Pytest add mi200 to analyze workloads (#334)

* Updated links in documentation. (#328)

Updated to reflect new GitHub organization.
Fixed broken links to GitHub pages.

Signed-off-by: David Galiffi <David.Galiffi@amd.com>

* update branch for 2.x documentation builds

Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>

* update checkout action and use concurrency instead of cancel-workflow-action

Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>

* test addition of user option for container launch

Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>

* remove --user option for container, try chown instead

Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>

* fixing yaml syntax

Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>

* reorder job step - start with checkout

Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>

* restore missing run directive

Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>

* Update workloads to include log.txt
Add missing MI200 workloads

Signed-off-by: Jose Santos <josantos@amd.com>

* Signed-off-by: Jose Santos <josantos@amd.com>
Add vcopy workload for tests

* Change exit codes for caught failures

Signed-off-by: Jose Santos <josantos@amd.com>

* reformat

Signed-off-by: Jose Santos <josantos@amd.com>

* Add pytest-xdist for pytest -n

Signed-off-by: Jose Santos <josantos@amd.com>

---------

Signed-off-by: David Galiffi <David.Galiffi@amd.com>
Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>
Signed-off-by: Jose Santos <josantos@amd.com>
Co-authored-by: David Galiffi <David.Galiffi@amd.com>
Co-authored-by: Karl W. Schulz <karl.schulz@amd.com>
这个提交包含在:
JoseSantosAMD
2024-03-25 10:20:31 -05:00
提交者 Cole Ramos
父节点 482fd6f2ca
当前提交 da506ad9b5
修改 1122 个文件,包含 37938 行新增3563 行删除
+1 -1
查看文件
@@ -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
+1 -1
查看文件
@@ -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
+605 -238
查看文件
@@ -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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 171832 1267481 171832 1267481 1048576 256 0 0 8 8 16 64 0x0 0x7f261105ce80 0x7f0eb8168ec0 48069 120424 48069 120424 16384 65536 12763 13369 1638700 1717376 194272922419343 1410193234401133 194285066464535 1410204895308401 194285066489175 1410204895332881 194272930391948 1410193242172960
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 171832 1267481 171832 1267481 1048576 256 0 0 8 8 16 64 0x0 0x7f261105ce80 0x7f0eb8168ec0 43546 46836 43546 46836 16384 65536 8369 8058 1048580 1048584 194272930413559 1410193242195944 194285066682455 1410204895428561 194285066701335 1410204895447761 194272930732383 1410193242512571
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 171832 1267481 171832 1267481 1048576 256 0 0 8 8 16 64 0x0 0x7f261105ce80 0x7f0eb8168ec0 43715 43828 43715 43828 16384 65536 8176 7998 1048580 1048588 194272930764153 1410193242544701 194285066722455 1410204895469361 194285066741335 1410204895488081 194272930942791 1410193242740050
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 172017 1267667 172017 1267667 1048576 256 0 0 8 8 16 64 0x0 0x7ff6bfca6e80 0x7f9eef0c0ec0 0 0 0 194273420605668 1410193715977501 194285066464535 1410204895308401 194285066489175 1410204895332881 194273428330044 1410193723553168
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 172017 1267667 172017 1267667 1048576 256 0 0 8 8 16 64 0x0 0x7ff6bfca6e80 0x7f9eef0c0ec0 0 0 0 194273428350383 1410193723574359 194285066682455 1410204895428561 194285066701335 1410204895447761 194273428660279 1410193723871880
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 172017 1267667 172017 1267667 1048576 256 0 0 8 8 16 64 0x0 0x7ff6bfca6e80 0x7f9eef0c0ec0 0 0 0 194273428688593 1410193723900664 194285066722455 1410204895469361 194285066741335 1410204895488081 194273428860549 1410193724075433
