540,2705,2705,0,3665471,2716,2716,0,3956343,2670,2670,194467450265772,194467450284492 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,SQ_INSTS_VSKIPPED,SQ_INSTS_SMEM,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_1,obj_1,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,wave_size_2,obj_2,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_3,obj_3,TCC_EA_ATOMIC_LEVEL_sum,wave_size_4,obj_4,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_5,obj_5,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,TCC_EA_RDREQ_DRAM_sum,wave_size_6,obj_6,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_7,obj_7,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,SQ_INSTS,SQ_WAIT_ANY,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_8,obj_8,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_9,obj_9,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,SQ_INSTS_SMEM_NORM,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,wave_size_10,obj_10,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_BUSY_CU_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,SQC_TC_DATA_WRITE_REQ,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_11,obj_11,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,SQC_ICACHE_MISSES_DUPLICATE,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_COALESCABLE_WAVEFRONT_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_12,obj_12,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_INSTS_VALU,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_WRREQ_IO_CREDIT_STALL_sum,TCC_EA_WRREQ_GMI_CREDIT_STALL_sum,TCC_EA_WRREQ_DRAM_CREDIT_STALL_sum,wave_size_13,obj_13,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_14,obj_14,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,SQ_WAVES_LT_32,SQ_WAVES_LT_16,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_EA_RDREQ_IO_CREDIT_STALL_sum,TCC_EA_RDREQ_GMI_CREDIT_STALL_sum,TCC_EA_RDREQ_DRAM_CREDIT_STALL_sum,TCC_TAG_STALL_sum,wave_size_15,obj_15,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,SQC_DCACHE_REQ_READ_1,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_16,obj_16,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f93318b0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,913,47948,0,131635.0,131072.0,0.0,131104.0,64,0x7f6520174ec0,131072.0,131072.0,0.0,2468054.0,0.0,0.0,130637271.0,62580356.0,64,0x7fc1bb190ec0,0,3758427,4096,4096,0,3798111,4096,4096,0,4569791,4096,4096,0,3045375,4096,4096,0,3438696,4096,4096,0,3286226,4096,4096,0,3554084,4096,4096,0,3187589,4096,4096,0,3387454,4096,4096,0,4526085,4096,4096,0,3850674,4096,4096,0,3458361,4096,4096,0,3896139,4096,4096,0,3263039,4096,4096,0,3306787,4096,4096,0,3260016,4096,4096,0,3852118,4096,4096,0,3826088,4096,4096,0,4085757,4096,4096,0,3440700,4096,4096,0,3292840,4096,4096,0,3815494,4096,4096,0,3363564,4096,4096,0,3503837,4096,4096,0,3452033,4096,4096,0,3889077,4096,4096,0,3527859,4096,4096,0,3408758,4096,4096,0,3899456,4096,4096,0,3503895,4096,4096,0,3478538,4096,4096,0,3321259,4096,4096,64,0x7f6563d10ec0,0.0,64,0x7fde430ccec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,141,8195,4240,8336,0,8192,4096,8192,0,8364,4268,8364,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,64,0x7fa3cf54cec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131340.0,0.0,528.0,131339.0,64,0x7ff0ae264ec0,8192,0,4096,8192,0,4096,8192,0,4096,8336,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9057c04ec0,32768,0,0,0,16384,16384,393216,20804030,960.0,513911.0,0.0,524288.0,1263996.0,32768.0,0,0,0,17962,131072.0,131072.0,0.0,131072.0,64,0x7f373b5a4ec0,3855,0,0,2007893,3979,0,0,2023914,1755,0,0,1773107,3831,0,0,2012186,2683,0,0,1891672,4489,0,0,2119634,2844,0,0,1945034,3629,0,0,2080366,2038,0,0,1846181,1363,0,0,1749187,1752,0,0,1747710,3025,0,0,1917495,2432,0,0,1936303,2466,0,0,1913736,1139,0,0,1733539,5649,0,0,2151887,3499,0,0,2084270,2308,0,0,1902496,821,0,0,1659360,4758,0,0,2009154,3225,0,0,1952555,5489,0,0,2206465,1243,0,0,1755009,6192,0,0,2143419,3103,0,0,1955316,530,0,0,1586926,2652,0,0,1928228,4650,0,0,1984375,5839,0,0,2171175,7417,0,0,2230052,1046,0,0,1740672,3823,0,0,1990735,64,0x7f28320acec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,87142.0,43930.0,131112.0,0.0,64,0x7f69c262cec0,395472,244656,3505482,16384,25459008,144,48,0,49433,49433,4022066.0,3134245.0,5432.0,1026242.0,2398244.0,0.0,3125141.0,2816478.0,393759,254586,49433,0,49433,0,1581856.0,1002365.0,0.0,0.0,64,0x7f548f7c0ec0,0,0,192,0,65536,64526,48,1339,31967,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,538,48104,1893,0,48.0,264.0,0.0,262288.0,64,0x7f66423c8ec0,2064881,360448,163840,0,0,180224,114688,0,71296906.0,198153096.0,77211339.0,131072.0,0.0,591550.0,0,0,26664,74413.0,0.0,0.0,74413.0,64,0x7faf88820ec0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,0,48575,0,0,64,0x7fe31868cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,30688.0,121747.0,64,0x7f991e830ec0,255719,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14494,30878,10106,588,0,47818,262603.0,0.0,188.0,262415.0,64,0x7f270f378ec0,4096,0,7729,0,4096,0,1029,0,4264,0,1568,0,4099,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,154,0,4096,0,0,0,4096,0,25,0,4096,0,224,0,4144,0,1035,0,4096,0,923,0,4096,0,455,0,4096,0,0,0,4096,0,23,0,4096,0,0,0,4096,0,3447,0,4096,0,528,0,4096,0,1204,0,4096,0,1733,0,4096,0,321,0,4096,0,23,0,4096,0,0,0,4096,0,0,0,4096,0,58,0,4096,0,2,0,4096,0,493,0,4096,0,0,0,4096,0,113,0,4096,0,0,0,4096,0,1529,0,1410078545959517,1410078545984317 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f93318b0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,4554,39422,0,131523.0,131072.0,0.0,86735.0,64,0x7f6520174ec0,131072.0,131072.0,0.0,2660010.0,0.0,0.0,108882266.0,47254132.0,64,0x7fc1bb190ec0,0,4064646,2746,2746,0,3931319,2716,2716,0,4125411,2686,2686,0,3850328,2698,2698,0,4147834,2706,2706,0,3512720,2728,2728,0,4809833,2687,2687,0,3625161,2714,2714,0,3751964,2698,2698,0,4802407,2700,2700,0,4299926,2722,2722,0,3576014,2712,2712,0,3610314,2730,2730,0,3749225,2688,2688,0,4119915,2706,2706,0,3674591,2693,2693,0,3771532,2718,2718,0,4001994,2710,2710,0,4144650,2708,2708,0,3775138,2719,2719,0,3644697,2710,2710,0,4319346,2721,2721,0,3890017,2693,2693,0,3385091,2706,2706,0,3488719,2694,2694,0,4096297,2684,2684,0,3903700,2720,2720,0,3253383,2718,2718,0,3869719,2700,2700,0,4090585,2696,2696,0,3336174,2718,2718,0,3632097,2728,2728,64,0x7f6563d10ec0,0.0,64,0x7fde430ccec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8361,4265,8361,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,64,0x7fa3cf54cec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131341.0,0.0,536.0,131340.0,64,0x7ff0ae264ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9057c04ec0,32768,0,0,0,16384,16384,393216,21896604,960.0,513935.0,0.0,524288.0,1236842.0,32768.0,0,0,0,13958,86546.0,86546.0,0.0,86546.0,64,0x7f373b5a4ec0,1360,0,0,1431224,1708,0,0,1366661,2032,0,0,1461214,3173,0,0,1580427,1508,0,0,1464623,19,0,0,1054571,6702,0,0,1921320,5155,0,0,1737278,2614,0,0,1600594,1054,0,0,1240503,1564,0,0,1509586,1580,0,0,1402223,327,0,0,1216362,450,0,0,1212336,3458,0,0,1626656,809,0,0,1322071,1314,0,0,1416180,206,0,0,1196756,4424,0,0,1770993,1345,0,0,1361095,696,0,0,1272579,435,0,0,1238605,7429,0,0,1921935,1621,0,0,1365859,2311,0,0,1486692,595,0,0,1341662,4653,0,0,1738557,1044,0,0,1352899,852,0,0,1337287,1078,0,0,1254085,2734,0,0,1609936,274,0,0,1315191,64,0x7f28320acec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86959.0,0.0,131112.0,0.0,64,0x7f69c262cec0,346256,235189,3376483,16384,24351024,0,48,0,43281,43281,3817346.0,3098319.0,6801.0,892874.0,2381845.0,0.0,3088893.0,2777860.0,346248,244971,43281,0,43281,0,1384992.0,842437.0,0.0,0.0,64,0x7f548f7c0ec0,0,0,48,0,65536,65536,0,0,30785,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,456,42783,1676,0,48.0,269.0,0.0,262144.0,64,0x7f66423c8ec0,3985618,360448,163840,0,0,180224,114688,0,62336305.0,168537726.0,81296325.0,131072.0,0.0,784607.0,0,0,29663,40804.0,0.0,0.0,40804.0,64,0x7faf88820ec0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,0,43932,0,0,64,0x7fe31868cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,41962.0,134156.0,64,0x7f991e830ec0,242669,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11393,27777,18697,6790,0,40589,262477.0,0.0,47.0,262430.0,64,0x7f270f378ec0,4096,0,1100,0,4096,0,3546,0,4264,0,1858,0,4096,0,2950,0,4097,0,2387,0,4097,0,352,0,4096,0,150,0,4096,0,2332,0,4096,0,3709,0,4096,0,2593,0,4096,0,5862,0,4144,0,1274,0,4096,0,1158,0,4096,0,1192,0,4096,0,1049,0,4098,0,1135,0,4096,0,3587,0,4096,0,4468,0,4096,0,2524,0,4096,0,437,0,4096,0,5730,0,4096,0,114,0,4096,0,575,0,4096,0,927,0,4096,0,3436,0,4096,0,3221,0,4096,0,2127,0,4097,0,247,0,4096,0,938,0,4096,0,2554,0,4096,0,107,0,4096,0,257,0,1410078546083997,1410078546102877 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,8,16,64,0x7f93318b0ec0,32768,0,16384,16384,32768,49152,0,65536,0.0,0.0,120.0,524288.0,0.0,0.0,0,0,2672,39629,0,131492.0,131072.0,0.0,86617.0,64,0x7f6520174ec0,131072.0,131072.0,0.0,2501838.0,0.0,0.0,124384310.0,48863827.0,64,0x7fc1bb190ec0,0,3655566,2746,2746,0,3657420,2727,2727,0,3319939,2676,2676,0,3582788,2708,2708,0,3611923,2712,2712,0,3665391,2715,2715,0,3746135,2689,2689,0,3579885,2692,2692,0,3625934,2718,2718,0,4673020,2708,2708,0,3543463,2696,2696,0,3545898,2714,2714,0,3563971,2760,2760,0,4312808,2699,2699,0,4192389,2688,2688,0,3894620,2726,2726,0,3807788,2690,2690,0,4022399,2691,2691,0,4079021,2702,2702,0,3500957,2714,2714,0,3772870,2708,2708,0,3637429,2748,2748,0,3827738,2681,2681,0,3753057,2684,2684,0,3851612,2697,2697,0,3620784,2700,2700,0,3476930,2712,2712,0,3717357,2706,2706,0,3519234,2740,2740,0,4062782,2745,2745,0,3421259,2701,2701,0,3138888,2721,2721,64,0x7f6563d10ec0,0.0,64,0x7fde430ccec0,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8371,4275,8371,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,47,8193,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8240,4144,8240,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8193,4097,8193,0,8192,4096,8192,0,8192,4096,8192,0,8192,4096,8192,0,8194,4098,8194,64,0x7fa3cf54cec0,32768,32768,16384,16384,65536,49152,11534336,65536,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131341.0,0.0,536.0,131340.0,64,0x7ff0ae264ec0,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,8192,0,4096,64,0x7f9057c04ec0,32768,0,0,0,16384,16384,393216,22259661,960.0,513939.0,0.0,524288.0,1244746.0,32768.0,0,0,0,13813,86724.0,86724.0,0.0,86724.0,64,0x7f373b5a4ec0,2109,0,0,1501443,2679,0,0,1434691,1021,0,0,1300124,1580,0,0,1362653,972,0,0,1308853,1323,0,0,1501215,3007,0,0,1525920,2335,0,0,1490745,669,0,0,1359012,3335,0,0,1651853,665,0,0,1215463,1791,0,0,1451151,1608,0,0,1387095,933,0,0,1327929,1741,0,0,1418966,892,0,0,1270453,1566,0,0,1406452,0,0,0,1197089,3239,0,0,1522909,1717,0,0,1332195,2516,0,0,1575566,1863,0,0,1476634,1755,0,0,1402685,2568,0,0,1613100,2684,0,0,1501581,3779,0,0,1619111,1687,0,0,1377061,3872,0,0,1614542,5418,0,0,1820403,1356,0,0,1395742,3544,0,0,1596771,1628,0,0,1419759,64,0x7f28320acec0,1048576,0,0,0,0,0,131072,0.0,0.0,0.0,0.0,16384,0,86797.0,0.0,131112.0,0.0,64,0x7f69c262cec0,346192,231394,3300937,16384,24251006,0,48,0,43273,43273,3760208.0,3025837.0,7589.0,798252.0,2357193.0,0.0,3016291.0,2705405.0,346184,240863,43273,0,43273,0,1384736.0,825227.0,0.0,0.0,64,0x7f548f7c0ec0,0,0,48,0,65536,65536,0,0,30772,0.0,0.0,0.0,32768.0,0.0,0.0,0.0,32768.0,4096,16384,458,42069,1684,0,48.0,269.0,0.0,262144.0,64,0x7f66423c8ec0,1858118,360448,163840,0,0,180224,114688,0,70715791.0,202374168.0,78271154.0,131072.0,0.0,585407.0,0,0,25357,63792.0,0.0,0.0,63792.0,64,0x7faf88820ec0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,0,43791,0,0,64,0x7fe31868cec0,0,0,0,16384,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,81920,0.0,0.0,34781.0,128833.0,64,0x7f991e830ec0,196245,0,0,65536,64048,48,1440,32768,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,14229,30613,8612,2551,0,41725,262462.0,0.0,47.0,262415.0,64,0x7f270f378ec0,4096,0,540,0,4096,0,1258,0,4264,0,7048,0,4096,0,0,0,4097,0,337,0,4097,0,3201,0,4096,0,743,0,4096,0,14,0,4096,0,62,0,4096,0,2031,0,4096,0,1842,0,4144,0,2247,0,4096,0,1764,0,4096,0,356,0,4096,0,1586,0,4098,0,0,0,4096,0,101,0,4096,0,1923,0,4096,0,1523,0,4096,0,728,0,4096,0,577,0,4096,0,3307,0,4096,0,1188,0,4096,0,24,0,4096,0,3986,0,4096,0,2067,0,4096,0,1024,0,4097,0,0,0,4096,0,0,0,4096,0,32,0,4096,0,589,0,4096,0,1371,0,1410078546122717,1410078546141597 diff --git a/tests/workloads/vcopy/MI100/sysinfo.csv b/tests/workloads/vcopy/MI100/sysinfo.csv index 5ee3f16f3e..4278075525 100644 --- a/tests/workloads/vcopy/MI100/sysinfo.csv +++ b/tests/workloads/vcopy/MI100/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -vcopy,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 07 Mar 2024 01:12:00 PM (CST),2,t008-007.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651100,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 +path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF,Thu 21 Mar 2024 03:52:12 PM (CDT),2,t007-001.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527651008,,6.0.2-115,113-D3431401-100,NA,NA,MI100,gfx908,16,8192,120,4,8,64,1024,40,1502,1200,1502,1200,32,32,64,4,1228.8,1 diff --git a/tests/workloads/vcopy/MI100/timestamps.csv b/tests/workloads/vcopy/MI100/timestamps.csv index e3a1e87f00..352aa23aa1 100644 --- a/tests/workloads/vcopy/MI100/timestamps.csv +++ b/tests/workloads/vcopy/MI100/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,230981,230981,1048576,256,0,0,8,8,16,64,0x0,0x7fe255228e80,194467450093848,194467450121772,194467450145932,194467450156146 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,230981,230981,1048576,256,0,0,8,8,16,64,0x0,0x7fe255228e80,194467450158591,194467450225612,194467450244652,194467450245996 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,230981,230981,1048576,256,0,0,8,8,16,64,0x0,0x7fe255228e80,194467450256566,194467450265772,194467450284492,194467450285701 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078545933634,1410078545959517,1410078545984317,1410078545996272 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078545996933,1410078546083997,1410078546102877,1410078546104276 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,1230104,1230104,1048576,256,0,0,8,8,16,64,0x0,0x7febef7c8ec0,1410078546114776,1410078546122717,1410078546141597,1410078546142898 diff --git a/tests/workloads/vcopy/MI200/SQ_IFETCH_LEVEL.csv b/tests/workloads/vcopy/MI200/SQ_IFETCH_LEVEL.csv index 792354df3a..d41441648f 100644 --- a/tests/workloads/vcopy/MI200/SQ_IFETCH_LEVEL.csv +++ b/tests/workloads/vcopy/MI200/SQ_IFETCH_LEVEL.