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 172202 1267850 172202 1267850 1048576 256 0 0 8 8 16 64 0x0 0x7f80dbc10e80 0x7f29fc24cec0 65536 198372 217080 25466512 27847144 194273910775706 1410194196106960 194285066464535 1410204895308401 194285066489175 1410204895332881 194273918668841 1410194203543485
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 172202 1267850 172202 1267850 1048576 256 0 0 8 8 16 64 0x0 0x7f80dbc10e80 0x7f29fc24cec0 65536 178410 201340 22861520 25741952 194273918687927 1410194203562862 194285066682455 1410204895428561 194285066701335 1410204895447761 194273919011510 1410194203889688
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 172202 1267850 172202 1267850 1048576 256 0 0 8 8 16 64 0x0 0x7f80dbc10e80 0x7f29fc24cec0 65536 178762 200810 22853312 25639968 194273919039884 1410194203918102 194285066722455 1410204895469361 194285066741335 1410204895488081 194273919232939 1410194204085558
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 172388 1268033 172388 1268033 1048576 256 0 0 8 8 16 64 0x0 0x7f91b7fd6e80 0x7fedffc74ec0 32768 645046 609944 82562784 78081400 194274390775457 1410194670380245 194285066464535 1410204895308401 194285066489175 1410204895332881 194274398576077 1410194678086308
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 172388 1268033 172388 1268033 1048576 256 0 0 8 8 16 64 0x0 0x7f91b7fd6e80 0x7fedffc74ec0 32768 656009 673533 83967432 86217068 194274398595203 1410194678107769 194285066682455 1410204895428561 194285066701335 1410204895447761 194274398895572 1410194678459913
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 172388 1268033 172388 1268033 1048576 256 0 0 8 8 16 64 0x0 0x7f91b7fd6e80 0x7fedffc74ec0 32768 654851 625490 83819532 80060980 194274398924006 1410194678486053 194285066722455 1410204895469361 194285066741335 1410204895488081 194274399099017 1410194678661503
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 172574 1268218 172574 1268218 1048576 256 0 0 8 8 16 64 0x0 0x7f63ef9aae80 0x7fa94f5d4ec0 48374 48952 48374 48952 16676 18068 387000 391624 16384 25449189 25128672 235661 238750 0 102288864 101043548 194274879224637 1410195147235800 194285066464535 1410204895308401 194285066489175 1410204895332881 194274887852072 1410195154883924
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 172574 1268218 172574 1268218 1048576 256 0 0 8 8 16 64 0x0 0x7f63ef9aae80 0x7fa94f5d4ec0 42333 42936 42333 42936 13500 13804 338672 343496 16384 24694478 24583226 228632 234692 0 99275804 98863936 194274887882279 1410195154913951 194285066682455 1410204895428561 194285066701335 1410204895447761 194274888171918 1410195155354471
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 172574 1268218 172574 1268218 1048576 256 0 0 8 8 16 64 0x0 0x7f63ef9aae80 0x7fa94f5d4ec0 42877 42192 42877 42192 13541 13020 343024 337544 16384 24621688 24104198 230950 233666 0 98996648 96939712 194274888210190 1410195155392643 194285066722455 1410204895469361 194285066741335 1410204895488081 194274888401232 1410195155592380
+679
查看文件
@@ -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]
文件差异因一行或多行过长而隐藏
@@ -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
1 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
2 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) Thu 21 Mar 2024 03:54:18 PM (CDT) 2 t008-007.hpcfund 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 527651100 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 175921 1271546 175921 1271546 1048576 256 0 0 8 8 16 64 0x0 0x7ff832f9ae80 0x7facae2fcec0 194285066439120 1410204895282038 194285066464535 1410204895308401 194285066489175 1410204895332881 194285066502310 1410204895343735
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 175921 1271546 175921 1271546 1048576 256 0 0 8 8 16 64 0x0 0x7ff832f9ae80 0x7facae2fcec0 194285066502350 1410204895345248 194285066682455 1410204895428561 194285066701335 1410204895447761 194285066702839 1410204895449153
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 175921 1271546 175921 1271546 1048576 256 0 0 8 8 16 64 0x0 0x7ff832f9ae80 0x7facae2fcec0 194285066713930 1410204895459924 194285066722455 1410204895469361 194285066741335 1410204895488081 194285066742634 1410204895489490
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 330344 4154776 330344 4154776 1048576 256 0 0 8 0 16 64 0x0 0x7fe6cf348ec0 0x7f4aeac78ec0 27379 28399 27379 28399 16384 65536 13546 16539 1530804 1859828 199109067732799 1412689608475887 199121780771567 1412702536508356 199121780791247 1412702536528996 199109083780798 1412689624744624
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 330344 4154776 330344 4154776 1048576 256 0 0 8 0 16 64 0x0 0x7fe6cf348ec0 0x7f4aeac78ec0 40641 41854 40641 41854 16384 65536 9422 9149 1048620 1048652 199109083800004 1412689624764922 199121780810127 1412702536548036 199121780825807 1412702536563556 199109084104139 1412689625202329
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 330344 4154776 330344 4154776 1048576 256 0 0 8 0 16 64 0x0 0x7fe6cf348ec0 0x7f4aeac78ec0 40214 42687 40214 42687 16384 65536 9321 9446 1048756 1048640 199109084143764 1412689625231735 199121780890127 1412702536625636 199121780906607 1412702536642116 199109084308516 1412689625401916
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 330545 4154974 330545 4154974 1048576 256 0 0 8 0 16 64 0x0 0x7f3c42f94ec0 0x7f1046a28ec0 0 0 0 199109550821338 1412690095463857 199121780771567 1412702536508356 199121780791247 1412702536528996 199109566789335 1412690111629429
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 330545 4154974 330545 4154974 1048576 256 0 0 8 0 16 64 0x0 0x7f3c42f94ec0 0x7f1046a28ec0 0 0 0 199109566805174 1412690111650128 199121780810127 1412702536548036 199121780825807 1412702536563556 199109567096836 1412690111919096
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 330545 4154974 330545 4154974 1048576 256 0 0 8 0 16 64 0x0 0x7f3c42f94ec0 0x7f1046a28ec0 0 0 0 199109567123557 1412690111945456 199121780890127 1412702536625636 199121780906607 1412702536642116 199109567286696 1412690112092594
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 330728 4155175 330728 4155175 1048576 256 0 0 8 0 16 64 0x0 0x7fc8f8a6cec0 0x7fd9f40c4ec0 65536 211460 172670 23579520 19277760 199110030597901 1412690576047496 199121780771567 1412702536508356 199121780791247 1412702536528996 199110046727484 1412690592443443
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 330728 4155175 330728 4155175 1048576 256 0 0 8 0 16 64 0x0 0x7fc8f8a6cec0 0x7fd9f40c4ec0 65536 254912 228700 28465096 25581136 199110046748423 1412690592461567 199121780810127 1412702536548036 199121780825807 1412702536563556 199110047009096 1412690592741416
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 330728 4155175 330728 4155175 1048576 256 0 0 8 0 16 64 0x0 0x7fc8f8a6cec0 0x7fd9f40c4ec0 65536 258838 231114 28871464 25926712 199110047035506 1412690592767165 199121780890127 1412702536625636 199121780906607 1412702536642116 199110047184308 1412690592915886
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 330929 4155361 330929 4155361 1048576 256 0 0 8 0 16 64 0x0 0x7fd12bbd8ec0 0x7f9045bb8ec0 32768 288902 290637 32346476 32556924 199110514009110 1412691060480394 199121780771567 1412702536508356 199121780791247 1412702536528996 199110529778261 1412691076529415
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 330929 4155361 330929 4155361 1048576 256 0 0 8 0 16 64 0x0 0x7fd12bbd8ec0 0x7f9045bb8ec0 32768 593947 589721 66524552 66052460 199110529795433 1412691076546758 199121780810127 1412702536548036 199121780825807 1412702536563556 199110530092144 1412691076842818
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 330929 4155361 330929 4155361 1048576 256 0 0 8 0 16 64 0x0 0x7fd12bbd8ec0 0x7f9045bb8ec0 32768 602236 574435 67452520 64354132 199110530118254 1412691076869588 199121780890127 1412702536625636 199121780906607 1412702536642116 199110530290219 1412691077020423