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,SQ_WAVES,SQ_IFETCH,SQ_IFETCH_LEVEL,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,394525,394525,1048576,256,0,0,8,0,16,64,0x0,0x7fa4ce5d8ec0,27838,27838,16384,65536,13873,1562816,201223084080551,201235827806132,201235827826452,201223100419741 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,394525,394525,1048576,256,0,0,8,0,16,64,0x0,0x7fa4ce5d8ec0,43758,43758,16384,65536,9431,1049076,201223100447614,201235827928052,201235827944532,201223100743825 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,394525,394525,1048576,256,0,0,8,0,16,64,0x0,0x7fa4ce5d8ec0,43202,43202,16384,65536,9318,1048656,201223100777739,201235827965492,201235827981172,201223100935016 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,27003,27003,16384,65536,13592,1540604,1411538900424691,1411551767635712,1411551767656192,1411538916711551 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,41252,41252,16384,65536,9433,1048652,1411538916734635,1411551767749472,1411551767765792,1411538916994887 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106060,4106060,1048576,256,0,0,8,0,16,64,0x0,0x7fd0b9184ec0,40493,40493,16384,65536,9496,1048672,1411538917024403,1411551767786592,1411551767802112,1411538917176591 diff --git a/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_LDS.csv b/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_LDS.csv index 70534f13ba..a5fea0bc5d 100644 --- a/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_LDS.csv +++ b/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_LDS.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_LDS,SQ_INST_LEVEL_LDS,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,394726,394726,1048576,256,0,0,8,0,16,64,0x0,0x7f71bad4cec0,0,0,0,201223578546484,201235827806132,201235827826452,201223594436774 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,394726,394726,1048576,256,0,0,8,0,16,64,0x0,0x7f71bad4cec0,0,0,0,201223594455770,201235827928052,201235827944532,201223594741812 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,394726,394726,1048576,256,0,0,8,0,16,64,0x0,0x7f71bad4cec0,0,0,0,201223594768452,201235827965492,201235827981172,201223594920590 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539386407497,1411551767635712,1411551767656192,1411539402298088 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539402313307,1411551767749472,1411551767765792,1411539402615388 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106253,4106253,1048576,256,0,0,8,0,16,64,0x0,0x7f677cde8ec0,0,0,0,1411539402642058,1411551767786592,1411551767802112,1411539402793835 diff --git a/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_SMEM.csv b/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_SMEM.csv index 6f5ac15b31..09b6207ef4 100644 --- a/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_SMEM.csv +++ b/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_SMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_SMEM,SQ_INST_LEVEL_SMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,394926,394926,1048576,256,0,0,8,0,16,64,0x0,0x7f7fa4ff8ec0,65536,174914,19688440,201224059000608,201235827806132,201235827826452,201224075415201 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,394926,394926,1048576,256,0,0,8,0,16,64,0x0,0x7f7fa4ff8ec0,65536,226196,25391536,201224075434297,201235827928052,201235827944532,201224075721811 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,394926,394926,1048576,256,0,0,8,0,16,64,0x0,0x7f7fa4ff8ec0,65536,276632,30961680,201224075747951,201235827965492,201235827981172,201224075902052 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,172104,19399360,1411539868015720,1411551767635712,1411551767656192,1411539884298563 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,225136,25260328,1411539884315856,1411551767749472,1411551767765792,1411539884617747 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106436,4106436,1048576,256,0,0,8,0,16,64,0x0,0x7f5bb2338ec0,65536,237466,26615144,1411539884643485,1411551767786592,1411551767802112,1411539884796224 diff --git a/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_VMEM.csv b/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_VMEM.csv index 24f639e144..d7a0583ce1 100644 --- a/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_VMEM.csv +++ b/tests/workloads/vcopy/MI200/SQ_INST_LEVEL_VMEM.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,SQ_INSTS_VMEM,SQ_INST_LEVEL_VMEM,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,395127,395127,1048576,256,0,0,8,0,16,64,0x0,0x7f50d0fa0ec0,32768,297037,33270176,201224537996364,201235827806132,201235827826452,201224553873981 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,395127,395127,1048576,256,0,0,8,0,16,64,0x0,0x7f50d0fa0ec0,32768,590678,66162124,201224553881225,201235827928052,201235827944532,201224554174059 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,395127,395127,1048576,256,0,0,8,0,16,64,0x0,0x7f50d0fa0ec0,32768,605142,67778228,201224554200650,201235827965492,201235827981172,201224554370170 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,296920,33259784,1411540349957093,1411551767635712,1411551767656192,1411540365771640 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,589718,66068516,1411540365791388,1411551767749472,1411551767765792,1411540366061018 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106628,4106628,1048576,256,0,0,8,0,16,64,0x0,0x7f187a930ec0,32768,602871,67508252,1411540366087468,1411551767786592,1411551767802112,1411540366250446 diff --git a/tests/workloads/vcopy/MI200/SQ_LEVEL_WAVES.csv b/tests/workloads/vcopy/MI200/SQ_LEVEL_WAVES.csv index 92e061836b..9878ed357f 100644 --- a/tests/workloads/vcopy/MI200/SQ_LEVEL_WAVES.csv +++ b/tests/workloads/vcopy/MI200/SQ_LEVEL_WAVES.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,GRBM_COUNT,GRBM_GUI_ACTIVE,CPC_ME1_BUSY_FOR_PACKET_DECODE,SQ_CYCLES,SQ_WAVES,SQ_WAVE_CYCLES,SQ_BUSY_CYCLES,SQ_LEVEL_WAVES,SQ_ACCUM_PREV_HIRES,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int)",2,0,0,395328,395328,1048576,256,0,0,8,0,16,64,0x0,0x7f5550a20ec0,28360,28360,10795,226888,16384,11341934,135652,0,45873472,201225018076291,201235827806132,201235827826452,201225033694898 -1,"vecCopy(double*, double*, double*, int, int)",2,0,2,395328,395328,1048576,256,0,0,8,0,16,64,0x0,0x7f5550a20ec0,42168,42168,13512,337352,16384,20033994,228377,0,80612844,201225033723593,201235827928052,201235827944532,201225034015615 -2,"vecCopy(double*, double*, double*, int, int)",2,0,4,395328,395328,1048576,256,0,0,8,0,16,64,0x0,0x7f5550a20ec0,41562,41562,13893,332504,16384,19478377,224580,0,78423684,201225034051203,201235827965492,201235827981172,201225034227847 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,27964,27964,11091,223720,16384,11075620,130670,0,44799316,1411540838121846,1411551767635712,1411551767656192,1411540853905555 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,40878,40878,12739,327032,16384,19248292,223753,0,77475332,1411540853935701,1411551767749472,1411551767765792,1411540854159996 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4106830,4106830,1048576,256,0,0,8,0,16,64,0x0,0x7f0003c04ec0,40812,40812,13091,326504,16384,19800227,224876,0,79703012,1411540854195663,1411551767786592,1411551767802112,1411540854346158 diff --git a/tests/workloads/vcopy/MI200/log.txt b/tests/workloads/vcopy/MI200/log.txt new file mode 100644 index 0000000000..598b465e56 --- /dev/null +++ b/tests/workloads/vcopy/MI200/log.txt @@ -0,0 +1,739 @@ +Omniperf version: 2.0.0-RC1 +Profiler choice: rocprofv1 +Path: /home1/josantos/omniperf/tests/workloads/path/MI200 +Target: MI200 +Command: ./tests/vcopy -n 1048576 -b 256 -i 3 +Kernel Selection: None +Dispatch Selection: None +IP Blocks: All + +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +Collecting Performance Counters +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_IFETCH_LEVEL.txt + |-> [rocprof] RPL: on '240321_161646' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_IFETCH_LEVEL.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161646_4105900' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161646_4105900/input0_results_240321_161646' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161646_4105900/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 6 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161646_4105900/input0_results_240321_161646 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_IFETCH_LEVEL.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_LDS.txt + |-> [rocprof] RPL: on '240321_161647' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_LDS.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161647_4106093' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161647_4106093/input0_results_240321_161647' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161647_4106093/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161647_4106093/input0_results_240321_161647 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_LDS.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt + |-> [rocprof] RPL: on '240321_161647' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_SMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161647_4106276' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161647_4106276/input0_results_240321_161647' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161647_4106276/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161647_4106276/input0_results_240321_161647 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_SMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt + |-> [rocprof] RPL: on '240321_161648' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_INST_LEVEL_VMEM.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161648_4106468' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161648_4106468/input0_results_240321_161648' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161648_4106468/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161648_4106468/input0_results_240321_161648 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_INST_LEVEL_VMEM.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/SQ_LEVEL_WAVES.txt + |-> [rocprof] RPL: on '240321_161648' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/SQ_LEVEL_WAVES.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161648_4106670' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161648_4106670/input0_results_240321_161648' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161648_4106670/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 9 metrics + |-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161648_4106670/input0_results_240321_161648 + |-> [rocprof] File 'tests/workloads/path/MI200/SQ_LEVEL_WAVES.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_0.txt + |-> [rocprof] RPL: on '240321_161649' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_0.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161649_4106855' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161649_4106855/input0_results_240321_161649' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161649_4106855/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 28 metrics + |-> [rocprof] SQ_CYCLES, SQ_BUSY_CYCLES, SQ_WAVES, SQ_INSTS_VALU_CVT, SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, GRBM_COUNT, GRBM_GUI_ACTIVE, TCP_GATE_EN1_sum, TCP_GATE_EN2_sum, TCP_TD_TCP_STALL_CYCLES_sum, TCP_TCR_TCP_STALL_CYCLES_sum, TA_TA_BUSY_sum, TA_BUFFER_WAVEFRONTS_sum, TD_TD_BUSY_sum, TD_TC_STALL_sum, SPI_CSN_WINDOW_VALID, SPI_CSN_BUSY, CPC_CPC_STAT_BUSY, CPC_CPC_STAT_IDLE, CPF_CPF_STAT_BUSY, CPF_CPF_STAT_STALL, TCC_CYCLE_sum, TCC_BUSY_sum, TCC_PROBE_sum, TCC_PROBE_ALL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161649_4106855/input0_results_240321_161649 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_0.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_1.txt + |-> [rocprof] RPL: on '240321_161649' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_1.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161649_4107038' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161649_4107038/input0_results_240321_161649' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161649_4107038/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 27 metrics + |-> [rocprof] SQ_INSTS_VSKIPPED, SQ_INSTS, SQ_INSTS_VALU, SQ_INSTS_VALU_ADD_F16, SQ_INSTS_VALU_MUL_F16, SQ_INSTS_VALU_FMA_F16, SQ_INSTS_VALU_TRANS_F16, SQ_INSTS_VALU_ADD_F32, GRBM_SPI_BUSY, TCP_READ_TAGCONFLICT_STALL_CYCLES_sum, TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum, TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum, TCP_TA_TCP_STATE_READ_sum, TA_BUFFER_READ_WAVEFRONTS_sum, TA_BUFFER_WRITE_WAVEFRONTS_sum, TD_SPI_STALL_sum, TD_LOAD_WAVEFRONT_sum, SPI_CSN_NUM_THREADGROUPS, SPI_CSN_WAVE, CPC_CPC_TCIU_BUSY, CPC_CPC_TCIU_IDLE, CPF_CPF_TCIU_BUSY, CPF_CPF_TCIU_STALL, TCC_NC_REQ_sum, TCC_UC_REQ_sum, TCC_CC_REQ_sum, TCC_RW_REQ_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161649_4107038/input0_results_240321_161649 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_1.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_10.txt + |-> [rocprof] RPL: on '240321_161650' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_10.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161650_4107221' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161650_4107221/input0_results_240321_161650' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161650_4107221/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ, SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161650_4107221/input0_results_240321_161650 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_10.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_11.txt + |-> [rocprof] RPL: on '240321_161650' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_11.