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 331115 4155559 331115 4155559 1048576 256 0 0 8 0 16 64 0x0 0x7f16a9730ec0 0x7f2e47d90ec0 27492 27782 27492 27782 10876 11060 219944 222264 16384 10773590 10980955 127834 128903 0 43600528 44430920 199110993347043 1412691542352890 199121780771567 1412702536508356 199121780791247 1412702536528996 199111009505921 1412691558586810
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 331115 4155559 331115 4155559 1048576 256 0 0 8 0 16 64 0x0 0x7f16a9730ec0 0x7f2e47d90ec0 41046 42364 41046 42364 13175 13501 328376 338920 16384 19783221 20566692 224811 235190 0 79611516 82737616 199111009533263 1412691558614052 199121780810127 1412702536548036 199121780825807 1412702536563556 199111009819264 1412691558909250
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 331115 4155559 331115 4155559 1048576 256 0 0 8 0 16 64 0x0 0x7f16a9730ec0 0x7f2e47d90ec0 40621 40646 40621 40646 11924 12686 324976 325176 16384 19553416 19387932 225262 222546 0 78707700 78034296 199111009854681 1412691558944307 199121780890127 1412702536625636 199121780906607 1412702536642116 199111010019924 1412691559104820
+739
查看文件
@@ -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...
文件差异因一行或多行过长而隐藏
@@ -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
1 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
2 0 1388.6548 1388.7948 1388.108 1388.2125 1389.2015 1389.3771 5015.9297 5016.1738 5012.8184 5013.2036 5019.041 5019.144 9223.8145 9226.4229 9223.0537 9225.7852 9224.5752 9227.0605 18052.502 17715.307 18051.623 17712.113 18053.381 17718.5 20935.658 20942.453 20875.303 20882.1 20996.014 21002.807 20266.73 20272.682 20266.039 20272.182 20267.422 20273.182 170456.62 170487.92 170450.44 170484.22 170462.81 170491.62 164889.83 164932.06 164885.14 164926.69 164894.52 164937.44 41426.273 41438.844 41425.676 41438.195 41426.871 41439.492 41480.551 41498.918 41480.051 41498.344 41481.051 41499.492 166346.09 166413.58 165855.02 165921.97 166837.17 166905.19
@@ -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
1 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
2 device_filter ./sample/vcopy -n 1048576 -b 256 -i 3 ./tests/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) 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 334902 4159385 334902 4159385 1048576 256 0 0 8 0 16 64 0x0 0x7fc789a84ec0 0x7f7aee850ec0 199121780746738 1412702536482286 199121780771567 1412702536508356 199121780791247 1412702536528996 199121780807012 1412702536542951
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 334902 4159385 334902 4159385 1048576 256 0 0 8 0 16 64 0x0 0x7fc789a84ec0 0x7f7aee850ec0 199121780801932 1412702536540095 199121780810127 1412702536548036 199121780825807 1412702536563556 199121780887234 1412702536623202
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 334902 4159385 334902 4159385 1048576 256 0 0 8 0 16 64 0x0 0x7fc789a84ec0 0x7f7aee850ec0 199121780836327 1412702536574069 199121780890127 1412702536625636 199121780906607 1412702536642116 199121780907502 1412702536643421
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 163106 1258700 163106 1258700 1048576 256 0 0 8 8 16 64 0x0 0x7fd0d59ece80 0x7f801c880ec0 47824 48936 47824 48936 16384 65536 14415 14799 1841604 1880476 194245701996654 1410167129401874 194257894802798 1410178815497695 194257894826478 1410178815522495 194245709757699 1410167137099481
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 163106 1258700 163106 1258700 1048576 256 0 0 8 8 16 64 0x0 0x7fd0d59ece80 0x7f801c880ec0 42607 42186 42607 42186 16384 65536 8172 8222 1048580 1048592 194245709780272 1410167137124759 194257894909678 1410178815542975 194257894929198 1410178815562015 194245710148639 1410167137378738