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161650_4107404' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161650_4107404/input0_results_240321_161650' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161650_4107404/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 8 metrics + |-> [rocprof] SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8, SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161650_4107404/input0_results_240321_161650 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_11.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_12.txt + |-> [rocprof] RPL: on '240321_161651' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_12.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161651_4107588' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161651_4107588/input0_results_240321_161651' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161651_4107588/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 3 metrics + |-> [rocprof] SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4 + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161651_4107588/input0_results_240321_161651 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_12.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_13.txt + |-> [rocprof] RPL: on '240321_161651' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_13.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161651_4107786' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161651_4107786/input0_results_240321_161651' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161651_4107786/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_ATOMIC[0], TCC_CYCLE[0], TCC_EA_ATOMIC[0], TCC_EA_ATOMIC_LEVEL[0], TCC_ATOMIC[1], TCC_CYCLE[1], TCC_EA_ATOMIC[1], TCC_EA_ATOMIC_LEVEL[1], TCC_ATOMIC[2], TCC_CYCLE[2], TCC_EA_ATOMIC[2], TCC_EA_ATOMIC_LEVEL[2], TCC_ATOMIC[3], TCC_CYCLE[3], TCC_EA_ATOMIC[3], TCC_EA_ATOMIC_LEVEL[3], TCC_ATOMIC[4], TCC_CYCLE[4], TCC_EA_ATOMIC[4], TCC_EA_ATOMIC_LEVEL[4], TCC_ATOMIC[5], TCC_CYCLE[5], TCC_EA_ATOMIC[5], TCC_EA_ATOMIC_LEVEL[5], TCC_ATOMIC[6], TCC_CYCLE[6], TCC_EA_ATOMIC[6], TCC_EA_ATOMIC_LEVEL[6], TCC_ATOMIC[7], TCC_CYCLE[7], TCC_EA_ATOMIC[7], TCC_EA_ATOMIC_LEVEL[7], TCC_ATOMIC[8], TCC_CYCLE[8], TCC_EA_ATOMIC[8], TCC_EA_ATOMIC_LEVEL[8], TCC_ATOMIC[9], TCC_CYCLE[9], TCC_EA_ATOMIC[9], TCC_EA_ATOMIC_LEVEL[9], TCC_ATOMIC[10], TCC_CYCLE[10], TCC_EA_ATOMIC[10], TCC_EA_ATOMIC_LEVEL[10], TCC_ATOMIC[11], TCC_CYCLE[11], TCC_EA_ATOMIC[11], TCC_EA_ATOMIC_LEVEL[11], TCC_ATOMIC[12], TCC_CYCLE[12], TCC_EA_ATOMIC[12], TCC_EA_ATOMIC_LEVEL[12], TCC_ATOMIC[13], TCC_CYCLE[13], TCC_EA_ATOMIC[13], TCC_EA_ATOMIC_LEVEL[13], TCC_ATOMIC[14], TCC_CYCLE[14], TCC_EA_ATOMIC[14], TCC_EA_ATOMIC_LEVEL[14], TCC_ATOMIC[15], TCC_CYCLE[15], TCC_EA_ATOMIC[15], TCC_EA_ATOMIC_LEVEL[15], TCC_ATOMIC[16], TCC_CYCLE[16], TCC_EA_ATOMIC[16], TCC_EA_ATOMIC_LEVEL[16], TCC_ATOMIC[17], TCC_CYCLE[17], TCC_EA_ATOMIC[17], TCC_EA_ATOMIC_LEVEL[17], TCC_ATOMIC[18], TCC_CYCLE[18], TCC_EA_ATOMIC[18], TCC_EA_ATOMIC_LEVEL[18], TCC_ATOMIC[19], TCC_CYCLE[19], TCC_EA_ATOMIC[19], TCC_EA_ATOMIC_LEVEL[19], TCC_ATOMIC[20], TCC_CYCLE[20], TCC_EA_ATOMIC[20], TCC_EA_ATOMIC_LEVEL[20], TCC_ATOMIC[21], TCC_CYCLE[21], TCC_EA_ATOMIC[21], TCC_EA_ATOMIC_LEVEL[21], TCC_ATOMIC[22], TCC_CYCLE[22], TCC_EA_ATOMIC[22], TCC_EA_ATOMIC_LEVEL[22], TCC_ATOMIC[23], TCC_CYCLE[23], TCC_EA_ATOMIC[23], TCC_EA_ATOMIC_LEVEL[23], TCC_ATOMIC[24], TCC_CYCLE[24], TCC_EA_ATOMIC[24], TCC_EA_ATOMIC_LEVEL[24], TCC_ATOMIC[25], TCC_CYCLE[25], TCC_EA_ATOMIC[25], TCC_EA_ATOMIC_LEVEL[25], TCC_ATOMIC[26], TCC_CYCLE[26], TCC_EA_ATOMIC[26], TCC_EA_ATOMIC_LEVEL[26], TCC_ATOMIC[27], TCC_CYCLE[27], TCC_EA_ATOMIC[27], TCC_EA_ATOMIC_LEVEL[27], TCC_ATOMIC[28], TCC_CYCLE[28], TCC_EA_ATOMIC[28], TCC_EA_ATOMIC_LEVEL[28], TCC_ATOMIC[29], TCC_CYCLE[29], TCC_EA_ATOMIC[29], TCC_EA_ATOMIC_LEVEL[29], TCC_ATOMIC[30], TCC_CYCLE[30], TCC_EA_ATOMIC[30], TCC_EA_ATOMIC_LEVEL[30], TCC_ATOMIC[31], TCC_CYCLE[31], TCC_EA_ATOMIC[31], TCC_EA_ATOMIC_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161651_4107786/input0_results_240321_161651 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_13.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_14.txt + |-> [rocprof] RPL: on '240321_161652' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_14.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161652_4107970' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161652_4107970/input0_results_240321_161652' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161652_4107970/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ[0], TCC_EA_RDREQ_32B[0], TCC_EA_RDREQ_DRAM_CREDIT_STALL[0], TCC_EA_RDREQ_GMI_CREDIT_STALL[0], TCC_EA_RDREQ[1], TCC_EA_RDREQ_32B[1], TCC_EA_RDREQ_DRAM_CREDIT_STALL[1], TCC_EA_RDREQ_GMI_CREDIT_STALL[1], TCC_EA_RDREQ[2], TCC_EA_RDREQ_32B[2], TCC_EA_RDREQ_DRAM_CREDIT_STALL[2], TCC_EA_RDREQ_GMI_CREDIT_STALL[2], TCC_EA_RDREQ[3], TCC_EA_RDREQ_32B[3], TCC_EA_RDREQ_DRAM_CREDIT_STALL[3], TCC_EA_RDREQ_GMI_CREDIT_STALL[3], TCC_EA_RDREQ[4], TCC_EA_RDREQ_32B[4], TCC_EA_RDREQ_DRAM_CREDIT_STALL[4], TCC_EA_RDREQ_GMI_CREDIT_STALL[4], TCC_EA_RDREQ[5], TCC_EA_RDREQ_32B[5], TCC_EA_RDREQ_DRAM_CREDIT_STALL[5], TCC_EA_RDREQ_GMI_CREDIT_STALL[5], TCC_EA_RDREQ[6], TCC_EA_RDREQ_32B[6], TCC_EA_RDREQ_DRAM_CREDIT_STALL[6], TCC_EA_RDREQ_GMI_CREDIT_STALL[6], TCC_EA_RDREQ[7], TCC_EA_RDREQ_32B[7], TCC_EA_RDREQ_DRAM_CREDIT_STALL[7], TCC_EA_RDREQ_GMI_CREDIT_STALL[7], TCC_EA_RDREQ[8], TCC_EA_RDREQ_32B[8], TCC_EA_RDREQ_DRAM_CREDIT_STALL[8], TCC_EA_RDREQ_GMI_CREDIT_STALL[8], TCC_EA_RDREQ[9], TCC_EA_RDREQ_32B[9], TCC_EA_RDREQ_DRAM_CREDIT_STALL[9], TCC_EA_RDREQ_GMI_CREDIT_STALL[9], TCC_EA_RDREQ[10], TCC_EA_RDREQ_32B[10], TCC_EA_RDREQ_DRAM_CREDIT_STALL[10], TCC_EA_RDREQ_GMI_CREDIT_STALL[10], TCC_EA_RDREQ[11], TCC_EA_RDREQ_32B[11], TCC_EA_RDREQ_DRAM_CREDIT_STALL[11], TCC_EA_RDREQ_GMI_CREDIT_STALL[11], TCC_EA_RDREQ[12], TCC_EA_RDREQ_32B[12], TCC_EA_RDREQ_DRAM_CREDIT_STALL[12], TCC_EA_RDREQ_GMI_CREDIT_STALL[12], TCC_EA_RDREQ[13], TCC_EA_RDREQ_32B[13], TCC_EA_RDREQ_DRAM_CREDIT_STALL[13], TCC_EA_RDREQ_GMI_CREDIT_STALL[13], TCC_EA_RDREQ[14], TCC_EA_RDREQ_32B[14], TCC_EA_RDREQ_DRAM_CREDIT_STALL[14], TCC_EA_RDREQ_GMI_CREDIT_STALL[14], TCC_EA_RDREQ[15], TCC_EA_RDREQ_32B[15], TCC_EA_RDREQ_DRAM_CREDIT_STALL[15], TCC_EA_RDREQ_GMI_CREDIT_STALL[15], TCC_EA_RDREQ[16], TCC_EA_RDREQ_32B[16], TCC_EA_RDREQ_DRAM_CREDIT_STALL[16], TCC_EA_RDREQ_GMI_CREDIT_STALL[16], TCC_EA_RDREQ[17], TCC_EA_RDREQ_32B[17], TCC_EA_RDREQ_DRAM_CREDIT_STALL[17], TCC_EA_RDREQ_GMI_CREDIT_STALL[17], TCC_EA_RDREQ[18], TCC_EA_RDREQ_32B[18], TCC_EA_RDREQ_DRAM_CREDIT_STALL[18], TCC_EA_RDREQ_GMI_CREDIT_STALL[18], TCC_EA_RDREQ[19], TCC_EA_RDREQ_32B[19], TCC_EA_RDREQ_DRAM_CREDIT_STALL[19], TCC_EA_RDREQ_GMI_CREDIT_STALL[19], TCC_EA_RDREQ[20], TCC_EA_RDREQ_32B[20], TCC_EA_RDREQ_DRAM_CREDIT_STALL[20], TCC_EA_RDREQ_GMI_CREDIT_STALL[20], TCC_EA_RDREQ[21], TCC_EA_RDREQ_32B[21], TCC_EA_RDREQ_DRAM_CREDIT_STALL[21], TCC_EA_RDREQ_GMI_CREDIT_STALL[21], TCC_EA_RDREQ[22], TCC_EA_RDREQ_32B[22], TCC_EA_RDREQ_DRAM_CREDIT_STALL[22], TCC_EA_RDREQ_GMI_CREDIT_STALL[22], TCC_EA_RDREQ[23], TCC_EA_RDREQ_32B[23], TCC_EA_RDREQ_DRAM_CREDIT_STALL[23], TCC_EA_RDREQ_GMI_CREDIT_STALL[23], TCC_EA_RDREQ[24], TCC_EA_RDREQ_32B[24], TCC_EA_RDREQ_DRAM_CREDIT_STALL[24], TCC_EA_RDREQ_GMI_CREDIT_STALL[24], TCC_EA_RDREQ[25], TCC_EA_RDREQ_32B[25], TCC_EA_RDREQ_DRAM_CREDIT_STALL[25], TCC_EA_RDREQ_GMI_CREDIT_STALL[25], TCC_EA_RDREQ[26], TCC_EA_RDREQ_32B[26], TCC_EA_RDREQ_DRAM_CREDIT_STALL[26], TCC_EA_RDREQ_GMI_CREDIT_STALL[26], TCC_EA_RDREQ[27], TCC_EA_RDREQ_32B[27], TCC_EA_RDREQ_DRAM_CREDIT_STALL[27], TCC_EA_RDREQ_GMI_CREDIT_STALL[27], TCC_EA_RDREQ[28], TCC_EA_RDREQ_32B[28], TCC_EA_RDREQ_DRAM_CREDIT_STALL[28], TCC_EA_RDREQ_GMI_CREDIT_STALL[28], TCC_EA_RDREQ[29], TCC_EA_RDREQ_32B[29], TCC_EA_RDREQ_DRAM_CREDIT_STALL[29], TCC_EA_RDREQ_GMI_CREDIT_STALL[29], TCC_EA_RDREQ[30], TCC_EA_RDREQ_32B[30], TCC_EA_RDREQ_DRAM_CREDIT_STALL[30], TCC_EA_RDREQ_GMI_CREDIT_STALL[30], TCC_EA_RDREQ[31], TCC_EA_RDREQ_32B[31], TCC_EA_RDREQ_DRAM_CREDIT_STALL[31], TCC_EA_RDREQ_GMI_CREDIT_STALL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161652_4107970/input0_results_240321_161652 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_14.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_15.txt + |-> [rocprof] RPL: on '240321_161652' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_15.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161652_4108161' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161652_4108161/input0_results_240321_161652' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161652_4108161/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_RDREQ_IO_CREDIT_STALL[0], TCC_EA_RDREQ_LEVEL[0], TCC_EA_WRREQ[0], TCC_EA_WRREQ_64B[0], TCC_EA_RDREQ_IO_CREDIT_STALL[1], TCC_EA_RDREQ_LEVEL[1], TCC_EA_WRREQ[1], TCC_EA_WRREQ_64B[1], TCC_EA_RDREQ_IO_CREDIT_STALL[2], TCC_EA_RDREQ_LEVEL[2], TCC_EA_WRREQ[2], TCC_EA_WRREQ_64B[2], TCC_EA_RDREQ_IO_CREDIT_STALL[3], TCC_EA_RDREQ_LEVEL[3], TCC_EA_WRREQ[3], TCC_EA_WRREQ_64B[3], TCC_EA_RDREQ_IO_CREDIT_STALL[4], TCC_EA_RDREQ_LEVEL[4], TCC_EA_WRREQ[4], TCC_EA_WRREQ_64B[4], TCC_EA_RDREQ_IO_CREDIT_STALL[5], TCC_EA_RDREQ_LEVEL[5], TCC_EA_WRREQ[5], TCC_EA_WRREQ_64B[5], TCC_EA_RDREQ_IO_CREDIT_STALL[6], TCC_EA_RDREQ_LEVEL[6], TCC_EA_WRREQ[6], TCC_EA_WRREQ_64B[6], TCC_EA_RDREQ_IO_CREDIT_STALL[7], TCC_EA_RDREQ_LEVEL[7], TCC_EA_WRREQ[7], TCC_EA_WRREQ_64B[7], TCC_EA_RDREQ_IO_CREDIT_STALL[8], TCC_EA_RDREQ_LEVEL[8], TCC_EA_WRREQ[8], TCC_EA_WRREQ_64B[8], TCC_EA_RDREQ_IO_CREDIT_STALL[9], TCC_EA_RDREQ_LEVEL[9], TCC_EA_WRREQ[9], TCC_EA_WRREQ_64B[9], TCC_EA_RDREQ_IO_CREDIT_STALL[10], TCC_EA_RDREQ_LEVEL[10], TCC_EA_WRREQ[10], TCC_EA_WRREQ_64B[10], TCC_EA_RDREQ_IO_CREDIT_STALL[11], TCC_EA_RDREQ_LEVEL[11], TCC_EA_WRREQ[11], TCC_EA_WRREQ_64B[11], TCC_EA_RDREQ_IO_CREDIT_STALL[12], TCC_EA_RDREQ_LEVEL[12], TCC_EA_WRREQ[12], TCC_EA_WRREQ_64B[12], TCC_EA_RDREQ_IO_CREDIT_STALL[13], TCC_EA_RDREQ_LEVEL[13], TCC_EA_WRREQ[13], TCC_EA_WRREQ_64B[13], TCC_EA_RDREQ_IO_CREDIT_STALL[14], TCC_EA_RDREQ_LEVEL[14], TCC_EA_WRREQ[14], TCC_EA_WRREQ_64B[14], TCC_EA_RDREQ_IO_CREDIT_STALL[15], TCC_EA_RDREQ_LEVEL[15], TCC_EA_WRREQ[15], TCC_EA_WRREQ_64B[15], TCC_EA_RDREQ_IO_CREDIT_STALL[16], TCC_EA_RDREQ_LEVEL[16], TCC_EA_WRREQ[16], TCC_EA_WRREQ_64B[16], TCC_EA_RDREQ_IO_CREDIT_STALL[17], TCC_EA_RDREQ_LEVEL[17], TCC_EA_WRREQ[17], TCC_EA_WRREQ_64B[17], TCC_EA_RDREQ_IO_CREDIT_STALL[18], TCC_EA_RDREQ_LEVEL[18], TCC_EA_WRREQ[18], TCC_EA_WRREQ_64B[18], TCC_EA_RDREQ_IO_CREDIT_STALL[19], TCC_EA_RDREQ_LEVEL[19], TCC_EA_WRREQ[19], TCC_EA_WRREQ_64B[19], TCC_EA_RDREQ_IO_CREDIT_STALL[20], TCC_EA_RDREQ_LEVEL[20], TCC_EA_WRREQ[20], TCC_EA_WRREQ_64B[20], TCC_EA_RDREQ_IO_CREDIT_STALL[21], TCC_EA_RDREQ_LEVEL[21], TCC_EA_WRREQ[21], TCC_EA_WRREQ_64B[21], TCC_EA_RDREQ_IO_CREDIT_STALL[22], TCC_EA_RDREQ_LEVEL[22], TCC_EA_WRREQ[22], TCC_EA_WRREQ_64B[22], TCC_EA_RDREQ_IO_CREDIT_STALL[23], TCC_EA_RDREQ_LEVEL[23], TCC_EA_WRREQ[23], TCC_EA_WRREQ_64B[23], TCC_EA_RDREQ_IO_CREDIT_STALL[24], TCC_EA_RDREQ_LEVEL[24], TCC_EA_WRREQ[24], TCC_EA_WRREQ_64B[24], TCC_EA_RDREQ_IO_CREDIT_STALL[25], TCC_EA_RDREQ_LEVEL[25], TCC_EA_WRREQ[25], TCC_EA_WRREQ_64B[25], TCC_EA_RDREQ_IO_CREDIT_STALL[26], TCC_EA_RDREQ_LEVEL[26], TCC_EA_WRREQ[26], TCC_EA_WRREQ_64B[26], TCC_EA_RDREQ_IO_CREDIT_STALL[27], TCC_EA_RDREQ_LEVEL[27], TCC_EA_WRREQ[27], TCC_EA_WRREQ_64B[27], TCC_EA_RDREQ_IO_CREDIT_STALL[28], TCC_EA_RDREQ_LEVEL[28], TCC_EA_WRREQ[28], TCC_EA_WRREQ_64B[28], TCC_EA_RDREQ_IO_CREDIT_STALL[29], TCC_EA_RDREQ_LEVEL[29], TCC_EA_WRREQ[29], TCC_EA_WRREQ_64B[29], TCC_EA_RDREQ_IO_CREDIT_STALL[30], TCC_EA_RDREQ_LEVEL[30], TCC_EA_WRREQ[30], TCC_EA_WRREQ_64B[30], TCC_EA_RDREQ_IO_CREDIT_STALL[31], TCC_EA_RDREQ_LEVEL[31], TCC_EA_WRREQ[31], TCC_EA_WRREQ_64B[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161652_4108161/input0_results_240321_161652 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_15.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_16.txt + |-> [rocprof] RPL: on '240321_161653' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_16.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161653_4108344' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161653_4108344/input0_results_240321_161653' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161653_4108344/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_EA_WRREQ_DRAM_CREDIT_STALL[0], TCC_EA_WRREQ_GMI_CREDIT_STALL[0], TCC_EA_WRREQ_IO_CREDIT_STALL[0], TCC_EA_WRREQ_LEVEL[0], TCC_EA_WRREQ_DRAM_CREDIT_STALL[1], TCC_EA_WRREQ_GMI_CREDIT_STALL[1], TCC_EA_WRREQ_IO_CREDIT_STALL[1], TCC_EA_WRREQ_LEVEL[1], TCC_EA_WRREQ_DRAM_CREDIT_STALL[2], TCC_EA_WRREQ_GMI_CREDIT_STALL[2], TCC_EA_WRREQ_IO_CREDIT_STALL[2], TCC_EA_WRREQ_LEVEL[2], TCC_EA_WRREQ_DRAM_CREDIT_STALL[3], TCC_EA_WRREQ_GMI_CREDIT_STALL[3], TCC_EA_WRREQ_IO_CREDIT_STALL[3], TCC_EA_WRREQ_LEVEL[3], TCC_EA_WRREQ_DRAM_CREDIT_STALL[4], TCC_EA_WRREQ_GMI_CREDIT_STALL[4], TCC_EA_WRREQ_IO_CREDIT_STALL[4], TCC_EA_WRREQ_LEVEL[4], TCC_EA_WRREQ_DRAM_CREDIT_STALL[5], TCC_EA_WRREQ_GMI_CREDIT_STALL[5], TCC_EA_WRREQ_IO_CREDIT_STALL[5], TCC_EA_WRREQ_LEVEL[5], TCC_EA_WRREQ_DRAM_CREDIT_STALL[6], TCC_EA_WRREQ_GMI_CREDIT_STALL[6], TCC_EA_WRREQ_IO_CREDIT_STALL[6], TCC_EA_WRREQ_LEVEL[6], TCC_EA_WRREQ_DRAM_CREDIT_STALL[7], TCC_EA_WRREQ_GMI_CREDIT_STALL[7], TCC_EA_WRREQ_IO_CREDIT_STALL[7], TCC_EA_WRREQ_LEVEL[7], TCC_EA_WRREQ_DRAM_CREDIT_STALL[8], TCC_EA_WRREQ_GMI_CREDIT_STALL[8], TCC_EA_WRREQ_IO_CREDIT_STALL[8], TCC_EA_WRREQ_LEVEL[8], TCC_EA_WRREQ_DRAM_CREDIT_STALL[9], TCC_EA_WRREQ_GMI_CREDIT_STALL[9], TCC_EA_WRREQ_IO_CREDIT_STALL[9], TCC_EA_WRREQ_LEVEL[9], TCC_EA_WRREQ_DRAM_CREDIT_STALL[10], TCC_EA_WRREQ_GMI_CREDIT_STALL[10], TCC_EA_WRREQ_IO_CREDIT_STALL[10], TCC_EA_WRREQ_LEVEL[10], TCC_EA_WRREQ_DRAM_CREDIT_STALL[11], TCC_EA_WRREQ_GMI_CREDIT_STALL[11], TCC_EA_WRREQ_IO_CREDIT_STALL[11], TCC_EA_WRREQ_LEVEL[11], TCC_EA_WRREQ_DRAM_CREDIT_STALL[12], TCC_EA_WRREQ_GMI_CREDIT_STALL[12], TCC_EA_WRREQ_IO_CREDIT_STALL[12], TCC_EA_WRREQ_LEVEL[12], TCC_EA_WRREQ_DRAM_CREDIT_STALL[13], TCC_EA_WRREQ_GMI_CREDIT_STALL[13], TCC_EA_WRREQ_IO_CREDIT_STALL[13], TCC_EA_WRREQ_LEVEL[13], TCC_EA_WRREQ_DRAM_CREDIT_STALL[14], TCC_EA_WRREQ_GMI_CREDIT_STALL[14], TCC_EA_WRREQ_IO_CREDIT_STALL[14], TCC_EA_WRREQ_LEVEL[14], TCC_EA_WRREQ_DRAM_CREDIT_STALL[15], TCC_EA_WRREQ_GMI_CREDIT_STALL[15], TCC_EA_WRREQ_IO_CREDIT_STALL[15], TCC_EA_WRREQ_LEVEL[15], TCC_EA_WRREQ_DRAM_CREDIT_STALL[16], TCC_EA_WRREQ_GMI_CREDIT_STALL[16], TCC_EA_WRREQ_IO_CREDIT_STALL[16], TCC_EA_WRREQ_LEVEL[16], TCC_EA_WRREQ_DRAM_CREDIT_STALL[17], TCC_EA_WRREQ_GMI_CREDIT_STALL[17], TCC_EA_WRREQ_IO_CREDIT_STALL[17], TCC_EA_WRREQ_LEVEL[17], TCC_EA_WRREQ_DRAM_CREDIT_STALL[18], TCC_EA_WRREQ_GMI_CREDIT_STALL[18], TCC_EA_WRREQ_IO_CREDIT_STALL[18], TCC_EA_WRREQ_LEVEL[18], TCC_EA_WRREQ_DRAM_CREDIT_STALL[19], TCC_EA_WRREQ_GMI_CREDIT_STALL[19], TCC_EA_WRREQ_IO_CREDIT_STALL[19], TCC_EA_WRREQ_LEVEL[19], TCC_EA_WRREQ_DRAM_CREDIT_STALL[20], TCC_EA_WRREQ_GMI_CREDIT_STALL[20], TCC_EA_WRREQ_IO_CREDIT_STALL[20], TCC_EA_WRREQ_LEVEL[20], TCC_EA_WRREQ_DRAM_CREDIT_STALL[21], TCC_EA_WRREQ_GMI_CREDIT_STALL[21], TCC_EA_WRREQ_IO_CREDIT_STALL[21], TCC_EA_WRREQ_LEVEL[21], TCC_EA_WRREQ_DRAM_CREDIT_STALL[22], TCC_EA_WRREQ_GMI_CREDIT_STALL[22], TCC_EA_WRREQ_IO_CREDIT_STALL[22], TCC_EA_WRREQ_LEVEL[22], TCC_EA_WRREQ_DRAM_CREDIT_STALL[23], TCC_EA_WRREQ_GMI_CREDIT_STALL[23], TCC_EA_WRREQ_IO_CREDIT_STALL[23], TCC_EA_WRREQ_LEVEL[23], TCC_EA_WRREQ_DRAM_CREDIT_STALL[24], TCC_EA_WRREQ_GMI_CREDIT_STALL[24], TCC_EA_WRREQ_IO_CREDIT_STALL[24], TCC_EA_WRREQ_LEVEL[24], TCC_EA_WRREQ_DRAM_CREDIT_STALL[25], TCC_EA_WRREQ_GMI_CREDIT_STALL[25], TCC_EA_WRREQ_IO_CREDIT_STALL[25], TCC_EA_WRREQ_LEVEL[25], TCC_EA_WRREQ_DRAM_CREDIT_STALL[26], TCC_EA_WRREQ_GMI_CREDIT_STALL[26], TCC_EA_WRREQ_IO_CREDIT_STALL[26], TCC_EA_WRREQ_LEVEL[26], TCC_EA_WRREQ_DRAM_CREDIT_STALL[27], TCC_EA_WRREQ_GMI_CREDIT_STALL[27], TCC_EA_WRREQ_IO_CREDIT_STALL[27], TCC_EA_WRREQ_LEVEL[27], TCC_EA_WRREQ_DRAM_CREDIT_STALL[28], TCC_EA_WRREQ_GMI_CREDIT_STALL[28], TCC_EA_WRREQ_IO_CREDIT_STALL[28], TCC_EA_WRREQ_LEVEL[28], TCC_EA_WRREQ_DRAM_CREDIT_STALL[29], TCC_EA_WRREQ_GMI_CREDIT_STALL[29], TCC_EA_WRREQ_IO_CREDIT_STALL[29], TCC_EA_WRREQ_LEVEL[29], TCC_EA_WRREQ_DRAM_CREDIT_STALL[30], TCC_EA_WRREQ_GMI_CREDIT_STALL[30], TCC_EA_WRREQ_IO_CREDIT_STALL[30], TCC_EA_WRREQ_LEVEL[30], TCC_EA_WRREQ_DRAM_CREDIT_STALL[31], TCC_EA_WRREQ_GMI_CREDIT_STALL[31], TCC_EA_WRREQ_IO_CREDIT_STALL[31], TCC_EA_WRREQ_LEVEL[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161653_4108344/input0_results_240321_161653 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_16.