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 163106 1258700 163106 1258700 1048576 256 0 0 8 8 16 64 0x0 0x7fd0d59ece80 0x7f801c880ec0 42359 42316 42359 42316 16384 65536 8301 8221 1048580 1048584 194245710180850 1410167137410247 194257894949838 1410178815623775 194257894968558 1410178815642655 194245710367043 1410167137580208
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 163295 1258888 163295 1258888 1048576 256 0 0 8 8 16 64 0x0 0x7f1c0fd10e80 0x7fe5d42a0ec0 0 0 0 194246201989340 1410167602796952 194257894802798 1410178815497695 194257894826478 1410178815522495 194246209682066 1410167610304281
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 163295 1258888 163295 1258888 1048576 256 0 0 8 8 16 64 0x0 0x7f1c0fd10e80 0x7fe5d42a0ec0 0 0 0 194246209701843 1410167610324359 194257894909678 1410178815542975 194257894929198 1410178815562015 194246209982224 1410167610647999
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 163295 1258888 163295 1258888 1048576 256 0 0 8 8 16 64 0x0 0x7f1c0fd10e80 0x7fe5d42a0ec0 0 0 0 194246210010568 1410167610676222 194257894949838 1410178815623775 194257894968558 1410178815642655 194246210167986 1410167610853958
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 163481 1259074 163481 1259074 1048576 256 0 0 8 8 16 64 0x0 0x7f41294aee80 0x7fb789834ec0 65536 202308 202864 25952544 26025240 194246693370130 1410168079709865 194257894802798 1410178815497695 194257894826478 1410178815522495 194246701328779 1410168087360905
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 163481 1259074 163481 1259074 1048576 256 0 0 8 8 16 64 0x0 0x7f41294aee80 0x7fb789834ec0 65536 182670 174246 23344896 22311240 194246701348828 1410168087381153 194257894909678 1410178815542975 194257894929198 1410178815562015 194246701641622 1410168087724951
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 163481 1259074 163481 1259074 1048576 256 0 0 8 8 16 64 0x0 0x7f41294aee80 0x7fb789834ec0 65536 181360 172432 23270400 22133472 194246701670366 1410168087753315 194257894949838 1410178815623775 194257894968558 1410178815642655 194246701840689 1410168087940107
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 163664 1259257 163664 1259257 1048576 256 0 0 8 8 16 64 0x0 0x7f0703804e80 0x7efca8c4cec0 32768 645357 619812 82598164 79322476 194247183554014 1410168553148666 194257894802798 1410178815497695 194257894826478 1410178815522495 194247191243955 1410168560839471
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 163664 1259257 163664 1259257 1048576 256 0 0 8 8 16 64 0x0 0x7f0703804e80 0x7efca8c4cec0 32768 670028 672501 85765020 86073620 194247191265515 1410168560860901 194257894909678 1410178815542975 194257894929198 1410178815562015 194247191518214 1410168561160366
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 163664 1259257 163664 1259257 1048576 256 0 0 8 8 16 64 0x0 0x7f0703804e80 0x7efca8c4cec0 32768 644220 653970 82464252 83703936 194247191549022 1410168561188710 194257894949838 1410178815623775 194257894968558 1410178815642655 194247191732850 1410168561366956
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 163849 1259442 163849 1259442 1048576 256 0 0 8 8 16 64 0x0 0x7f24c9b52e80 0x7fbda6074ec0 48152 48635 48152 48635 17278 18326 385224 389088 16384 24999057 24577632 233984 235420 0 100494368 98846104 194247678463586 1410169028962927 194257894802798 1410178815497695 194257894826478 1410178815522495 194247686158065 1410169036445289
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 163849 1259442 163849 1259442 1048576 256 0 0 8 8 16 64 0x0 0x7f24c9b52e80 0x7fbda6074ec0 42999 41605 42999 41605 13485 13181 344000 332848 16384 25054375 23608799 233600 226270 0 100720288 94967360 194247686185978 1410169036474975 194257894909678 1410178815542975 194257894929198 1410178815562015 194247686516484 1410169036807712
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 163849 1259442 163849 1259442 1048576 256 0 0 8 8 16 64 0x0 0x7f24c9b52e80 0x7fbda6074ec0 43151 41728 43151 41728 13780 13800 345216 333832 16384 23923902 23454903 232092 231784 0 96192684 94343436 194247686554565 1410169036845844 194257894949838 1410178815623775 194257894968558 1410178815642655 194247686738744 1410169037034279
@@ -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]
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2
文件差异因一行或多行过长而隐藏
@@ -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
1 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
2 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) Thu 21 Mar 2024 03:53:52 PM (CDT) 2 t008-007.hpcfund 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 527651100 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 167187 1262821 167187 1262821 1048576 256 0 0 8 8 16 64 0x0 0x7f75a08c8e80 0x7f366fb34ec0 194257894775994 1410178815466976 194257894802798 1410178815497695 194257894826478 1410178815522495 194257894838072 1410178815537880
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 167187 1262821 167187 1262821 1048576 256 0 0 8 8 16 64 0x0 0x7f75a08c8e80 0x7f366fb34ec0 194257894839254 1410178815534784 194257894909678 1410178815542975 194257894929198 1410178815562015 194257894930367 1410178815636256
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 167187 1262821 167187 1262821 1048576 256 0 0 8 8 16 64 0x0 0x7f75a08c8e80 0x7f366fb34ec0 194257894941187 1410178815573177 194257894949838 1410178815623775 194257894968558 1410178815642655 194257894969812 1410178815648288
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 320367 4144746 320367 4144746 1048576 256 0 0 8 0 16 64 0x0 0x7fc46ea24ec0 0x7ff86800cec0 27912 27678 27912 27678 16384 65536 13514 13718 1516880 1552004 198989177854165 1412569418785866 199001894935363 1412582414437599 199001894955843 1412582414457599 198989193725590 1412569434785613
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 320367 4144746 320367 4144746 1048576 256 0 0 8 0 16 64 0x0 0x7fc46ea24ec0 0x7ff86800cec0 41103 41715 41103 41715 16384 65536 9163 9728 1048712 1048636 198989193746269 1412569434805591 199001895045923 1412582414476479 199001895062403 1412582414491999 198989194045705 1412569435124494
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 320367 4144746 320367 4144746 1048576 256 0 0 8 0 16 64 0x0 0x7fc46ea24ec0 0x7ff86800cec0 42248 42139 42248 42139 16384 65536 9321 9154 1048688 1048652 198989194074961 1412569435153789 199001895083363 1412582414551359 199001895098883 1412582414567679 198989194247106 1412569435328620
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 320552 4144947 320552 4144947 1048576 256 0 0 8 0 16 64 0x0 0x7fd2d0168ec0 0x7f93fef18ec0 0 0 0 198989659429121 1412569904374106 199001894935363 1412582414437599 199001894955843 1412582414457599 198989675029403 1412569920255991
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 320552 4144947 320552 4144947 1048576 256 0 0 8 0 16 64 0x0 0x7fd2d0168ec0 0x7f93fef18ec0 0 0 0 198989675045944 1412569920277472 199001895045923 1412582414476479 199001895062403 1412582414491999 198989675468113 1412569920573351
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 320552 4144947 320552 4144947 1048576 256 0 0 8 0 16 64 0x0 0x7fd2d0168ec0 0x7f93fef18ec0 0 0 0 198989675494523 1412569920599611 199001895083363 1412582414551359 199001895098883 1412582414567679 198989675627705 1412569920753051
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 320753 4145133 320753 4145133 1048576 256 0 0 8 0 16 64 0x0 0x7f4cb8e90ec0 0x7fa244294ec0 65536 170884 195342 19184888 21793984 198990137856562 1412570388029401 199001894935363 1412582414437599 199001894955843 1412582414457599 198990153574507 1412570404294060
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 320753 4145133 320753 4145133 1048576 256 0 0 8 0 16 64 0x0 0x7f4cb8e90ec0 0x7fa244294ec0 65536 270394 307640 30243744 34543088 198990153590808 1412570404315240 199001895045923 1412582414476479 199001895062403 1412582414491999 198990153897729 1412570404581574
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 320753 4145133 320753 4145133 1048576 256 0 0 8 0 16 64 0x0 0x7f4cb8e90ec0 0x7fa244294ec0 65536 259860 266008 29229728 29709392 198990153924269 1412570404607944 199001895083363 1412582414551359 199001895098883 1412582414567679 198990154075054 1412570404762556
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 320954 4145318 320954 4145318 1048576 256 0 0 8 0 16 64 0x0 0x7f40f4f68ec0 0x7f895b6e0ec0 32768 278475 289884 31173412 32469952 198990619125670 1412570872387977 199001894935363 1412582414437599 199001894955843 1412582414457599 198990634836722 1412570888873843
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 320954 4145318 320954 4145318 1048576 256 0 0 8 0 16 64 0x0 0x7f40f4f68ec0 0x7f895b6e0ec0 32768 559977 599906 62717076 67183036 198990634856980 1412570888893811 199001895045923 1412582414476479 199001895062403 1412582414491999 198990635121510 1412570889171757
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 320954 4145318 320954 4145318 1048576 256 0 0 8 0 16 64 0x0 0x7f40f4f68ec0 0x7f895b6e0ec0 32768 569028 583331 63722036 65336048 198990635147840 1412570889198147 199001895083363 1412582414551359 199001895098883 1412582414567679 198990635324454 1412570889355965
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 321157 4145521 321157 4145521 1048576 256 0 0 8 0 16 64 0x0 0x7f6e1b100ec0 0x7f7f9d9b0ec0 29013 27994 29013 27994 11176 11226 232112 223960 16384 11736679 10642083 138268 128366 0 47442548 43085488 198991099206579 1412571356271493 199001894935363 1412582414437599 199001894955843 1412582414457599 198991115265029 1412571372190678
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 321157 4145521 321157 4145521 1048576 256 0 0 8 0 16 64 0x0 0x7f6e1b100ec0 0x7f7f9d9b0ec0 40851 40639 40851 40639 13491 12658 326816 325120 16384 18989824 19865141 219727 225740 0 76441744 79939960 198991115292040 1412571372218141 199001895045923 1412582414476479 199001895062403 1412582414491999 198991115577520 1412571372507969
4 2 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 321157 4145521 321157 4145521 1048576 256 0 0 8 0 16 64 0x0 0x7f6e1b100ec0 0x7f7f9d9b0ec0 41371 40808 41371 40808 13947 12670 330976 326472 16384 19441122 19726094 223986 225982 0 78257552 79390392 198991115612746 1412571372543296 199001895083363 1412582414551359 199001895098883 1412582414567679 198991115779131 1412571372709790
@@ -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...
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
文件差异因一行或多行过长而隐藏
@@ -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
1 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
2 0 1388.4407 1389.1462 1387.9556 1388.6844 1388.9258 1389.608 5012.3818 5017.5005 5009.4272 5014.4473 5015.3364 5020.5537 9220.9736 9228.3779 9220.4082 9227.6279 9221.5391 9229.1279 18048.867 17717.744 18047.982 17714.797 18049.752 17720.691 20929.025 20946.693 20868.734 20886.242 20989.316 21007.145 20262.105 20272.535 20261.408 20272.062 20262.803 20273.008 170368.28 170499.52 170364.62 170494.77 170371.94 170504.27 164833.34 164933.34 164829.61 164928.09 164837.08 164938.59 41411.355 41436.176 41410.75 41435.543 41411.961 41436.809 41471.086 41492.594 41470.277 41491.988 41471.895 41493.199 166320.92 166403.12 165829.64 165911.45 166812.2 166894.8
3 1 1388.9957 1389.674 1388.3947 1389.1433 1389.5968 1390.2046 5027.0874 5027.3335 5024.9897 5025.1128 5029.1851 5029.5542 9231.418 9233.5205 9230.6963 9232.8916 9232.1396 9234.1494 18088.484 18229.463 18084.846 18227.5 18092.123 18231.426 20968.271 20973.705 20901.262 20905.861 21035.281 21041.549 20286.959 20293.215 20286.332 20292.557 20287.586 20293.873 170792.02 170827.14 170786.41 170823.33 170797.62 170830.95 165064.95 165099.89 165061.06 165096.33 165068.84 165103.45 41475.48 41482.094 41474.453 41481.465 41476.508 41482.723 41528.645 41539.863 41527.684 41539.215 41529.605 41540.512 166824.89 166862.95 166821.84 166860.66 166827.94 166865.25