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_17.txt + |-> [rocprof] RPL: on '240321_161654' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_17.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161654_4108547' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161654_4108547/input0_results_240321_161654' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161654_4108547/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 128 metrics + |-> [rocprof] TCC_HIT[0], TCC_MISS[0], TCC_READ[0], TCC_REQ[0], TCC_HIT[1], TCC_MISS[1], TCC_READ[1], TCC_REQ[1], TCC_HIT[2], TCC_MISS[2], TCC_READ[2], TCC_REQ[2], TCC_HIT[3], TCC_MISS[3], TCC_READ[3], TCC_REQ[3], TCC_HIT[4], TCC_MISS[4], TCC_READ[4], TCC_REQ[4], TCC_HIT[5], TCC_MISS[5], TCC_READ[5], TCC_REQ[5], TCC_HIT[6], TCC_MISS[6], TCC_READ[6], TCC_REQ[6], TCC_HIT[7], TCC_MISS[7], TCC_READ[7], TCC_REQ[7], TCC_HIT[8], TCC_MISS[8], TCC_READ[8], TCC_REQ[8], TCC_HIT[9], TCC_MISS[9], TCC_READ[9], TCC_REQ[9], TCC_HIT[10], TCC_MISS[10], TCC_READ[10], TCC_REQ[10], TCC_HIT[11], TCC_MISS[11], TCC_READ[11], TCC_REQ[11], TCC_HIT[12], TCC_MISS[12], TCC_READ[12], TCC_REQ[12], TCC_HIT[13], TCC_MISS[13], TCC_READ[13], TCC_REQ[13], TCC_HIT[14], TCC_MISS[14], TCC_READ[14], TCC_REQ[14], TCC_HIT[15], TCC_MISS[15], TCC_READ[15], TCC_REQ[15], TCC_HIT[16], TCC_MISS[16], TCC_READ[16], TCC_REQ[16], TCC_HIT[17], TCC_MISS[17], TCC_READ[17], TCC_REQ[17], TCC_HIT[18], TCC_MISS[18], TCC_READ[18], TCC_REQ[18], TCC_HIT[19], TCC_MISS[19], TCC_READ[19], TCC_REQ[19], TCC_HIT[20], TCC_MISS[20], TCC_READ[20], TCC_REQ[20], TCC_HIT[21], TCC_MISS[21], TCC_READ[21], TCC_REQ[21], TCC_HIT[22], TCC_MISS[22], TCC_READ[22], TCC_REQ[22], TCC_HIT[23], TCC_MISS[23], TCC_READ[23], TCC_REQ[23], TCC_HIT[24], TCC_MISS[24], TCC_READ[24], TCC_REQ[24], TCC_HIT[25], TCC_MISS[25], TCC_READ[25], TCC_REQ[25], TCC_HIT[26], TCC_MISS[26], TCC_READ[26], TCC_REQ[26], TCC_HIT[27], TCC_MISS[27], TCC_READ[27], TCC_REQ[27], TCC_HIT[28], TCC_MISS[28], TCC_READ[28], TCC_REQ[28], TCC_HIT[29], TCC_MISS[29], TCC_READ[29], TCC_REQ[29], TCC_HIT[30], TCC_MISS[30], TCC_READ[30], TCC_REQ[30], TCC_HIT[31], TCC_MISS[31], TCC_READ[31], TCC_REQ[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161654_4108547/input0_results_240321_161654 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_17.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_18.txt + |-> [rocprof] RPL: on '240321_161655' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_18.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161655_4108730' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161655_4108730/input0_results_240321_161655' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161655_4108730/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 96 metrics + |-> [rocprof] TCC_RW_REQ[0], TCC_TOO_MANY_EA_WRREQS_STALL[0], TCC_WRITE[0], TCC_RW_REQ[1], TCC_TOO_MANY_EA_WRREQS_STALL[1], TCC_WRITE[1], TCC_RW_REQ[2], TCC_TOO_MANY_EA_WRREQS_STALL[2], TCC_WRITE[2], TCC_RW_REQ[3], TCC_TOO_MANY_EA_WRREQS_STALL[3], TCC_WRITE[3], TCC_RW_REQ[4], TCC_TOO_MANY_EA_WRREQS_STALL[4], TCC_WRITE[4], TCC_RW_REQ[5], TCC_TOO_MANY_EA_WRREQS_STALL[5], TCC_WRITE[5], TCC_RW_REQ[6], TCC_TOO_MANY_EA_WRREQS_STALL[6], TCC_WRITE[6], TCC_RW_REQ[7], TCC_TOO_MANY_EA_WRREQS_STALL[7], TCC_WRITE[7], TCC_RW_REQ[8], TCC_TOO_MANY_EA_WRREQS_STALL[8], TCC_WRITE[8], TCC_RW_REQ[9], TCC_TOO_MANY_EA_WRREQS_STALL[9], TCC_WRITE[9], TCC_RW_REQ[10], TCC_TOO_MANY_EA_WRREQS_STALL[10], TCC_WRITE[10], TCC_RW_REQ[11], TCC_TOO_MANY_EA_WRREQS_STALL[11], TCC_WRITE[11], TCC_RW_REQ[12], TCC_TOO_MANY_EA_WRREQS_STALL[12], TCC_WRITE[12], TCC_RW_REQ[13], TCC_TOO_MANY_EA_WRREQS_STALL[13], TCC_WRITE[13], TCC_RW_REQ[14], TCC_TOO_MANY_EA_WRREQS_STALL[14], TCC_WRITE[14], TCC_RW_REQ[15], TCC_TOO_MANY_EA_WRREQS_STALL[15], TCC_WRITE[15], TCC_RW_REQ[16], TCC_TOO_MANY_EA_WRREQS_STALL[16], TCC_WRITE[16], TCC_RW_REQ[17], TCC_TOO_MANY_EA_WRREQS_STALL[17], TCC_WRITE[17], TCC_RW_REQ[18], TCC_TOO_MANY_EA_WRREQS_STALL[18], TCC_WRITE[18], TCC_RW_REQ[19], TCC_TOO_MANY_EA_WRREQS_STALL[19], TCC_WRITE[19], TCC_RW_REQ[20], TCC_TOO_MANY_EA_WRREQS_STALL[20], TCC_WRITE[20], TCC_RW_REQ[21], TCC_TOO_MANY_EA_WRREQS_STALL[21], TCC_WRITE[21], TCC_RW_REQ[22], TCC_TOO_MANY_EA_WRREQS_STALL[22], TCC_WRITE[22], TCC_RW_REQ[23], TCC_TOO_MANY_EA_WRREQS_STALL[23], TCC_WRITE[23], TCC_RW_REQ[24], TCC_TOO_MANY_EA_WRREQS_STALL[24], TCC_WRITE[24], TCC_RW_REQ[25], TCC_TOO_MANY_EA_WRREQS_STALL[25], TCC_WRITE[25], TCC_RW_REQ[26], TCC_TOO_MANY_EA_WRREQS_STALL[26], TCC_WRITE[26], TCC_RW_REQ[27], TCC_TOO_MANY_EA_WRREQS_STALL[27], TCC_WRITE[27], TCC_RW_REQ[28], TCC_TOO_MANY_EA_WRREQS_STALL[28], TCC_WRITE[28], TCC_RW_REQ[29], TCC_TOO_MANY_EA_WRREQS_STALL[29], TCC_WRITE[29], TCC_RW_REQ[30], TCC_TOO_MANY_EA_WRREQS_STALL[30], TCC_WRITE[30], TCC_RW_REQ[31], TCC_TOO_MANY_EA_WRREQS_STALL[31], TCC_WRITE[31] + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161655_4108730/input0_results_240321_161655 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_18.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_2.txt + |-> [rocprof] RPL: on '240321_161655' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_2.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161655_4108920' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161655_4108920/input0_results_240321_161655' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161655_4108920/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 26 metrics + |-> [rocprof] SQ_INSTS_VALU_MUL_F32, SQ_INSTS_VALU_FMA_F32, SQ_INSTS_VALU_TRANS_F32, SQ_INSTS_VALU_ADD_F64, SQ_INSTS_VALU_MUL_F64, SQ_INSTS_VALU_FMA_F64, SQ_INSTS_VALU_TRANS_F64, SQ_INSTS_VALU_INT32, TCP_VOLATILE_sum, TCP_TOTAL_ACCESSES_sum, TCP_TOTAL_READ_sum, TCP_TOTAL_WRITE_sum, TA_BUFFER_ATOMIC_WAVEFRONTS_sum, TA_BUFFER_TOTAL_CYCLES_sum, TD_ATOMIC_WAVEFRONT_sum, TD_STORE_WAVEFRONT_sum, SPI_RA_REQ_NO_ALLOC, SPI_RA_REQ_NO_ALLOC_CSN, CPC_CPC_STAT_STALL, CPC_UTCL1_STALL_ON_TRANSLATION, CPF_CPF_STAT_IDLE, CPF_CPF_TCIU_IDLE, TCC_REQ_sum, TCC_STREAMING_REQ_sum, TCC_HIT_sum, TCC_MISS_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161655_4108920/input0_results_240321_161655 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_2.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_3.txt + |-> [rocprof] RPL: on '240321_161656' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_3.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161656_4109119' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161656_4109119/input0_results_240321_161656' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161656_4109119/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 24 metrics + |-> [rocprof] SQ_INSTS_VALU_INT64, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, TCP_TOTAL_ATOMIC_WITH_RET_sum, TCP_TOTAL_ATOMIC_WITHOUT_RET_sum, TCP_TOTAL_WRITEBACK_INVALIDATES_sum, TCP_TOTAL_CACHE_ACCESSES_sum, TA_BUFFER_COALESCED_READ_CYCLES_sum, TA_BUFFER_COALESCED_WRITE_CYCLES_sum, TD_COALESCABLE_WAVEFRONT_sum, SPI_RA_RES_STALL_CSN, SPI_RA_TMP_STALL_CSN, CPC_CPC_UTCL2IU_BUSY, CPC_CPC_UTCL2IU_IDLE, CPF_CMP_UTCL1_STALL_ON_TRANSLATION, TCC_READ_sum, TCC_WRITE_sum, TCC_ATOMIC_sum, TCC_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161656_4109119/input0_results_240321_161656 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_3.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_4.txt + |-> [rocprof] RPL: on '240321_161656' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_4.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161656_4109302' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161656_4109302/input0_results_240321_161656' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161656_4109302/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 22 metrics + |-> [rocprof] SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY, SQ_ACTIVE_INST_ANY, SQ_BUSY_CU_CYCLES, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU, TCP_UTCL1_TRANSLATION_MISS_sum, TCP_UTCL1_TRANSLATION_HIT_sum, TCP_UTCL1_PERMISSION_MISS_sum, TCP_UTCL1_REQUEST_sum, TA_ADDR_STALLED_BY_TC_CYCLES_sum, TA_TOTAL_WAVEFRONTS_sum, SPI_RA_WAVE_SIMD_FULL_CSN, SPI_RA_VGPR_SIMD_FULL_CSN, CPC_CPC_UTCL2IU_STALL, CPC_ME1_BUSY_FOR_PACKET_DECODE, TCC_EA_WRREQ_sum, TCC_EA_WRREQ_64B_sum, TCC_EA_WR_UNCACHED_32B_sum, TCC_EA_WRREQ_DRAM_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161656_4109302/input0_results_240321_161656 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_4.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_5.txt + |-> [rocprof] RPL: on '240321_161657' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_5.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161657_4109485' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161657_4109485/input0_results_240321_161657' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161657_4109485/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 21 metrics + |-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU, TCP_TCP_LATENCY_sum, TCP_TCC_READ_REQ_LATENCY_sum, TCP_TCC_WRITE_REQ_LATENCY_sum, TCP_TCC_READ_REQ_sum, TA_ADDR_STALLED_BY_TD_CYCLES_sum, TA_DATA_STALLED_BY_TC_CYCLES_sum, SPI_RA_SGPR_SIMD_FULL_CSN, SPI_RA_LDS_CU_FULL_CSN, CPC_ME1_DC0_SPI_BUSY, TCC_EA_WRREQ_STALL_sum, TCC_EA_RDREQ_sum, TCC_EA_RDREQ_32B_sum, TCC_EA_RD_UNCACHED_32B_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161657_4109485/input0_results_240321_161657 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_5.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_6.txt + |-> [rocprof] RPL: on '240321_161657' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_6.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161657_4109668' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161657_4109668/input0_results_240321_161657' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161657_4109668/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES_EQ_64, SQ_WAVES_LT_64, SQ_WAVES_LT_48, TCP_TCC_WRITE_REQ_sum, TCP_TCC_ATOMIC_WITH_RET_REQ_sum, TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum, TCP_TCC_NC_READ_REQ_sum, TA_FLAT_WAVEFRONTS_sum, TA_FLAT_READ_WAVEFRONTS_sum, SPI_RA_BAR_CU_FULL_CSN, SPI_RA_TGLIM_CU_FULL_CSN, TCC_EA_RDREQ_DRAM_sum, TCC_TAG_STALL_sum, TCC_NORMAL_WRITEBACK_sum, TCC_ALL_TC_OP_WB_WRITEBACK_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161657_4109668/input0_results_240321_161657 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_6.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_7.txt + |-> [rocprof] RPL: on '240321_161658' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_7.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161658_4109851' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161658_4109851/input0_results_240321_161658' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161658_4109851/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 20 metrics + |-> [rocprof] SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED, SQ_WAVES_SAVED, TCP_TCC_NC_WRITE_REQ_sum, TCP_TCC_NC_ATOMIC_REQ_sum, TCP_TCC_UC_READ_REQ_sum, TCP_TCC_UC_WRITE_REQ_sum, TA_FLAT_WRITE_WAVEFRONTS_sum, TA_FLAT_ATOMIC_WAVEFRONTS_sum, SPI_RA_WVLIM_STALL_CSN, SPI_SWC_CSC_WR, TCC_NORMAL_EVICT_sum, TCC_ALL_TC_OP_INV_EVICT_sum, TCC_TOO_MANY_EA_WRREQS_STALL_sum, TCC_EA_ATOMIC_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161658_4109851/input0_results_240321_161658 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_7.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_8.txt + |-> [rocprof] RPL: on '240321_161658' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_8.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161658_4110053' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161658_4110053/input0_results_240321_161658' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161658_4110053/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 17 metrics + |-> [rocprof] SQ_INSTS_SMEM_NORM, SQ_INSTS_MFMA, SQ_INSTS_VALU_MFMA_I8, SQ_INSTS_VALU_MFMA_F16, SQ_INSTS_VALU_MFMA_BF16, SQ_INSTS_VALU_MFMA_F32, SQ_INSTS_VALU_MFMA_F64, SQ_VALU_MFMA_BUSY_CYCLES, TCP_TCC_UC_ATOMIC_REQ_sum, TCP_TCC_CC_READ_REQ_sum, TCP_TCC_CC_WRITE_REQ_sum, TCP_TCC_CC_ATOMIC_REQ_sum, SPI_VWC_CSC_WR, SPI_RA_BULKY_CU_FULL_CSN, TCC_EA_RDREQ_LEVEL_sum, TCC_EA_WRREQ_LEVEL_sum, TCC_EA_ATOMIC_LEVEL_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161658_4110053/input0_results_240321_161658 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_8.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/pmc_perf_9.txt + |-> [rocprof] RPL: on '240321_161659' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/pmc_perf_9.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161659_4110244' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161659_4110244/input0_results_240321_161659' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161659_4110244/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 12 metrics + |-> [rocprof] SQ_INSTS_FLAT_LDS_ONLY, SQ_INSTS_VALU_MFMA_MOPS_I8, SQ_INSTS_VALU_MFMA_MOPS_F16, SQ_INSTS_VALU_MFMA_MOPS_BF16, SQ_INSTS_VALU_MFMA_MOPS_F32, SQ_INSTS_VALU_MFMA_MOPS_F64, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, TCP_TCC_RW_READ_REQ_sum, TCP_TCC_RW_WRITE_REQ_sum, TCP_TCC_RW_ATOMIC_REQ_sum, TCP_PENDING_STALL_CYCLES_sum + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161659_4110244/input0_results_240321_161659 + |-> [rocprof] File 'tests/workloads/path/MI200/pmc_perf_9.csv' is generating + |-> [rocprof] +[profiling] Current input file: tests/workloads/path/MI200/perfmon/timestamps.txt + |-> [rocprof] RPL: on '240321_161659' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf' + |-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""' + |-> [rocprof] RPL: input file 'tests/workloads/path/MI200/perfmon/timestamps.txt' + |-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_161659_4110431' + |-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_161659_4110431/input0_results_240321_161659' + |-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_161659_4110431/input0.xml" + |-> [rocprof] gpu_index = + |-> [rocprof] kernel = + |-> [rocprof] range = + |-> [rocprof] 0 metrics + |-> [rocprof] vcopy testing on GCD 0 + |-> [rocprof] Finished allocating vectors on the CPU + |-> [rocprof] Finished allocating vectors on the GPU + |-> [rocprof] Finished copying vectors to the GPU + |-> [rocprof] sw thinks it moved 1.000000 KB per wave + |-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384: + |-> [rocprof] Launching the kernel on the GPU + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished executing kernel + |-> [rocprof] Finished copying the output vector from the GPU to the CPU + |-> [rocprof] Releasing GPU memory + |-> [rocprof] Releasing CPU memory + |-> [rocprof] + |-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_161659_4110431/input0_results_240321_161659 + |-> [rocprof] File 'tests/workloads/path/MI200/timestamps.csv' is generating + |-> [rocprof] +[roofline] Checking for roofline.csv in tests/workloads/path/MI200 +[roofline] No roofline data found. Generating... diff --git a/tests/workloads/vcopy/MI200/pmc_dispatch_info.csv b/tests/workloads/vcopy/MI200/pmc_dispatch_info.csv index 963116dcd7..2166cd6fad 100644 --- a/tests/workloads/vcopy/MI200/pmc_dispatch_info.csv +++ b/tests/workloads/vcopy/MI200/pmc_dispatch_info.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID -0,"vecCopy(double*, double*, double*, int, int)",2 -1,"vecCopy(double*, double*, double*, int, int)",2 -2,"vecCopy(double*, double*, double*, int, int)",2 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2 diff --git a/tests/workloads/vcopy/MI200/pmc_perf.csv b/tests/workloads/vcopy/MI200/pmc_perf.csv index aa9ae43c4c..1c1f02b367 100644 --- a/tests/workloads/vcopy/MI200/pmc_perf.csv +++ b/tests/workloads/vcopy/MI200/pmc_perf.csv @@ -1,4 +1,4 @@ -Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_1,obj_1,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_2,obj_2,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_3,obj_3,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_4,obj_4,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_5,obj_5,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_6,obj_6,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_7,obj_7,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_8,obj_8,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_9,obj_9,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_10,obj_10,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,wave_size_11,obj_11,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_12,obj_12,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_13,obj_13,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_14,obj_14,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_15,obj_15,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_16,obj_16,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_17,obj_17,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_18,obj_18,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,Start_Timestamp,End_Timestamp -0,"vecCopy(double*, double*, double*, int, int)",2,1048576,256,0,0,8,0,16,64,0x7fb4a0edcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,11646,19146,8298,545,0,26572,204498.0,0.0,73418.0,131080.0,64,0x7eff96e3cec0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,22,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,45,0,4096,0,3,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,171,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,64,0x7f0162004ec0,2320,4096,2320,6416,2345,4096,2345,6441,2272,4096,2272,6368,2294,4096,2294,6390,2309,4096,2309,6405,2287,4096,2287,6383,2264,4096,2264,6360,2315,4096,2315,6411,2320,4096,2320,6416,2322,4096,2322,6418,2349,4096,2349,6445,2326,4097,2327,6423,2291,4096,2291,6387,2309,4096,2309,6405,2288,4099,2291,6387,2266,4096,2266,6362,2322,4096,2322,6418,2254,4096,2254,6350,2305,4097,2306,6402,2298,4096,2298,6394,2258,4096,2258,6354,2300,4096,2300,6396,2282,4096,2282,6378,2450,4098,2452,6548,2284,4100,2288,6384,2322,4096,2322,6418,2253,4096,2253,6349,2309,4096,2309,6405,2300,4096,2300,6396,2258,4096,2258,6354,2304,4096,2304,6400,2281,4096,2281,6377,64,0x7fb16d318ec0,0,0,0,224,0,65536,64202,56,64,0x7fcabad68ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10669,0,814,28255,0,73286.0,131072.0,0.0,65568.0,64,0x7fac465a8ec0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,0,27952,0,0,64,0x7f36fb5d0ec0,1287,116534,0,0,65536,63800,56,1680,64,0x7f3fef764ec0,0,0,0,968773,0,0,0,1046379,0,0,0,931859,0,0,0,1088169,0,0,0,1036146,0,0,0,1100520,0,0,0,1111087,0,0,0,1180116,0,0,0,1066428,0,0,0,1068040,0,0,0,1037208,0,0,0,1045516,0,0,0,1073318,0,0,0,1056088,0,0,0,1061344,0,0,0,1146401,0,0,0,1034076,0,0,0,1181387,0,0,0,1030210,0,0,0,1133433,0,0,0,1040324,0,0,0,1142502,0,0,0,1128877,0,0,0,1205328,0,0,0,1024096,0,0,0,1048953,0,0,0,1181364,0,0,0,1202599,0,0,0,1082919,0,0,0,1036674,0,0,0,1001608,0,0,0,1090962,64,0x7f9ffe368ec0,114688,0,32768,32768,16384,16384,65536,49152,28118176.0,88521205.0,38473704.0,131072.0,0.0,196049.0,0,0,14850,118.0,131079.0,0.0,6.0,64,0x7f5708c48ec0,0,1166932,4096,4096,0,1395985,4096,4096,0,1025976,4096,4096,0,1255026,4096,4096,0,1302678,4096,4096,0,1581533,4096,4096,0,1143995,4096,4096,0,1242918,4096,4096,0,1119435,4096,4096,0,1248616,4096,4096,0,1370894,4096,4096,0,1105956,4096,4096,0,1249602,4096,4096,0,1170709,4096,4096,0,1237850,4096,4096,0,1132896,4096,4096,0,1104076,4096,4096,0,1245774,4096,4096,0,1127630,4096,4096,0,1353599,4096,4096,0,1283692,4096,4096,0,1288768,4096,4096,0,1253996,4096,4096,0,1391761,4096,4096,0,1557423,4096,4096,0,1161668,4096,4096,0,1128015,4096,4096,0,1428921,4096,4096,0,1179511,4096,4096,0,1281523,4096,4096,0,1205520,4096,4096,0,1386321,4096,4096,64,0x7f8089254ec0,32768,32768,0,64,0x7f2f67c48ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,41170710.0,34395870.0,0.0,64,0x7f9f3d44cec0,239328,136518,16384,0,16384,16384,32768,49152,29915,29915,2052445.0,1417612.0,3362.0,165528.0,1117569.0,0.0,1409937.0,1111787.0,237617,144656,29915,0,29915,0,957280.0,500995.0,0.0,0.0,64,0x7f6ee9174ec0,0,393216,163840,0,0,0,0,0,17406,0.0,0.0,0.0,32768.0,0.0,0.0,431.0,32768.0,4096,16384,352,27738,2024,0,56.0,6.0,0.0,204310.0,64,0x7fef1254cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f52ec2c0ec0,6379,0,4096,6372,0,4096,6371,0,4096,6406,0,4096,6332,0,4096,6420,0,4096,6348,0,4096,6363,0,4096,6366,0,4096,6384,0,4096,6377,0,4096,6370,0,4096,6407,0,4096,6338,0,4096,6423,0,4096,6349,0,4096,6370,0,4096,6372,0,4096,6359,0,4096,6405,0,4096,6374,0,4096,6378,0,4096,6359,0,4096,6560,0,4096,6392,0,4096,6378,0,4096,6375,0,4096,6361,0,4096,6406,0,4096,6373,0,4096,6379,0,4096,6366,0,4096,64,0x7f6882364ec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,973539.0,64,0x7fd881b0cec0,11205498,10059337,802097,344064,1675022,0,0,163840,832.0,515136.0,0.0,524288.0,341376.0,32768.0,516908,0,0,11466,131072.0,131072.0,0.0,131072.0,64,0x7fc179a3cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,34316.0,46130.0,19406.0,201235827806132,201235827826452 -1,"vecCopy(double*, double*, double*, int, int)",2,1048576,256,0,0,8,0,16,64,0x7fb4a0edcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,28647,25773,9780,2869,0,38710,200276.0,0.0,69192.0,131084.0,64,0x7eff96e3cec0,4096,0,2002,0,4096,0,669,0,4096,0,276,0,4096,0,2494,0,4097,0,358,0,4096,0,1762,0,4096,0,1117,0,4096,0,1084,0,4096,0,305,0,4096,0,991,0,4096,0,1264,0,4096,0,504,0,4096,0,376,0,4097,0,594,0,4096,0,250,0,4096,0,1054,0,4096,0,422,0,4096,0,746,0,4098,0,770,0,4098,0,587,0,4096,0,624,0,4096,0,606,0,4096,0,414,0,4096,0,1195,0,4096,0,389,0,4096,0,1706,0,4096,0,194,0,4096,0,432,0,4096,0,538,0,4096,0,485,0,4097,0,82,0,4097,0,340,0,64,0x7f0162004ec0,2162,4096,2162,6258,2177,4096,2177,6273,2136,4096,2136,6232,2161,4096,2161,6257,2166,4096,2166,6262,2166,4096,2166,6262,2151,4096,2151,6247,2180,4096,2180,6276,2182,4096,2182,6278,2161,4096,2161,6257,2185,4096,2185,6281,2191,4098,2193,6289,2159,4096,2159,6255,2167,4096,2167,6263,2166,4098,2168,6264,2147,4096,2147,6243,2142,4096,2142,6238,2166,4096,2166,6262,2174,4097,2175,6271,2158,4096,2158,6254,2164,4096,2164,6260,2171,4096,2171,6267,2160,4096,2160,6256,2168,4096,2168,6264,2170,4100,2174,6270,2142,4096,2142,6238,2168,4096,2168,6264,2182,4097,2183,6279,2159,4096,2159,6255,2170,4098,2172,6268,2173,4096,2173,6269,2162,4096,2162,6258,64,0x7fb16d318ec0,0,0,0,56,0,65536,65536,0,64,0x7fcabad68ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21647,0,2589,38939,0,69469.0,131072.0,0.0,45585.0,64,0x7fac465a8ec0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,0,41623,0,0,64,0x7f36fb5d0ec0,0,182515,0,0,65536,63800,56,1680,64,0x7f3fef764ec0,0,0,0,1660122,573,0,0,2449079,0,0,0,1488363,9,0,0,1994224,108,0,0,2035613,161,0,0,2020162,354,0,0,1748750,158,0,0,1884247,0,0,0,1581844,0,0,0,1638587,0,0,0,1810117,0,0,0,1643714,142,0,0,1833208,131,0,0,2098519,130,0,0,2005959,246,0,0,1631836,0,0,0,1376071,0,0,0,1792830,221,0,0,1868278,496,0,0,2009394,0,0,0,1891337,558,0,0,2183458,55,0,0,1739207,32,0,0,2069047,0,0,0,1517524,0,0,0,1515978,0,0,0,1574496,0,0,0,1626672,0,0,0,1785863,0,0,0,1767504,578,0,0,2013700,0,0,0,1859679,64,0x7f9ffe368ec0,114688,0,32768,32768,16384,16384,65536,49152,58397920.0,193362197.0,45260427.0,131072.0,0.0,546544.0,0,0,24891,779.0,131080.0,0.0,14.0,64,0x7f5708c48ec0,0,4329966,2848,2848,0,4247951,2872,2872,0,3472990,2830,2830,0,4219262,2852,2852,0,3926380,2880,2880,0,3719899,2820,2820,0,3253574,2860,2860,0,4278446,2832,2832,0,4279566,2824,2824,0,3475039,2864,2864,0,3514198,2872,2872,0,3615281,2830,2830,0,3419570,2848,2848,0,3366545,2880,2880,0,3281020,2820,2820,0,3499537,2864,2864,0,3359148,2832,2832,0,4377177,2852,2852,0,3674939,2868,2868,0,4300609,2860,2860,0,4336756,2816,2816,0,4236263,2866,2866,0,3424635,2792,2792,0,3744931,2816,2816,0,3154486,2820,2820,0,3400763,2832,2832,0,3521101,2842,2842,0,3742326,2868,2868,0,3969013,2856,2856,0,3433936,2820,2820,0,3542462,2864,2864,0,3822272,2796,2796,64,0x7f8089254ec0,32768,32768,0,64,0x7f2f67c48ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,124608928.0,63942657.0,0.0,64,0x7f9f3d44cec0,326288,218374,16384,0,16384,16384,32768,49152,40785,40785,3112096.0,2427093.0,4536.0,328742.0,1669080.0,0.0,2415427.0,2106949.0,326280,226999,40785,0,40785,0,1305120.0,768752.0,0.0,0.0,64,0x7f6ee9174ec0,0,393216,163840,0,0,0,0,0,29614,0.0,0.0,0.0,32768.0,0.0,0.0,208.0,32768.0,4096,16384,302,40788,2108,0,56.0,10.0,0.0,200851.0,64,0x7fef1254cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f52ec2c0ec0,6256,0,4096,6302,0,4096,6273,0,4096,6285,0,4096,6256,0,4096,6249,0,4096,6271,0,4096,6239,0,4096,6245,0,4096,6253,0,4096,6311,0,4096,6270,0,4096,6285,0,4096,6260,0,4096,6245,0,4096,6269,0,4096,6235,0,4096,6272,0,4096,6279,0,4096,6252,0,4096,6265,0,4096,6295,0,4096,6262,0,4096,6261,0,4096,6264,0,4096,6234,0,4096,6273,0,4096,6280,0,4096,6255,0,4096,6268,0,4096,6293,0,4096,6258,0,4096,64,0x7f6882364ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2024050.0,64,0x7fd881b0cec0,18487458,17752805,390589,344064,2664681,0,0,163840,0.0,524288.0,0.0,524288.0,474859.0,32768.0,851710,0,0,11774,90906.0,90906.0,0.0,90906.0,64,0x7fc179a3cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,98996.0,45724.0,0.0,201235827928052,201235827944532 -2,"vecCopy(double*, double*, double*, int, int)",2,1048576,256,0,0,8,0,16,64,0x7fb4a0edcec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,28105,26731,9813,2874,0,38408,200649.0,0.0,69566.0,131083.0,64,0x7eff96e3cec0,4096,0,2613,0,4096,0,198,0,4096,0,793,0,4096,0,1360,0,4097,0,203,0,4096,0,7,0,4096,0,0,0,4096,0,221,0,4096,0,57,0,4096,0,56,0,4096,0,1,0,4096,0,2,0,4096,0,222,0,4097,0,45,0,4096,0,4,0,4096,0,58,0,4096,0,804,0,4096,0,25,0,4098,0,82,0,4098,0,997,0,4096,0,1151,0,4096,0,494,0,4096,0,500,0,4096,0,1158,0,4096,0,285,0,4096,0,274,0,4096,0,33,0,4096,0,431,0,4096,0,413,0,4096,0,284,0,4097,0,42,0,4097,0,912,0,64,0x7f0162004ec0,2121,4096,2121,6217,2171,4096,2171,6267,2142,4096,2142,6238,2174,4096,2174,6270,2154,4096,2154,6250,2182,4096,2182,6278,2185,4096,2185,6281,2169,4096,2169,6265,2168,4096,2168,6264,2120,4096,2120,6216,2175,4096,2175,6271,2197,4098,2199,6295,2174,4096,2174,6270,2155,4096,2155,6251,2181,4099,2184,6280,2188,4096,2188,6284,2164,4096,2164,6260,2209,4096,2209,6305,2182,4097,2183,6279,2183,4096,2183,6279,2197,4096,2197,6293,2161,4096,2161,6257,2162,4096,2162,6258,2162,4096,2162,6258,2165,4100,2169,6265,2167,4096,2167,6263,2207,4096,2207,6303,2195,4097,2196,6292,2180,4096,2180,6276,2196,4098,2198,6294,2161,4096,2161,6257,2167,4096,2167,6263,64,0x7fb16d318ec0,0,0,0,56,0,65536,65536,0,64,0x7fcabad68ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20720,0,3300,38545,0,69910.0,131072.0,0.0,45584.0,64,0x7fac465a8ec0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,0,42020,0,0,64,0x7f36fb5d0ec0,0,187148,0,0,65536,63800,56,1680,64,0x7f3fef764ec0,0,0,0,1652263,55,0,0,1967138,0,0,0,1670660,0,0,0,1770464,1023,0,0,2295800,803,0,0,2245974,0,0,0,1512910,0,0,0,1979017,0,0,0,1740158,0,0,0,1653137,1467,0,0,2738319,0,0,0,1565175,0,0,0,1550835,0,0,0,1666165,517,0,0,2064308,0,0,0,2070251,292,0,0,1838701,459,0,0,2130508,0,0,0,2022279,0,0,0,2090017,249,0,0,2005093,0,0,0,1934006,55,0,0,1994453,0,0,0,1868225,0,0,0,1740126,0,0,0,1580346,0,0,0,1743591,46,0,0,2113293,335,0,0,2333628,0,0,0,1675146,0,0,0,1770632,28,0,0,1914787,64,0x7f9ffe368ec0,114688,0,32768,32768,16384,16384,65536,49152,59763562.0,194651549.0,51407335.0,131072.0,0.0,503363.0,0,0,25278,4347.0,131080.0,0.0,14.0,64,0x7f5708c48ec0,0,4076183,2832,2832,0,5357660,2868,2868,0,3594543,2844,2844,0,3772097,2844,2844,0,3656203,2916,2916,0,3169184,2880,2880,0,2934011,2868,2868,0,3618595,2840,2840,0,3711725,2840,2840,0,3696731,2836,2836,0,4028595,2868,2868,0,3796692,2844,2844,0,3450697,2848,2848,0,4209391,2920,2920,0,2968842,2880,2880,0,2953732,2864,2864,0,3295249,2824,2824,0,3122354,2856,2856,0,3468466,2844,2844,0,4314470,2840,2840,0,3794132,2816,2816,0,4021208,2850,2850,0,2543429,2880,2880,0,3774927,2852,2852,0,4139829,2856,2856,0,3165971,2824,2824,0,2931919,2852,2852,0,5146190,2846,2846,0,3291705,2840,2840,0,3063762,2820,2820,0,3399880,2848,2848,0,3771066,2880,2880,64,0x7f8089254ec0,32768,32768,0,64,0x7f2f67c48ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,121254673.0,64899367.0,0.0,64,0x7f9f3d44cec0,341568,225876,16384,0,16384,16384,32768,49152,42695,42695,3210997.0,2530783.0,4952.0,343112.0,1686355.0,0.0,2518209.0,2209372.0,341560,234753,42695,0,42695,0,1366240.0,777985.0,0.0,0.0,64,0x7f6ee9174ec0,0,393216,163840,0,0,0,0,0,28942,0.0,0.0,0.0,32768.0,0.0,0.0,248.0,32768.0,4096,16384,302,40066,1989,0,56.0,10.0,0.0,200581.0,64,0x7fef1254cec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f52ec2c0ec0,6274,0,4096,6272,0,4096,6258,0,4096,6283,0,4096,6236,0,4096,6249,0,4096,6254,0,4096,6291,0,4096,6296,0,4096,6279,0,4096,6275,0,4096,6256,0,4096,6280,0,4096,6245,0,4096,6253,0,4096,6254,0,4096,6260,0,4096,6275,0,4096,6279,0,4096,6275,0,4096,6260,0,4096,6285,0,4096,6232,0,4096,6276,0,4096,6279,0,4096,6257,0,4096,6274,0,4096,6279,0,4096,6275,0,4096,6261,0,4096,6293,0,4096,6239,0,4096,64,0x7f6882364ec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2142962.0,64,0x7fd881b0cec0,19373759,18004819,1024876,344064,2794491,0,0,163840,832.0,515136.0,0.0,524288.0,729590.0,32768.0,963405,0,0,13505,91316.0,91316.0,0.0,91316.0,64,0x7fc179a3cec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131082.0,104521.0,45652.0,0.0,201235827965492,201235827981172 +Dispatch_ID,Kernel_Name,GPU_ID,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,obj,TCC_EA_RDREQ_IO_CREDIT_STALL[0],TCC_EA_RDREQ_LEVEL[0],TCC_EA_WRREQ[0],TCC_EA_WRREQ_64B[0],TCC_EA_RDREQ_IO_CREDIT_STALL[1],TCC_EA_RDREQ_LEVEL[1],TCC_EA_WRREQ[1],TCC_EA_WRREQ_64B[1],TCC_EA_RDREQ_IO_CREDIT_STALL[2],TCC_EA_RDREQ_LEVEL[2],TCC_EA_WRREQ[2],TCC_EA_WRREQ_64B[2],TCC_EA_RDREQ_IO_CREDIT_STALL[3],TCC_EA_RDREQ_LEVEL[3],TCC_EA_WRREQ[3],TCC_EA_WRREQ_64B[3],TCC_EA_RDREQ_IO_CREDIT_STALL[4],TCC_EA_RDREQ_LEVEL[4],TCC_EA_WRREQ[4],TCC_EA_WRREQ_64B[4],TCC_EA_RDREQ_IO_CREDIT_STALL[5],TCC_EA_RDREQ_LEVEL[5],TCC_EA_WRREQ[5],TCC_EA_WRREQ_64B[5],TCC_EA_RDREQ_IO_CREDIT_STALL[6],TCC_EA_RDREQ_LEVEL[6],TCC_EA_WRREQ[6],TCC_EA_WRREQ_64B[6],TCC_EA_RDREQ_IO_CREDIT_STALL[7],TCC_EA_RDREQ_LEVEL[7],TCC_EA_WRREQ[7],TCC_EA_WRREQ_64B[7],TCC_EA_RDREQ_IO_CREDIT_STALL[8],TCC_EA_RDREQ_LEVEL[8],TCC_EA_WRREQ[8],TCC_EA_WRREQ_64B[8],TCC_EA_RDREQ_IO_CREDIT_STALL[9],TCC_EA_RDREQ_LEVEL[9],TCC_EA_WRREQ[9],TCC_EA_WRREQ_64B[9],TCC_EA_RDREQ_IO_CREDIT_STALL[10],TCC_EA_RDREQ_LEVEL[10],TCC_EA_WRREQ[10],TCC_EA_WRREQ_64B[10],TCC_EA_RDREQ_IO_CREDIT_STALL[11],TCC_EA_RDREQ_LEVEL[11],TCC_EA_WRREQ[11],TCC_EA_WRREQ_64B[11],TCC_EA_RDREQ_IO_CREDIT_STALL[12],TCC_EA_RDREQ_LEVEL[12],TCC_EA_WRREQ[12],TCC_EA_WRREQ_64B[12],TCC_EA_RDREQ_IO_CREDIT_STALL[13],TCC_EA_RDREQ_LEVEL[13],TCC_EA_WRREQ[13],TCC_EA_WRREQ_64B[13],TCC_EA_RDREQ_IO_CREDIT_STALL[14],TCC_EA_RDREQ_LEVEL[14],TCC_EA_WRREQ[14],TCC_EA_WRREQ_64B[14],TCC_EA_RDREQ_IO_CREDIT_STALL[15],TCC_EA_RDREQ_LEVEL[15],TCC_EA_WRREQ[15],TCC_EA_WRREQ_64B[15],TCC_EA_RDREQ_IO_CREDIT_STALL[16],TCC_EA_RDREQ_LEVEL[16],TCC_EA_WRREQ[16],TCC_EA_WRREQ_64B[16],TCC_EA_RDREQ_IO_CREDIT_STALL[17],TCC_EA_RDREQ_LEVEL[17],TCC_EA_WRREQ[17],TCC_EA_WRREQ_64B[17],TCC_EA_RDREQ_IO_CREDIT_STALL[18],TCC_EA_RDREQ_LEVEL[18],TCC_EA_WRREQ[18],TCC_EA_WRREQ_64B[18],TCC_EA_RDREQ_IO_CREDIT_STALL[19],TCC_EA_RDREQ_LEVEL[19],TCC_EA_WRREQ[19],TCC_EA_WRREQ_64B[19],TCC_EA_RDREQ_IO_CREDIT_STALL[20],TCC_EA_RDREQ_LEVEL[20],TCC_EA_WRREQ[20],TCC_EA_WRREQ_64B[20],TCC_EA_RDREQ_IO_CREDIT_STALL[21],TCC_EA_RDREQ_LEVEL[21],TCC_EA_WRREQ[21],TCC_EA_WRREQ_64B[21],TCC_EA_RDREQ_IO_CREDIT_STALL[22],TCC_EA_RDREQ_LEVEL[22],TCC_EA_WRREQ[22],TCC_EA_WRREQ_64B[22],TCC_EA_RDREQ_IO_CREDIT_STALL[23],TCC_EA_RDREQ_LEVEL[23],TCC_EA_WRREQ[23],TCC_EA_WRREQ_64B[23],TCC_EA_RDREQ_IO_CREDIT_STALL[24],TCC_EA_RDREQ_LEVEL[24],TCC_EA_WRREQ[24],TCC_EA_WRREQ_64B[24],TCC_EA_RDREQ_IO_CREDIT_STALL[25],TCC_EA_RDREQ_LEVEL[25],TCC_EA_WRREQ[25],TCC_EA_WRREQ_64B[25],TCC_EA_RDREQ_IO_CREDIT_STALL[26],TCC_EA_RDREQ_LEVEL[26],TCC_EA_WRREQ[26],TCC_EA_WRREQ_64B[26],TCC_EA_RDREQ_IO_CREDIT_STALL[27],TCC_EA_RDREQ_LEVEL[27],TCC_EA_WRREQ[27],TCC_EA_WRREQ_64B[27],TCC_EA_RDREQ_IO_CREDIT_STALL[28],TCC_EA_RDREQ_LEVEL[28],TCC_EA_WRREQ[28],TCC_EA_WRREQ_64B[28],TCC_EA_RDREQ_IO_CREDIT_STALL[29],TCC_EA_RDREQ_LEVEL[29],TCC_EA_WRREQ[29],TCC_EA_WRREQ_64B[29],TCC_EA_RDREQ_IO_CREDIT_STALL[30],TCC_EA_RDREQ_LEVEL[30],TCC_EA_WRREQ[30],TCC_EA_WRREQ_64B[30],TCC_EA_RDREQ_IO_CREDIT_STALL[31],TCC_EA_RDREQ_LEVEL[31],TCC_EA_WRREQ[31],TCC_EA_WRREQ_64B[31],wave_size_1,obj_1,TCC_ATOMIC[0],TCC_CYCLE[0],TCC_EA_ATOMIC[0],TCC_EA_ATOMIC_LEVEL[0],TCC_ATOMIC[1],TCC_CYCLE[1],TCC_EA_ATOMIC[1],TCC_EA_ATOMIC_LEVEL[1],TCC_ATOMIC[2],TCC_CYCLE[2],TCC_EA_ATOMIC[2],TCC_EA_ATOMIC_LEVEL[2],TCC_ATOMIC[3],TCC_CYCLE[3],TCC_EA_ATOMIC[3],TCC_EA_ATOMIC_LEVEL[3],TCC_ATOMIC[4],TCC_CYCLE[4],TCC_EA_ATOMIC[4],TCC_EA_ATOMIC_LEVEL[4],TCC_ATOMIC[5],TCC_CYCLE[5],TCC_EA_ATOMIC[5],TCC_EA_ATOMIC_LEVEL[5],TCC_ATOMIC[6],TCC_CYCLE[6],TCC_EA_ATOMIC[6],TCC_EA_ATOMIC_LEVEL[6],TCC_ATOMIC[7],TCC_CYCLE[7],TCC_EA_ATOMIC[7],TCC_EA_ATOMIC_LEVEL[7],TCC_ATOMIC[8],TCC_CYCLE[8],TCC_EA_ATOMIC[8],TCC_EA_ATOMIC_LEVEL[8],TCC_ATOMIC[9],TCC_CYCLE[9],TCC_EA_ATOMIC[9],TCC_EA_ATOMIC_LEVEL[9],TCC_ATOMIC[10],TCC_CYCLE[10],TCC_EA_ATOMIC[10],TCC_EA_ATOMIC_LEVEL[10],TCC_ATOMIC[11],TCC_CYCLE[11],TCC_EA_ATOMIC[11],TCC_EA_ATOMIC_LEVEL[11],TCC_ATOMIC[12],TCC_CYCLE[12],TCC_EA_ATOMIC[12],TCC_EA_ATOMIC_LEVEL[12],TCC_ATOMIC[13],TCC_CYCLE[13],TCC_EA_ATOMIC[13],TCC_EA_ATOMIC_LEVEL[13],TCC_ATOMIC[14],TCC_CYCLE[14],TCC_EA_ATOMIC[14],TCC_EA_ATOMIC_LEVEL[14],TCC_ATOMIC[15],TCC_CYCLE[15],TCC_EA_ATOMIC[15],TCC_EA_ATOMIC_LEVEL[15],TCC_ATOMIC[16],TCC_CYCLE[16],TCC_EA_ATOMIC[16],TCC_EA_ATOMIC_LEVEL[16],TCC_ATOMIC[17],TCC_CYCLE[17],TCC_EA_ATOMIC[17],TCC_EA_ATOMIC_LEVEL[17],TCC_ATOMIC[18],TCC_CYCLE[18],TCC_EA_ATOMIC[18],TCC_EA_ATOMIC_LEVEL[18],TCC_ATOMIC[19],TCC_CYCLE[19],TCC_EA_ATOMIC[19],TCC_EA_ATOMIC_LEVEL[19],TCC_ATOMIC[20],TCC_CYCLE[20],TCC_EA_ATOMIC[20],TCC_EA_ATOMIC_LEVEL[20],TCC_ATOMIC[21],TCC_CYCLE[21],TCC_EA_ATOMIC[21],TCC_EA_ATOMIC_LEVEL[21],TCC_ATOMIC[22],TCC_CYCLE[22],TCC_EA_ATOMIC[22],TCC_EA_ATOMIC_LEVEL[22],TCC_ATOMIC[23],TCC_CYCLE[23],TCC_EA_ATOMIC[23],TCC_EA_ATOMIC_LEVEL[23],TCC_ATOMIC[24],TCC_CYCLE[24],TCC_EA_ATOMIC[24],TCC_EA_ATOMIC_LEVEL[24],TCC_ATOMIC[25],TCC_CYCLE[25],TCC_EA_ATOMIC[25],TCC_EA_ATOMIC_LEVEL[25],TCC_ATOMIC[26],TCC_CYCLE[26],TCC_EA_ATOMIC[26],TCC_EA_ATOMIC_LEVEL[26],TCC_ATOMIC[27],TCC_CYCLE[27],TCC_EA_ATOMIC[27],TCC_EA_ATOMIC_LEVEL[27],TCC_ATOMIC[28],TCC_CYCLE[28],TCC_EA_ATOMIC[28],TCC_EA_ATOMIC_LEVEL[28],TCC_ATOMIC[29],TCC_CYCLE[29],TCC_EA_ATOMIC[29],TCC_EA_ATOMIC_LEVEL[29],TCC_ATOMIC[30],TCC_CYCLE[30],TCC_EA_ATOMIC[30],TCC_EA_ATOMIC_LEVEL[30],TCC_ATOMIC[31],TCC_CYCLE[31],TCC_EA_ATOMIC[31],TCC_EA_ATOMIC_LEVEL[31],wave_size_2,obj_2,SQ_INSTS_VALU_INT64,SQ_INSTS_SMEM,SQ_INSTS_FLAT,SQ_INSTS_LDS,SQ_INSTS_GDS,SQ_INSTS_EXP_GDS,SQ_INSTS_BRANCH,SQ_INSTS_SENDMSG,TCP_TOTAL_ATOMIC_WITH_RET_sum,TCP_TOTAL_ATOMIC_WITHOUT_RET_sum,TCP_TOTAL_WRITEBACK_INVALIDATES_sum,TCP_TOTAL_CACHE_ACCESSES_sum,TA_BUFFER_COALESCED_READ_CYCLES_sum,TA_BUFFER_COALESCED_WRITE_CYCLES_sum,TD_COALESCABLE_WAVEFRONT_sum,SPI_RA_RES_STALL_CSN,SPI_RA_TMP_STALL_CSN,CPC_CPC_UTCL2IU_BUSY,CPC_CPC_UTCL2IU_IDLE,CPF_CMP_UTCL1_STALL_ON_TRANSLATION,TCC_READ_sum,TCC_WRITE_sum,TCC_ATOMIC_sum,TCC_WRITEBACK_sum,wave_size_3,obj_3,SQC_ICACHE_MISSES_DUPLICATE,SQC_DCACHE_INPUT_VALID_READYB,SQC_DCACHE_ATOMIC,SQC_DCACHE_REQ_READ_8,SQC_DCACHE_REQ,SQC_DCACHE_HITS,SQC_DCACHE_MISSES,SQC_DCACHE_MISSES_DUPLICATE,wave_size_4,obj_4,SQ_INSTS_SMEM_NORM,SQ_INSTS_MFMA,SQ_INSTS_VALU_MFMA_I8,SQ_INSTS_VALU_MFMA_F16,SQ_INSTS_VALU_MFMA_BF16,SQ_INSTS_VALU_MFMA_F32,SQ_INSTS_VALU_MFMA_F64,SQ_VALU_MFMA_BUSY_CYCLES,TCP_TCC_UC_ATOMIC_REQ_sum,TCP_TCC_CC_READ_REQ_sum,TCP_TCC_CC_WRITE_REQ_sum,TCP_TCC_CC_ATOMIC_REQ_sum,SPI_VWC_CSC_WR,SPI_RA_BULKY_CU_FULL_CSN,TCC_EA_RDREQ_LEVEL_sum,TCC_EA_WRREQ_LEVEL_sum,TCC_EA_ATOMIC_LEVEL_sum,wave_size_5,obj_5,SQ_INSTS_FLAT_LDS_ONLY,SQ_INSTS_VALU_MFMA_MOPS_I8,SQ_INSTS_VALU_MFMA_MOPS_F16,SQ_INSTS_VALU_MFMA_MOPS_BF16,SQ_INSTS_VALU_MFMA_MOPS_F32,SQ_INSTS_VALU_MFMA_MOPS_F64,SQC_TC_INST_REQ,SQC_TC_DATA_READ_REQ,TCP_TCC_RW_READ_REQ_sum,TCP_TCC_RW_WRITE_REQ_sum,TCP_TCC_RW_ATOMIC_REQ_sum,TCP_PENDING_STALL_CYCLES_sum,wave_size_6,obj_6,TCC_EA_RDREQ[0],TCC_EA_RDREQ_32B[0],TCC_EA_RDREQ_DRAM_CREDIT_STALL[0],TCC_EA_RDREQ_GMI_CREDIT_STALL[0],TCC_EA_RDREQ[1],TCC_EA_RDREQ_32B[1],TCC_EA_RDREQ_DRAM_CREDIT_STALL[1],TCC_EA_RDREQ_GMI_CREDIT_STALL[1],TCC_EA_RDREQ[2],TCC_EA_RDREQ_32B[2],TCC_EA_RDREQ_DRAM_CREDIT_STALL[2],TCC_EA_RDREQ_GMI_CREDIT_STALL[2],TCC_EA_RDREQ[3],TCC_EA_RDREQ_32B[3],TCC_EA_RDREQ_DRAM_CREDIT_STALL[3],TCC_EA_RDREQ_GMI_CREDIT_STALL[3],TCC_EA_RDREQ[4],TCC_EA_RDREQ_32B[4],TCC_EA_RDREQ_DRAM_CREDIT_STALL[4],TCC_EA_RDREQ_GMI_CREDIT_STALL[4],TCC_EA_RDREQ[5],TCC_EA_RDREQ_32B[5],TCC_EA_RDREQ_DRAM_CREDIT_STALL[5],TCC_EA_RDREQ_GMI_CREDIT_STALL[5],TCC_EA_RDREQ[6],TCC_EA_RDREQ_32B[6],TCC_EA_RDREQ_DRAM_CREDIT_STALL[6],TCC_EA_RDREQ_GMI_CREDIT_STALL[6],TCC_EA_RDREQ[7],TCC_EA_RDREQ_32B[7],TCC_EA_RDREQ_DRAM_CREDIT_STALL[7],TCC_EA_RDREQ_GMI_CREDIT_STALL[7],TCC_EA_RDREQ[8],TCC_EA_RDREQ_32B[8],TCC_EA_RDREQ_DRAM_CREDIT_STALL[8],TCC_EA_RDREQ_GMI_CREDIT_STALL[8],TCC_EA_RDREQ[9],TCC_EA_RDREQ_32B[9],TCC_EA_RDREQ_DRAM_CREDIT_STALL[9],TCC_EA_RDREQ_GMI_CREDIT_STALL[9],TCC_EA_RDREQ[10],TCC_EA_RDREQ_32B[10],TCC_EA_RDREQ_DRAM_CREDIT_STALL[10],TCC_EA_RDREQ_GMI_CREDIT_STALL[10],TCC_EA_RDREQ[11],TCC_EA_RDREQ_32B[11],TCC_EA_RDREQ_DRAM_CREDIT_STALL[11],TCC_EA_RDREQ_GMI_CREDIT_STALL[11],TCC_EA_RDREQ[12],TCC_EA_RDREQ_32B[12],TCC_EA_RDREQ_DRAM_CREDIT_STALL[12],TCC_EA_RDREQ_GMI_CREDIT_STALL[12],TCC_EA_RDREQ[13],TCC_EA_RDREQ_32B[13],TCC_EA_RDREQ_DRAM_CREDIT_STALL[13],TCC_EA_RDREQ_GMI_CREDIT_STALL[13],TCC_EA_RDREQ[14],TCC_EA_RDREQ_32B[14],TCC_EA_RDREQ_DRAM_CREDIT_STALL[14],TCC_EA_RDREQ_GMI_CREDIT_STALL[14],TCC_EA_RDREQ[15],TCC_EA_RDREQ_32B[15],TCC_EA_RDREQ_DRAM_CREDIT_STALL[15],TCC_EA_RDREQ_GMI_CREDIT_STALL[15],TCC_EA_RDREQ[16],TCC_EA_RDREQ_32B[16],TCC_EA_RDREQ_DRAM_CREDIT_STALL[16],TCC_EA_RDREQ_GMI_CREDIT_STALL[16],TCC_EA_RDREQ[17],TCC_EA_RDREQ_32B[17],TCC_EA_RDREQ_DRAM_CREDIT_STALL[17],TCC_EA_RDREQ_GMI_CREDIT_STALL[17],TCC_EA_RDREQ[18],TCC_EA_RDREQ_32B[18],TCC_EA_RDREQ_DRAM_CREDIT_STALL[18],TCC_EA_RDREQ_GMI_CREDIT_STALL[18],TCC_EA_RDREQ[19],TCC_EA_RDREQ_32B[19],TCC_EA_RDREQ_DRAM_CREDIT_STALL[19],TCC_EA_RDREQ_GMI_CREDIT_STALL[19],TCC_EA_RDREQ[20],TCC_EA_RDREQ_32B[20],TCC_EA_RDREQ_DRAM_CREDIT_STALL[20],TCC_EA_RDREQ_GMI_CREDIT_STALL[20],TCC_EA_RDREQ[21],TCC_EA_RDREQ_32B[21],TCC_EA_RDREQ_DRAM_CREDIT_STALL[21],TCC_EA_RDREQ_GMI_CREDIT_STALL[21],TCC_EA_RDREQ[22],TCC_EA_RDREQ_32B[22],TCC_EA_RDREQ_DRAM_CREDIT_STALL[22],TCC_EA_RDREQ_GMI_CREDIT_STALL[22],TCC_EA_RDREQ[23],TCC_EA_RDREQ_32B[23],TCC_EA_RDREQ_DRAM_CREDIT_STALL[23],TCC_EA_RDREQ_GMI_CREDIT_STALL[23],TCC_EA_RDREQ[24],TCC_EA_RDREQ_32B[24],TCC_EA_RDREQ_DRAM_CREDIT_STALL[24],TCC_EA_RDREQ_GMI_CREDIT_STALL[24],TCC_EA_RDREQ[25],TCC_EA_RDREQ_32B[25],TCC_EA_RDREQ_DRAM_CREDIT_STALL[25],TCC_EA_RDREQ_GMI_CREDIT_STALL[25],TCC_EA_RDREQ[26],TCC_EA_RDREQ_32B[26],TCC_EA_RDREQ_DRAM_CREDIT_STALL[26],TCC_EA_RDREQ_GMI_CREDIT_STALL[26],TCC_EA_RDREQ[27],TCC_EA_RDREQ_32B[27],TCC_EA_RDREQ_DRAM_CREDIT_STALL[27],TCC_EA_RDREQ_GMI_CREDIT_STALL[27],TCC_EA_RDREQ[28],TCC_EA_RDREQ_32B[28],TCC_EA_RDREQ_DRAM_CREDIT_STALL[28],TCC_EA_RDREQ_GMI_CREDIT_STALL[28],TCC_EA_RDREQ[29],TCC_EA_RDREQ_32B[29],TCC_EA_RDREQ_DRAM_CREDIT_STALL[29],TCC_EA_RDREQ_GMI_CREDIT_STALL[29],TCC_EA_RDREQ[30],TCC_EA_RDREQ_32B[30],TCC_EA_RDREQ_DRAM_CREDIT_STALL[30],TCC_EA_RDREQ_GMI_CREDIT_STALL[30],TCC_EA_RDREQ[31],TCC_EA_RDREQ_32B[31],TCC_EA_RDREQ_DRAM_CREDIT_STALL[31],TCC_EA_RDREQ_GMI_CREDIT_STALL[31],wave_size_7,obj_7,TCC_HIT[0],TCC_MISS[0],TCC_READ[0],TCC_REQ[0],TCC_HIT[1],TCC_MISS[1],TCC_READ[1],TCC_REQ[1],TCC_HIT[2],TCC_MISS[2],TCC_READ[2],TCC_REQ[2],TCC_HIT[3],TCC_MISS[3],TCC_READ[3],TCC_REQ[3],TCC_HIT[4],TCC_MISS[4],TCC_READ[4],TCC_REQ[4],TCC_HIT[5],TCC_MISS[5],TCC_READ[5],TCC_REQ[5],TCC_HIT[6],TCC_MISS[6],TCC_READ[6],TCC_REQ[6],TCC_HIT[7],TCC_MISS[7],TCC_READ[7],TCC_REQ[7],TCC_HIT[8],TCC_MISS[8],TCC_READ[8],TCC_REQ[8],TCC_HIT[9],TCC_MISS[9],TCC_READ[9],TCC_REQ[9],TCC_HIT[10],TCC_MISS[10],TCC_READ[10],TCC_REQ[10],TCC_HIT[11],TCC_MISS[11],TCC_READ[11],TCC_REQ[11],TCC_HIT[12],TCC_MISS[12],TCC_READ[12],TCC_REQ[12],TCC_HIT[13],TCC_MISS[13],TCC_READ[13],TCC_REQ[13],TCC_HIT[14],TCC_MISS[14],TCC_READ[14],TCC_REQ[14],TCC_HIT[15],TCC_MISS[15],TCC_READ[15],TCC_REQ[15],TCC_HIT[16],TCC_MISS[16],TCC_READ[16],TCC_REQ[16],TCC_HIT[17],TCC_MISS[17],TCC_READ[17],TCC_REQ[17],TCC_HIT[18],TCC_MISS[18],TCC_READ[18],TCC_REQ[18],TCC_HIT[19],TCC_MISS[19],TCC_READ[19],TCC_REQ[19],TCC_HIT[20],TCC_MISS[20],TCC_READ[20],TCC_REQ[20],TCC_HIT[21],TCC_MISS[21],TCC_READ[21],TCC_REQ[21],TCC_HIT[22],TCC_MISS[22],TCC_READ[22],TCC_REQ[22],TCC_HIT[23],TCC_MISS[23],TCC_READ[23],TCC_REQ[23],TCC_HIT[24],TCC_MISS[24],TCC_READ[24],TCC_REQ[24],TCC_HIT[25],TCC_MISS[25],TCC_READ[25],TCC_REQ[25],TCC_HIT[26],TCC_MISS[26],TCC_READ[26],TCC_REQ[26],TCC_HIT[27],TCC_MISS[27],TCC_READ[27],TCC_REQ[27],TCC_HIT[28],TCC_MISS[28],TCC_READ[28],TCC_REQ[28],TCC_HIT[29],TCC_MISS[29],TCC_READ[29],TCC_REQ[29],TCC_HIT[30],TCC_MISS[30],TCC_READ[30],TCC_REQ[30],TCC_HIT[31],TCC_MISS[31],TCC_READ[31],TCC_REQ[31],wave_size_8,obj_8,SQ_ACTIVE_INST_SCA,SQ_ACTIVE_INST_EXP_GDS,SQ_ACTIVE_INST_MISC,SQ_ACTIVE_INST_FLAT,SQ_INST_CYCLES_VMEM_WR,SQ_INST_CYCLES_VMEM_RD,SQ_INST_CYCLES_SMEM,SQ_INST_CYCLES_SALU,TCP_TCP_LATENCY_sum,TCP_TCC_READ_REQ_LATENCY_sum,TCP_TCC_WRITE_REQ_LATENCY_sum,TCP_TCC_READ_REQ_sum,TA_ADDR_STALLED_BY_TD_CYCLES_sum,TA_DATA_STALLED_BY_TC_CYCLES_sum,SPI_RA_SGPR_SIMD_FULL_CSN,SPI_RA_LDS_CU_FULL_CSN,CPC_ME1_DC0_SPI_BUSY,TCC_EA_WRREQ_STALL_sum,TCC_EA_RDREQ_sum,TCC_EA_RDREQ_32B_sum,TCC_EA_RD_UNCACHED_32B_sum,wave_size_9,obj_9,TCC_EA_WRREQ_DRAM_CREDIT_STALL[0],TCC_EA_WRREQ_GMI_CREDIT_STALL[0],TCC_EA_WRREQ_IO_CREDIT_STALL[0],TCC_EA_WRREQ_LEVEL[0],TCC_EA_WRREQ_DRAM_CREDIT_STALL[1],TCC_EA_WRREQ_GMI_CREDIT_STALL[1],TCC_EA_WRREQ_IO_CREDIT_STALL[1],TCC_EA_WRREQ_LEVEL[1],TCC_EA_WRREQ_DRAM_CREDIT_STALL[2],TCC_EA_WRREQ_GMI_CREDIT_STALL[2],TCC_EA_WRREQ_IO_CREDIT_STALL[2],TCC_EA_WRREQ_LEVEL[2],TCC_EA_WRREQ_DRAM_CREDIT_STALL[3],TCC_EA_WRREQ_GMI_CREDIT_STALL[3],TCC_EA_WRREQ_IO_CREDIT_STALL[3],TCC_EA_WRREQ_LEVEL[3],TCC_EA_WRREQ_DRAM_CREDIT_STALL[4],TCC_EA_WRREQ_GMI_CREDIT_STALL[4],TCC_EA_WRREQ_IO_CREDIT_STALL[4],TCC_EA_WRREQ_LEVEL[4],TCC_EA_WRREQ_DRAM_CREDIT_STALL[5],TCC_EA_WRREQ_GMI_CREDIT_STALL[5],TCC_EA_WRREQ_IO_CREDIT_STALL[5],TCC_EA_WRREQ_LEVEL[5],TCC_EA_WRREQ_DRAM_CREDIT_STALL[6],TCC_EA_WRREQ_GMI_CREDIT_STALL[6],TCC_EA_WRREQ_IO_CREDIT_STALL[6],TCC_EA_WRREQ_LEVEL[6],TCC_EA_WRREQ_DRAM_CREDIT_STALL[7],TCC_EA_WRREQ_GMI_CREDIT_STALL[7],TCC_EA_WRREQ_IO_CREDIT_STALL[7],TCC_EA_WRREQ_LEVEL[7],TCC_EA_WRREQ_DRAM_CREDIT_STALL[8],TCC_EA_WRREQ_GMI_CREDIT_STALL[8],TCC_EA_WRREQ_IO_CREDIT_STALL[8],TCC_EA_WRREQ_LEVEL[8],TCC_EA_WRREQ_DRAM_CREDIT_STALL[9],TCC_EA_WRREQ_GMI_CREDIT_STALL[9],TCC_EA_WRREQ_IO_CREDIT_STALL[9],TCC_EA_WRREQ_LEVEL[9],TCC_EA_WRREQ_DRAM_CREDIT_STALL[10],TCC_EA_WRREQ_GMI_CREDIT_STALL[10],TCC_EA_WRREQ_IO_CREDIT_STALL[10],TCC_EA_WRREQ_LEVEL[10],TCC_EA_WRREQ_DRAM_CREDIT_STALL[11],TCC_EA_WRREQ_GMI_CREDIT_STALL[11],TCC_EA_WRREQ_IO_CREDIT_STALL[11],TCC_EA_WRREQ_LEVEL[11],TCC_EA_WRREQ_DRAM_CREDIT_STALL[12],TCC_EA_WRREQ_GMI_CREDIT_STALL[12],TCC_EA_WRREQ_IO_CREDIT_STALL[12],TCC_EA_WRREQ_LEVEL[12],TCC_EA_WRREQ_DRAM_CREDIT_STALL[13],TCC_EA_WRREQ_GMI_CREDIT_STALL[13],TCC_EA_WRREQ_IO_CREDIT_STALL[13],TCC_EA_WRREQ_LEVEL[13],TCC_EA_WRREQ_DRAM_CREDIT_STALL[14],TCC_EA_WRREQ_GMI_CREDIT_STALL[14],TCC_EA_WRREQ_IO_CREDIT_STALL[14],TCC_EA_WRREQ_LEVEL[14],TCC_EA_WRREQ_DRAM_CREDIT_STALL[15],TCC_EA_WRREQ_GMI_CREDIT_STALL[15],TCC_EA_WRREQ_IO_CREDIT_STALL[15],TCC_EA_WRREQ_LEVEL[15],TCC_EA_WRREQ_DRAM_CREDIT_STALL[16],TCC_EA_WRREQ_GMI_CREDIT_STALL[16],TCC_EA_WRREQ_IO_CREDIT_STALL[16],TCC_EA_WRREQ_LEVEL[16],TCC_EA_WRREQ_DRAM_CREDIT_STALL[17],TCC_EA_WRREQ_GMI_CREDIT_STALL[17],TCC_EA_WRREQ_IO_CREDIT_STALL[17],TCC_EA_WRREQ_LEVEL[17],TCC_EA_WRREQ_DRAM_CREDIT_STALL[18],TCC_EA_WRREQ_GMI_CREDIT_STALL[18],TCC_EA_WRREQ_IO_CREDIT_STALL[18],TCC_EA_WRREQ_LEVEL[18],TCC_EA_WRREQ_DRAM_CREDIT_STALL[19],TCC_EA_WRREQ_GMI_CREDIT_STALL[19],TCC_EA_WRREQ_IO_CREDIT_STALL[19],TCC_EA_WRREQ_LEVEL[19],TCC_EA_WRREQ_DRAM_CREDIT_STALL[20],TCC_EA_WRREQ_GMI_CREDIT_STALL[20],TCC_EA_WRREQ_IO_CREDIT_STALL[20],TCC_EA_WRREQ_LEVEL[20],TCC_EA_WRREQ_DRAM_CREDIT_STALL[21],TCC_EA_WRREQ_GMI_CREDIT_STALL[21],TCC_EA_WRREQ_IO_CREDIT_STALL[21],TCC_EA_WRREQ_LEVEL[21],TCC_EA_WRREQ_DRAM_CREDIT_STALL[22],TCC_EA_WRREQ_GMI_CREDIT_STALL[22],TCC_EA_WRREQ_IO_CREDIT_STALL[22],TCC_EA_WRREQ_LEVEL[22],TCC_EA_WRREQ_DRAM_CREDIT_STALL[23],TCC_EA_WRREQ_GMI_CREDIT_STALL[23],TCC_EA_WRREQ_IO_CREDIT_STALL[23],TCC_EA_WRREQ_LEVEL[23],TCC_EA_WRREQ_DRAM_CREDIT_STALL[24],TCC_EA_WRREQ_GMI_CREDIT_STALL[24],TCC_EA_WRREQ_IO_CREDIT_STALL[24],TCC_EA_WRREQ_LEVEL[24],TCC_EA_WRREQ_DRAM_CREDIT_STALL[25],TCC_EA_WRREQ_GMI_CREDIT_STALL[25],TCC_EA_WRREQ_IO_CREDIT_STALL[25],TCC_EA_WRREQ_LEVEL[25],TCC_EA_WRREQ_DRAM_CREDIT_STALL[26],TCC_EA_WRREQ_GMI_CREDIT_STALL[26],TCC_EA_WRREQ_IO_CREDIT_STALL[26],TCC_EA_WRREQ_LEVEL[26],TCC_EA_WRREQ_DRAM_CREDIT_STALL[27],TCC_EA_WRREQ_GMI_CREDIT_STALL[27],TCC_EA_WRREQ_IO_CREDIT_STALL[27],TCC_EA_WRREQ_LEVEL[27],TCC_EA_WRREQ_DRAM_CREDIT_STALL[28],TCC_EA_WRREQ_GMI_CREDIT_STALL[28],TCC_EA_WRREQ_IO_CREDIT_STALL[28],TCC_EA_WRREQ_LEVEL[28],TCC_EA_WRREQ_DRAM_CREDIT_STALL[29],TCC_EA_WRREQ_GMI_CREDIT_STALL[29],TCC_EA_WRREQ_IO_CREDIT_STALL[29],TCC_EA_WRREQ_LEVEL[29],TCC_EA_WRREQ_DRAM_CREDIT_STALL[30],TCC_EA_WRREQ_GMI_CREDIT_STALL[30],TCC_EA_WRREQ_IO_CREDIT_STALL[30],TCC_EA_WRREQ_LEVEL[30],TCC_EA_WRREQ_DRAM_CREDIT_STALL[31],TCC_EA_WRREQ_GMI_CREDIT_STALL[31],TCC_EA_WRREQ_IO_CREDIT_STALL[31],TCC_EA_WRREQ_LEVEL[31],wave_size_10,obj_10,SQ_THREAD_CYCLES_VALU,SQ_IFETCH,SQ_LDS_BANK_CONFLICT,SQ_LDS_ADDR_CONFLICT,SQ_LDS_UNALIGNED_STALL,SQ_WAVES_EQ_64,SQ_WAVES_LT_64,SQ_WAVES_LT_48,TCP_TCC_WRITE_REQ_sum,TCP_TCC_ATOMIC_WITH_RET_REQ_sum,TCP_TCC_ATOMIC_WITHOUT_RET_REQ_sum,TCP_TCC_NC_READ_REQ_sum,TA_FLAT_WAVEFRONTS_sum,TA_FLAT_READ_WAVEFRONTS_sum,SPI_RA_BAR_CU_FULL_CSN,SPI_RA_TGLIM_CU_FULL_CSN,TCC_EA_RDREQ_DRAM_sum,TCC_TAG_STALL_sum,TCC_NORMAL_WRITEBACK_sum,TCC_ALL_TC_OP_WB_WRITEBACK_sum,wave_size_11,obj_11,SQ_INSTS_VALU_MUL_F32,SQ_INSTS_VALU_FMA_F32,SQ_INSTS_VALU_TRANS_F32,SQ_INSTS_VALU_ADD_F64,SQ_INSTS_VALU_MUL_F64,SQ_INSTS_VALU_FMA_F64,SQ_INSTS_VALU_TRANS_F64,SQ_INSTS_VALU_INT32,TCP_VOLATILE_sum,TCP_TOTAL_ACCESSES_sum,TCP_TOTAL_READ_sum,TCP_TOTAL_WRITE_sum,TA_BUFFER_ATOMIC_WAVEFRONTS_sum,TA_BUFFER_TOTAL_CYCLES_sum,TD_ATOMIC_WAVEFRONT_sum,TD_STORE_WAVEFRONT_sum,SPI_RA_REQ_NO_ALLOC,SPI_RA_REQ_NO_ALLOC_CSN,CPC_CPC_STAT_STALL,CPC_UTCL1_STALL_ON_TRANSLATION,CPF_CPF_STAT_IDLE,CPF_CPF_TCIU_IDLE,TCC_REQ_sum,TCC_STREAMING_REQ_sum,TCC_HIT_sum,TCC_MISS_sum,wave_size_12,obj_12,SQC_TC_DATA_WRITE_REQ,SQC_TC_DATA_ATOMIC_REQ,SQC_TC_STALL,SQC_TC_REQ,SQC_DCACHE_REQ_READ_16,SQC_ICACHE_REQ,SQC_ICACHE_HITS,SQC_ICACHE_MISSES,wave_size_13,obj_13,SQ_WAVE_CYCLES,SQ_WAIT_ANY,SQ_WAIT_INST_ANY,SQ_ACTIVE_INST_ANY,SQ_BUSY_CU_CYCLES,SQ_ACTIVE_INST_VMEM,SQ_ACTIVE_INST_LDS,SQ_ACTIVE_INST_VALU,TCP_UTCL1_TRANSLATION_MISS_sum,TCP_UTCL1_TRANSLATION_HIT_sum,TCP_UTCL1_PERMISSION_MISS_sum,TCP_UTCL1_REQUEST_sum,TA_ADDR_STALLED_BY_TC_CYCLES_sum,TA_TOTAL_WAVEFRONTS_sum,SPI_RA_WAVE_SIMD_FULL_CSN,SPI_RA_VGPR_SIMD_FULL_CSN,CPC_CPC_UTCL2IU_STALL,CPC_ME1_BUSY_FOR_PACKET_DECODE,TCC_EA_WRREQ_sum,TCC_EA_WRREQ_64B_sum,TCC_EA_WR_UNCACHED_32B_sum,TCC_EA_WRREQ_DRAM_sum,wave_size_14,obj_14,SQ_WAVES_LT_32,SQ_WAVES_LT_16,SQ_ITEMS,SQ_LDS_MEM_VIOLATIONS,SQ_LDS_ATOMIC_RETURN,SQ_LDS_IDX_ACTIVE,SQ_WAVES_RESTORED,SQ_WAVES_SAVED,TCP_TCC_NC_WRITE_REQ_sum,TCP_TCC_NC_ATOMIC_REQ_sum,TCP_TCC_UC_READ_REQ_sum,TCP_TCC_UC_WRITE_REQ_sum,TA_FLAT_WRITE_WAVEFRONTS_sum,TA_FLAT_ATOMIC_WAVEFRONTS_sum,SPI_RA_WVLIM_STALL_CSN,SPI_SWC_CSC_WR,TCC_NORMAL_EVICT_sum,TCC_ALL_TC_OP_INV_EVICT_sum,TCC_TOO_MANY_EA_WRREQS_STALL_sum,TCC_EA_ATOMIC_sum,wave_size_15,obj_15,SQ_INSTS_VSKIPPED,SQ_INSTS,SQ_INSTS_VALU,SQ_INSTS_VALU_ADD_F16,SQ_INSTS_VALU_MUL_F16,SQ_INSTS_VALU_FMA_F16,SQ_INSTS_VALU_TRANS_F16,SQ_INSTS_VALU_ADD_F32,GRBM_SPI_BUSY,TCP_READ_TAGCONFLICT_STALL_CYCLES_sum,TCP_WRITE_TAGCONFLICT_STALL_CYCLES_sum,TCP_ATOMIC_TAGCONFLICT_STALL_CYCLES_sum,TCP_TA_TCP_STATE_READ_sum,TA_BUFFER_READ_WAVEFRONTS_sum,TA_BUFFER_WRITE_WAVEFRONTS_sum,TD_SPI_STALL_sum,TD_LOAD_WAVEFRONT_sum,SPI_CSN_NUM_THREADGROUPS,SPI_CSN_WAVE,CPC_CPC_TCIU_BUSY,CPC_CPC_TCIU_IDLE,CPF_CPF_TCIU_BUSY,CPF_CPF_TCIU_STALL,TCC_NC_REQ_sum,TCC_UC_REQ_sum,TCC_CC_REQ_sum,TCC_RW_REQ_sum,wave_size_16,obj_16,SQ_CYCLES,SQ_BUSY_CYCLES,SQ_WAVES,SQ_INSTS_VALU_CVT,SQ_INSTS_VMEM_WR,SQ_INSTS_VMEM_RD,SQ_INSTS_VMEM,SQ_INSTS_SALU,GRBM_COUNT,GRBM_GUI_ACTIVE,TCP_GATE_EN1_sum,TCP_GATE_EN2_sum,TCP_TD_TCP_STALL_CYCLES_sum,TCP_TCR_TCP_STALL_CYCLES_sum,TA_TA_BUSY_sum,TA_BUFFER_WAVEFRONTS_sum,TD_TD_BUSY_sum,TD_TC_STALL_sum,SPI_CSN_WINDOW_VALID,SPI_CSN_BUSY,CPC_CPC_STAT_BUSY,CPC_CPC_STAT_IDLE,CPF_CPF_STAT_BUSY,CPF_CPF_STAT_STALL,TCC_CYCLE_sum,TCC_BUSY_sum,TCC_PROBE_sum,TCC_PROBE_ALL_sum,wave_size_17,obj_17,TCC_RW_REQ[0],TCC_TOO_MANY_EA_WRREQS_STALL[0],TCC_WRITE[0],TCC_RW_REQ[1],TCC_TOO_MANY_EA_WRREQS_STALL[1],TCC_WRITE[1],TCC_RW_REQ[2],TCC_TOO_MANY_EA_WRREQS_STALL[2],TCC_WRITE[2],TCC_RW_REQ[3],TCC_TOO_MANY_EA_WRREQS_STALL[3],TCC_WRITE[3],TCC_RW_REQ[4],TCC_TOO_MANY_EA_WRREQS_STALL[4],TCC_WRITE[4],TCC_RW_REQ[5],TCC_TOO_MANY_EA_WRREQS_STALL[5],TCC_WRITE[5],TCC_RW_REQ[6],TCC_TOO_MANY_EA_WRREQS_STALL[6],TCC_WRITE[6],TCC_RW_REQ[7],TCC_TOO_MANY_EA_WRREQS_STALL[7],TCC_WRITE[7],TCC_RW_REQ[8],TCC_TOO_MANY_EA_WRREQS_STALL[8],TCC_WRITE[8],TCC_RW_REQ[9],TCC_TOO_MANY_EA_WRREQS_STALL[9],TCC_WRITE[9],TCC_RW_REQ[10],TCC_TOO_MANY_EA_WRREQS_STALL[10],TCC_WRITE[10],TCC_RW_REQ[11],TCC_TOO_MANY_EA_WRREQS_STALL[11],TCC_WRITE[11],TCC_RW_REQ[12],TCC_TOO_MANY_EA_WRREQS_STALL[12],TCC_WRITE[12],TCC_RW_REQ[13],TCC_TOO_MANY_EA_WRREQS_STALL[13],TCC_WRITE[13],TCC_RW_REQ[14],TCC_TOO_MANY_EA_WRREQS_STALL[14],TCC_WRITE[14],TCC_RW_REQ[15],TCC_TOO_MANY_EA_WRREQS_STALL[15],TCC_WRITE[15],TCC_RW_REQ[16],TCC_TOO_MANY_EA_WRREQS_STALL[16],TCC_WRITE[16],TCC_RW_REQ[17],TCC_TOO_MANY_EA_WRREQS_STALL[17],TCC_WRITE[17],TCC_RW_REQ[18],TCC_TOO_MANY_EA_WRREQS_STALL[18],TCC_WRITE[18],TCC_RW_REQ[19],TCC_TOO_MANY_EA_WRREQS_STALL[19],TCC_WRITE[19],TCC_RW_REQ[20],TCC_TOO_MANY_EA_WRREQS_STALL[20],TCC_WRITE[20],TCC_RW_REQ[21],TCC_TOO_MANY_EA_WRREQS_STALL[21],TCC_WRITE[21],TCC_RW_REQ[22],TCC_TOO_MANY_EA_WRREQS_STALL[22],TCC_WRITE[22],TCC_RW_REQ[23],TCC_TOO_MANY_EA_WRREQS_STALL[23],TCC_WRITE[23],TCC_RW_REQ[24],TCC_TOO_MANY_EA_WRREQS_STALL[24],TCC_WRITE[24],TCC_RW_REQ[25],TCC_TOO_MANY_EA_WRREQS_STALL[25],TCC_WRITE[25],TCC_RW_REQ[26],TCC_TOO_MANY_EA_WRREQS_STALL[26],TCC_WRITE[26],TCC_RW_REQ[27],TCC_TOO_MANY_EA_WRREQS_STALL[27],TCC_WRITE[27],TCC_RW_REQ[28],TCC_TOO_MANY_EA_WRREQS_STALL[28],TCC_WRITE[28],TCC_RW_REQ[29],TCC_TOO_MANY_EA_WRREQS_STALL[29],TCC_WRITE[29],TCC_RW_REQ[30],TCC_TOO_MANY_EA_WRREQS_STALL[30],TCC_WRITE[30],TCC_RW_REQ[31],TCC_TOO_MANY_EA_WRREQS_STALL[31],TCC_WRITE[31],wave_size_18,obj_18,SQC_DCACHE_REQ_READ_1,SQC_DCACHE_REQ_READ_2,SQC_DCACHE_REQ_READ_4,Start_Timestamp,End_Timestamp +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f719d074ec0,0,1280294,4096,4096,0,1016298,4096,4096,0,1173736,4096,4096,0,1331612,4096,4096,0,1104334,4096,4096,0,1203531,4096,4096,0,1008753,4096,4096,0,1292385,4096,4096,0,1190225,4096,4096,0,1227828,4096,4096,0,1131202,4096,4096,0,1203672,4096,4096,0,1138456,4096,4096,0,1183327,4096,4096,0,1394894,4096,4096,0,1277117,4096,4096,0,1253645,4096,4096,0,1265595,4096,4096,0,1071387,4096,4096,0,1761815,4096,4096,0,1356100,4096,4096,0,1511464,4096,4096,0,1122717,4096,4096,0,1268678,4096,4096,0,1126448,4096,4096,0,1062773,4096,4096,0,1041707,4096,4096,0,1233636,4096,4096,0,1492365,4096,4096,0,1237295,4096,4096,0,1420029,4096,4096,0,1217238,4096,4096,64,0x7f5871864ec0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,0,27506,0,0,64,0x7f842c814ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,10074,0,816,27715,0,73251.0,131072.0,0.0,65568.0,64,0x7f64e75d8ec0,1276,114416,0,0,65536,63800,56,1680,64,0x7f01f2d00ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,39527436.0,35354785.0,0.0,64,0x7f6ecb88cec0,0,0,0,0,0,0,168,56,131072.0,131072.0,0.0,946191.0,64,0x7fc1d67f8ec0,4096,0,0,0,4096,0,129,0,4096,0,0,0,4096,0,147,0,4098,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,355,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,207,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4099,0,0,0,4096,0,0,0,4096,0,0,0,4097,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,4096,0,0,0,64,0x7feb1c338ec0,2253,4099,2256,6352,2274,4096,2274,6370,2292,4096,2292,6388,2317,4096,2317,6413,2232,4096,2232,6328,2266,4096,2266,6362,2275,4096,2275,6371,2286,4096,2286,6382,2287,4096,2287,6383,2249,4096,2249,6345,2279,4096,2279,6375,2295,4096,2295,6391,2315,4096,2315,6411,2238,4096,2238,6334,2270,4096,2270,6366,2277,4096,2277,6373,2263,4096,2263,6359,2285,4096,2285,6381,2196,4098,2198,6294,2265,4096,2265,6361,2327,4097,2328,6424,2304,4096,2304,6400,2280,4096,2280,6376,2435,4098,2437,6533,2270,4096,2270,6366,2262,4096,2262,6358,2286,4096,2286,6382,2204,4096,2204,6300,2266,4096,2266,6362,2270,4096,2270,6366,2308,4096,2308,6404,2280,4096,2280,6376,64,0x7f0c851d0ec0,114688,0,32768,32768,16384,16384,65536,49152,27530242.0,84637584.0,37276646.0,131072.0,0.0,221242.0,0,0,15056,687.0,131086.0,0.0,20.0,64,0x7f2a26314ec0,0,0,0,1027825,74,0,0,1131751,0,0,0,1057543,0,0,0,1097462,0,0,0,1120029,55,0,0,1246251,0,0,0,1072885,0,0,0,1216521,0,0,0,1086561,0,0,0,1064423,0,0,0,1004711,0,0,0,1108645,0,0,0,1024831,0,0,0,1142102,0,0,0,1177389,22,0,0,1214656,0,0,0,1014701,0,0,0,1107805,0,0,0,1131637,0,0,0,1218413,0,0,0,1074604,0,0,0,1079222,60,0,0,1246159,0,0,0,1124479,0,0,0,1077444,0,0,0,1099417,145,0,0,1205829,41,0,0,1224358,0,0,0,1128386,0,0,0,1121967,0,0,0,1026123,69,0,0,1279568,64,0x7f980b700ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131079.0,33891.0,46047.0,19489.0,64,0x7f9e9e168ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,13604,19334,8300,545,0,27266,204016.0,0.0,72935.0,131081.0,64,0x7f80e4520ec0,0,0,0,224,0,65536,64132,56,64,0x7fbd96bb4ec0,10620646,9564806,711776,344064,1594430,0,0,163840,832.0,515136.0,0.0,524288.0,277686.0,32768.0,458925,0,0,10761,131072.0,131072.0,0.0,131072.0,64,0x7fa1d1cb0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65551.0,0.0,0.0,0.0,64,0x7f9a5f924ec0,0,393216,163840,0,0,0,0,0,18078,0.0,0.0,0.0,32768.0,0.0,0.0,416.0,32768.0,4096,16384,352,28633,2150,0,56.0,6.0,0.0,204556.0,64,0x7ff854d0cec0,235728,131018,16384,0,16384,16384,32768,49152,29465,29465,1980828.0,1398275.0,3488.0,200607.0,1093079.0,0.0,1390463.0,1092398.0,234017,139150,29465,0,29465,0,942880.0,503329.0,0.0,0.0,64,0x7f6ca7ed0ec0,6374,0,4096,6393,0,4096,6379,0,4096,6357,0,4096,6399,0,4096,6418,0,4096,6391,0,4096,6360,0,4096,6365,0,4096,6370,0,4096,6395,0,4096,6379,0,4096,6353,0,4096,6399,0,4096,6420,0,4096,6395,0,4096,6363,0,4096,6356,0,4096,6403,0,4096,6401,0,4096,6386,0,4096,6350,0,4096,6397,0,4096,6587,0,4096,6419,0,4096,6365,0,4096,6360,0,4096,6400,0,4096,6404,0,4096,6387,0,4096,6353,0,4096,6401,0,4096,64,0x7f52604a0ec0,32768,32768,0,1411551767635712,1411551767656192 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f719d074ec0,0,3635368,2844,2844,0,3358869,2868,2868,0,4507800,2836,2836,0,4427655,2872,2872,0,3528702,2908,2908,0,4042385,2856,2856,0,3222489,2848,2848,0,4461160,2804,2804,0,3796362,2800,2800,0,3636483,2848,2848,0,4079095,2868,2868,0,4022898,2832,2832,0,3688662,2872,2872,0,3878807,2908,2908,0,3509431,2856,2856,0,3142952,2850,2850,0,3168535,2804,2804,0,3760235,2832,2832,0,3390587,2860,2860,0,4033999,2860,2860,0,3370259,2830,2830,0,3976984,2878,2878,0,3924020,2834,2834,0,4706973,2840,2840,0,4308399,2840,2840,0,3268498,2808,2808,0,3235184,2836,2836,0,3606911,2860,2860,0,4164092,2860,2860,0,3140833,2828,2828,0,3982134,2872,2872,0,4308084,2828,2828,64,0x7f5871864ec0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,0,40844,0,0,64,0x7f842c814ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,21863,0,2857,39450,0,70312.0,131072.0,0.0,45621.0,64,0x7f64e75d8ec0,0,184431,0,0,65536,63800,56,1680,64,0x7f01f2d00ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,116463987.0,59127715.0,0.0,64,0x7f6ecb88cec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,1983462.0,64,0x7fc1d67f8ec0,4096,0,456,0,4096,0,291,0,4096,0,2176,0,4096,0,727,0,4098,0,725,0,4097,0,1024,0,4096,0,71,0,4096,0,925,0,4096,0,0,0,4096,0,332,0,4096,0,729,0,4098,0,911,0,4096,0,185,0,4096,0,548,0,4096,0,1181,0,4096,0,155,0,4096,0,771,0,4096,0,828,0,4097,0,87,0,4098,0,541,0,4096,0,259,0,4096,0,295,0,4096,0,1833,0,4096,0,1038,0,4096,0,1152,0,4096,0,752,0,4097,0,372,0,4096,0,515,0,4096,0,66,0,4096,0,55,0,4096,0,21,0,4096,0,932,0,64,0x7feb1c338ec0,2167,4099,2170,6266,2163,4098,2165,6261,2166,4096,2166,6262,2131,4096,2131,6227,2155,4096,2155,6251,2126,4096,2126,6222,2198,4096,2198,6294,2205,4096,2205,6301,2205,4096,2205,6301,2167,4096,2167,6263,2167,4096,2167,6263,2170,4096,2170,6266,2131,4096,2131,6227,2157,4096,2157,6253,2128,4096,2128,6224,2200,4096,2200,6296,2197,4096,2197,6293,2192,4096,2192,6288,2191,4098,2193,6289,2165,4096,2165,6261,2224,4098,2226,6322,2159,4096,2159,6255,2142,4096,2142,6238,2143,4096,2143,6239,2141,4096,2141,6237,2196,4096,2196,6292,2191,4096,2191,6287,2194,4096,2194,6290,2163,4097,2164,6260,2166,4096,2166,6262,2156,4096,2156,6252,2148,4096,2148,6244,64,0x7f0c851d0ec0,114688,0,32768,32768,16384,16384,65536,49152,57344038.0,201189675.0,49212604.0,131072.0,0.0,469527.0,0,0,24792,3406.0,131086.0,0.0,26.0,64,0x7f2a26314ec0,0,0,0,1951688,0,0,0,2040120,1375,0,0,2515290,388,0,0,1924121,0,0,0,1959773,0,0,0,2144087,0,0,0,1601755,0,0,0,2227649,0,0,0,1515823,0,0,0,1712370,747,0,0,2281309,0,0,0,1754410,0,0,0,1631638,0,0,0,1959634,0,0,0,1945745,0,0,0,2101434,0,0,0,1485087,0,0,0,1663642,0,0,0,1597442,361,0,0,2320340,0,0,0,1479920,0,0,0,1769753,0,0,0,1643637,0,0,0,2016612,0,0,0,1590062,0,0,0,1353961,0,0,0,1457530,0,0,0,1782668,1,0,0,1962887,0,0,0,1575942,0,0,0,1874338,0,0,0,2035352,64,0x7f980b700ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131072.0,92644.0,45484.0,0.0,64,0x7f9e9e168ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32251,27914,9640,2417,0,39435,200735.0,0.0,69652.0,131083.0,64,0x7f80e4520ec0,0,0,0,56,0,65536,65536,0,64,0x7fbd96bb4ec0,19460332,18326981,789287,344064,2808219,0,0,163840,832.0,515136.0,0.0,524288.0,662213.0,32768.0,1020891,0,0,13732,91072.0,91072.0,0.0,91072.0,64,0x7fa1d1cb0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65550.0,0.0,0.0,0.0,64,0x7f9a5f924ec0,0,393216,163840,0,0,0,0,0,29953,0.0,0.0,0.0,32768.0,0.0,0.0,211.0,32768.0,4096,16384,302,41182,2074,0,56.0,11.0,0.0,200382.0,64,0x7ff854d0cec0,332936,217335,16384,0,16384,16384,32768,49152,41616,41616,3122366.0,2426905.0,4865.0,361077.0,1765505.0,0.0,2413768.0,2104530.0,332928,227334,41616,0,41616,0,1331712.0,770089.0,0.0,0.0,64,0x7f6ca7ed0ec0,6275,0,4096,6265,0,4096,6270,0,4096,6315,0,4096,6256,0,4096,6282,0,4096,6280,0,4096,6295,0,4096,6297,0,4096,6284,0,4096,6266,0,4096,6267,0,4096,6316,0,4096,6258,0,4096,6284,0,4096,6278,0,4096,6276,0,4096,6303,0,4096,6319,0,4096,6272,0,4096,6287,0,4096,6292,0,4096,6259,0,4096,6244,0,4096,6247,0,4096,6279,0,4096,6308,0,4096,6325,0,4096,6270,0,4096,6288,0,4096,6301,0,4096,6264,0,4096,64,0x7f52604a0ec0,32768,32768,0,1411551767749472,1411551767765792 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,1048576,256,0,0,8,0,16,64,0x7f719d074ec0,0,4893434,2842,2842,0,3008209,2884,2884,0,3693531,2840,2840,0,4755946,2844,2844,0,3066626,2916,2916,0,3804873,2868,2868,0,3252142,2864,2864,0,4476300,2820,2820,0,2954350,2820,2820,0,4062496,2840,2840,0,3474505,2880,2880,0,3357615,2840,2840,0,4920610,2840,2840,0,3165935,2920,2920,0,3358292,2868,2868,0,3102609,2864,2864,0,3416702,2784,2784,0,3889266,2832,2832,0,3431023,2872,2872,0,3536202,2872,2872,0,3319281,2848,2848,0,3611600,2872,2872,0,4564855,2852,2852,0,3948416,2848,2848,0,4021456,2846,2846,0,3292413,2784,2784,0,2882639,2832,2832,0,3946100,2860,2860,0,3749723,2872,2872,0,2710590,2848,2848,0,3573893,2872,2872,0,4205309,2860,2860,64,0x7f5871864ec0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,0,40789,0,0,64,0x7f842c814ec0,0,65536,32768,0,0,0,16384,16384,0.0,0.0,0.0,524288.0,0.0,0.0,0.0,20454,0,2734,38217,0,70013.0,131072.0,0.0,45741.0,64,0x7f64e75d8ec0,0,182947,0,0,65536,63800,56,1680,64,0x7f01f2d00ec0,131072,0,0,0,0,0,0,0,0.0,0.0,0.0,0.0,16384,0,119691070.0,60044646.0,0.0,64,0x7f6ecb88cec0,0,0,0,0,0,0,0,56,131072.0,131072.0,0.0,2007495.0,64,0x7fc1d67f8ec0,4096,0,1430,0,4096,0,786,0,4096,0,706,0,4096,0,110,0,4098,0,877,0,4097,0,422,0,4096,0,723,0,4096,0,701,0,4096,0,605,0,4096,0,935,0,4096,0,516,0,4098,0,596,0,4096,0,203,0,4096,0,464,0,4096,0,1484,0,4096,0,281,0,4096,0,593,0,4096,0,646,0,4097,0,208,0,4098,0,1107,0,4096,0,0,0,4096,0,460,0,4096,0,440,0,4096,0,744,0,4096,0,2052,0,4096,0,322,0,4097,0,568,0,4096,0,659,0,4096,0,431,0,4096,0,719,0,4096,0,0,0,4096,0,767,0,64,0x7feb1c338ec0,2191,4099,2194,6290,2198,4098,2200,6296,2227,4096,2227,6323,2207,4096,2207,6303,2195,4096,2195,6291,2175,4096,2175,6271,2169,4096,2169,6265,2181,4096,2181,6277,2183,4096,2183,6279,2196,4096,2196,6292,2203,4096,2203,6299,2229,4096,2229,6325,2209,4096,2209,6305,2198,4096,2198,6294,2174,4096,2174,6270,2168,4096,2168,6264,2192,4096,2192,6288,2193,4096,2193,6289,2166,4098,2168,6264,2187,4096,2187,6283,2250,4098,2252,6348,2209,4096,2209,6305,2185,4096,2185,6281,2197,4096,2197,6293,2195,4096,2195,6291,2192,4096,2192,6288,2191,4096,2191,6287,2169,4096,2169,6265,2189,4097,2190,6286,2201,4096,2201,6297,2210,4096,2210,6306,2187,4096,2187,6283,64,0x7f0c851d0ec0,114688,0,32768,32768,16384,16384,65536,49152,57372751.0,203209514.0,46896816.0,131072.0,0.0,520441.0,0,0,24918,6541.0,131087.0,0.0,28.0,64,0x7f2a26314ec0,0,0,0,1925466,4,0,0,1901532,0,0,0,1769391,78,0,0,2063862,49,0,0,1996144,1302,0,0,2244795,0,0,0,1567085,69,0,0,1956879,1,0,0,1666303,0,0,0,1671082,0,0,0,1509605,0,0,0,1696856,1076,0,0,2560896,0,0,0,1888969,724,0,0,2078267,0,0,0,1859150,0,0,0,1746326,0,0,0,1616154,0,0,0,1541765,0,0,0,1842461,0,0,0,1516028,108,0,0,2160627,7,0,0,1691966,0,0,0,1716188,0,0,0,1637841,0,0,0,1746015,0,0,0,1918312,0,0,0,1645271,0,0,0,1677917,0,0,0,1485077,0,0,0,1510985,0,0,0,1731264,64,0x7f980b700ec0,10485760,65536,0,0,0,16384,0,0,131072.0,0.0,0.0,0.0,32768.0,16384.0,0,0,131081.0,99736.0,45511.0,0.0,64,0x7f9e9e168ec0,0,0,0,0,0,0,0,114688,2097152.0,2097152.0,1048576.0,1048576.0,0.0,0.0,0.0,16384.0,32796,28321,9652,2427,0,39845,201111.0,0.0,70029.0,131082.0,64,0x7f80e4520ec0,0,0,0,56,0,65536,65536,0,64,0x7fbd96bb4ec0,18674882,17567758,763060,344064,2706223,0,0,163840,832.0,515148.0,0.0,524288.0,630567.0,32768.0,915443,0,0,13879,91113.0,91113.0,0.0,91113.0,64,0x7fa1d1cb0ec0,0,0,1048576,0,0,0,0,0,0.0,0.0,0.0,0.0,16384.0,0.0,0,32768,65552.0,0.0,0.0,0.0,64,0x7f9a5f924ec0,0,393216,163840,0,0,0,0,0,30614,0.0,0.0,0.0,32768.0,0.0,0.0,207.0,32768.0,4096,16384,302,41805,1941,0,56.0,11.0,0.0,200333.0,64,0x7ff854d0cec0,332832,226984,16384,0,16384,16384,32768,49152,41603,41603,3227887.0,2522631.0,4209.0,383730.0,1781211.0,0.0,2511870.0,2205061.0,332824,236399,41603,0,41603,0,1331296.0,778074.0,0.0,0.0,64,0x7f6ca7ed0ec0,6283,0,4096,6303,0,4096,6273,0,4096,6293,0,4096,6279,0,4096,6274,0,4096,6280,0,4096,6297,0,4096,6295,0,4096,6287,0,4096,6307,0,4096,6278,0,4096,6299,0,4096,6280,0,4096,6279,0,4096,6277,0,4096,6285,0,4096,6283,0,4096,6281,0,4096,6284,0,4096,6295,0,4096,6306,0,4096,6263,0,4096,6303,0,4096,6306,0,4096,6283,0,4096,6280,0,4096,6277,0,4096,6283,0,4096,6298,0,4096,6311,0,4096,6267,0,4096,64,0x7f52604a0ec0,32768,32768,0,1411551767786592,1411551767802112 diff --git a/tests/workloads/vcopy/MI200/roofline.csv b/tests/workloads/vcopy/MI200/roofline.csv index f453db4916..e2e8aae3f9 100644 --- a/tests/workloads/vcopy/MI200/roofline.csv +++ b/tests/workloads/vcopy/MI200/roofline.csv @@ -1,5 +1,5 @@ device,HBMBw,HBMBwLow,hbmBwHigh,L2Bw,L2BwLow,L2BwHigh,L1Bw,L1BwLow,L1BwHigh,LDSBw,LDSBwLow,LDSBwHigh,FP32Flops,FP32FlopsLow,FP32FlopsHigh,FP64Flops,FP64FlopsLow,FP64FlopsHigh,MFMABF16Flops,MFMABF16FlopsLow,MFMABF16FlopsHigh,MFMAF16Flops,MFMAF16FlopsLow,MFMAF16FlopsHigh,MFMAF32Flops,MFMAF32FlopsLow,MFMAF32FlopsHigh,MFMAF64Flops,MFMAF64FlopsLow,MFMAF64FlopsHigh,MFMAI8Ops,MFMAFI8OpsLow,MFMAI8OpsHigh -0,1388.856,1388.2861,1389.4258,5015.5361,5012.5439,5018.5283,9223.8896,9223.2637,9224.5156,17835.65,17830.1,17841.201,20932.104,20872.141,20992.066,20263.07,20262.441,20263.699,170383.09,170378.7,170387.48,164842.7,164838.19,164847.22,41412.672,41412.055,41413.289,41469,41468.379,41469.621,166307.77,165820.33,166795.2 -1,1389.4937,1388.932,1390.0553,5027.6265,5025.5444,5029.7085,9235.3457,9234.5566,9236.1348,17917.186,17912.863,17921.508,20977.213,20911.021,21043.404,20299.027,20298.414,20299.641,170859.36,170856.08,170862.64,165131.33,165126.56,165136.09,41488.863,41488.031,41489.695,41544.867,41544.039,41545.695,166884.27,166881.91,166886.62 -2,1389.1772,1388.5885,1389.766,5037.2246,5035.0132,5039.436,9263.832,9263.082,9264.582,18021.938,18020.277,18023.598,21052.32,21052.016,21052.625,20359.711,20359.244,20360.178,171164.77,171161.05,171168.48,165542.94,165539.05,165546.83,41585.906,41584.66,41587.152,41651.629,41650.547,41652.711,167004.73,166418.69,167590.78 -3,1389.0337,1388.4918,1389.5756,5031.668,5030.1841,5033.1519,9240.9766,9240.3418,9241.6113,17894.789,17893.949,17895.629,21033.523,21032.922,21034.125,20312.473,20311.721,20313.225,171012.7,171009.16,171016.25,165219.06,165215.48,165222.64,41441.723,41288.957,41594.488,41583.414,41582.887,41583.941,167015.88,167013.72,167018.03 +0,1388.9302,1388.3835,1389.4768,5018.2891,5015.416,5021.1621,9226.7266,9226.168,9227.2852,17717.834,17714.895,17720.773,20941.971,20881.785,21002.156,20272.537,20271.938,20273.137,170483.16,170480.25,170486.06,164938.17,164933.98,164942.36,41438.68,41438.27,41439.09,41497.562,41496.836,41498.289,166402.27,165911.17,166893.36 +1,1389.3043,1388.6895,1389.9192,5029.6997,5027.6914,5031.708,9239.2627,9238.5391,9239.9863,18243.783,18241.363,18246.203,20985.506,20918.434,21052.578,20301.832,20301.094,20302.57,170928.06,170923.66,170932.47,165162.06,165158.09,165166.03,41494.691,41493.625,41495.758,41550.176,41549.141,41551.211,166923.81,166920.55,166927.08 +2,1389.0227,1388.4105,1389.6349,5036.6968,5034.5093,5038.8843,9263.2725,9262.6641,9263.8809,18220.432,18219.43,18221.434,21053.373,21052.924,21053.822,20354.846,20354.256,20355.436,171150.41,171147,171153.81,165537.12,165534.03,165540.22,41587.383,41586.57,41588.195,41645.191,41644.094,41646.289,166970.84,166374.36,167567.33 +3,1389.0236,1388.4886,1389.5585,5033.541,5031.9014,5035.1807,9237.8057,9237.0996,9238.5117,18326.717,18325.787,18327.646,21032.83,21032.598,21033.062,20308.371,20307.881,20308.861,171040.98,171036.05,171045.92,165174.33,165170.09,165178.56,41430.328,41276.879,41583.777,41578.465,41577.258,41579.672,166994.86,166991.23,166998.48 diff --git a/tests/workloads/vcopy/MI200/sysinfo.csv b/tests/workloads/vcopy/MI200/sysinfo.csv index 99378d7865..a382607e3d 100644 --- a/tests/workloads/vcopy/MI200/sysinfo.csv +++ b/tests/workloads/vcopy/MI200/sysinfo.csv @@ -1,2 +1,2 @@ workload_name,command,ip_blocks,timestamp,version,hostname,cpu_model,sbios,linux_distro,linux_kernel_version,amd_gpu_kernel_version,cpu_memory,gpu_memory,rocm_version,vbios,compute_partition,memory_partition,gpu_model,gpu_arch,gpu_l1,gpu_l2,cu_per_gpu,simd_per_cu,se_per_gpu,wave_size,workgroup_max_size,max_waves_per_cu,max_sclk,max_mclk,cur_sclk,cur_mclk,total_l2_chan,lds_banks_per_cu,sqc_per_gpu,pipes_per_gpu,hbm_bw,num_xcd -vcopy,./sample/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 07 Mar 2024 03:04:49 PM (CST),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 +path,./tests/vcopy -n 1048576 -b 256 -i 3,SQ|LDS|SQC|TA|TD|TCP|TCC|SPI|CPC|CPF|roofline,Thu 21 Mar 2024 04:16:46 PM (CDT),2,t007-002.hpcfund,AMD EPYC 7V13 64-Core Processor,American Megatrends Inc.0602,Rocky Linux 9.1 (Blue Onyx),5.14.0-162.18.1.el9_1.x86_64,,527650760,,6.0.2-115,113-D67301-059,NA,NA,MI200,gfx90a,16,8192,104,4,8,64,1024,32,1700,1600,1700,1600,32,32,56,4,1638.4,1 diff --git a/tests/workloads/vcopy/MI200/timestamps.csv b/tests/workloads/vcopy/MI200/timestamps.csv index c8692b7a32..c7262b43a5 100644 --- a/tests/workloads/vcopy/MI200/timestamps.csv +++ b/tests/workloads/vcopy/MI200/timestamps.csv @@ -1,4 +1,4 @@ Dispatch_ID,Kernel_Name,GPU_ID,queue-id,queue-index,pid,tid,Grid_Size,Workgroup_Size,LDS_Per_Workgroup,Scratch_Per_Workitem,Arch_VGPR,Accum_VGPR,SGPR,wave_size,sig,obj,DispatchNs,Start_Timestamp,End_Timestamp,CompleteNs -0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,399295,399295,1048576,256,0,0,8,0,16,64,0x0,0x7fcc74b94ec0,201235827780917,201235827806132,201235827826452,201235827839077 -1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,399295,399295,1048576,256,0,0,8,0,16,64,0x0,0x7fcc74b94ec0,201235827837845,201235827928052,201235827944532,201235827946120 -2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,399295,399295,1048576,256,0,0,8,0,16,64,0x0,0x7fcc74b94ec0,201235827955808,201235827965492,201235827981172,201235827982789 +0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,0,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767610475,1411551767635712,1411551767656192,1411551767669456 +1,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,2,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767667252,1411551767749472,1411551767765792,1411551767767061 +2,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2,0,4,4110591,4110591,1048576,256,0,0,8,0,16,64,0x0,0x7fc6de634ec0,1411551767776669,1411551767786592,1411551767802112,1411551767803299