4 2 1388.7762 1388.6648 1388.223 1388.1245 1389.3295 1389.2051 5033.8354 5037.0464 5031.5078 5034.8857 5036.1631 5039.207 9260.0098 9263.9912 9259.3555 9262.6768 9260.6641 9265.3057 18109.824 18222.869 18108.805 18221.883 18110.844 18223.855 21048.404 21056.984 21047.924 21056.562 21048.885 21057.406 20354.592 20357.533 20354.098 20356.988 20355.086 20358.078 171145.12 171205.48 171140.94 171201.55 171149.31 171209.42 165515.59 165565.27 165511.66 165560.72 165519.53 165569.81 41583.41 41598.941 41582.383 41597.836 41584.438 41600.047 41643.316 41652.184 41641.996 41651.406 41644.637 41652.961 166962.69 167016.72 166359.5 166423.66 167565.88 167609.78
5 3 1389.2411 1388.9971 1388.7584 1388.3999 1389.7238 1389.5942 5030.2002 5033.2759 5028.9575 5031.7471 5031.4429 5034.8047 9239.7422 9236.5371 9239.1396 9235.832 9240.3447 9237.2422 18027.953 18325.387 18024.689 18324.445 18031.217 18326.328 21032.553 21031.562 21032.098 21031.207 21033.008 21031.918 20313.242 20305.99 20312.57 20305.543 20313.914 20306.438 171017.05 171012.06 171013.84 171007.19 171020.25 171016.94 165231.08 165121.73 165227.28 165116.78 165234.88 165126.69 41521.387 41423.219 41520.555 41270.75 41522.219 41575.688 41580.211 41557.129 41579.453 41556.031 41580.969 41558.227 167016.34 166901 167014.17 166896.89 167018.52 166905.11
@@ -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
1 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
2 device_inv_int ./sample/vcopy -n 1048576 -b 256 -i 3 ./tests/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) 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 325033 4149441 325033 4149441 1048576 256 0 0 8 0 16 64 0x0 0x7f31a7fccec0 0x7fc3cc4e4ec0 199001894911168 1412582414412809 199001894935363 1412582414437599 199001894955843 1412582414457599 199001894968617 1412582414473534
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 325033 4149441 325033 4149441 1048576 256 0 0 8 0 16 64 0x0 0x7f31a7fccec0 0x7fc3cc4e4ec0 199001894966613 1412582414468815 199001895045923 1412582414476479 199001895062403 1412582414491999 199001895063647 1412582414549858
4 2 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 4 325033 4149441 325033 4149441 1048576 256 0 0 8 0 16 64 0x0 0x7f31a7fccec0 0x7fc3cc4e4ec0 199001895073536 1412582414502669 199001895083363 1412582414551359 199001895098883 1412582414567679 199001895100126 1412582414568934
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 150756 1246429 150756 1246429 1048576 256 0 0 8 8 16 64 0x0 0x7f820df66e80 0x7fe4492acec0 47744 47968 47744 47968 16384 65536 12856 13609 1674844 1730416 194204807313230 1410128918207610 194218184431477 1410140689683045 194218184455957 1410140689707365 194204815275476 1410128925944983
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 150941 1246616 150941 1246616 1048576 256 0 0 8 8 16 64 0x0 0x7fb5db332e80 0x7fd526ad0ec0 0 0 0 194205315685723 1410129409181220 194218184431477 1410140689683045 194218184455957 1410140689707365 194205323317172 1410129416783247
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 151125 1246801 151125 1246801 1048576 256 0 0 8 8 16 64 0x0 0x7f690a0c0e80 0x7f6611660ec0 65536 205956 190502 26258976 24371720 194205816966838 1410129893979623 194218184431477 1410140689683045 194218184455957 1410140689707365 194205824797164 1410129901509554
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 151312 1247003 151312 1247003 1048576 256 0 0 8 8 16 64 0x0 0x7fa9adb0ce80 0x7f106ce74ec0 32768 667106 667005 85389576 85368756 194206315490934 1410130378569022 194218184431477 1410140689683045 194218184455957 1410140689707365 194206323400790 1410130386436229
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 151497 1247190 151497 1247190 1048576 256 0 0 8 8 16 64 0x0 0x7fd5b2e38e80 0x7f14d9abcec0 48008 48766 48008 48766 17263 17302 384072 390136 16384 24600233 24586988 232757 235330 0 98897844 98882880 194207844573840 1410130866243399 194218184431477 1410140689683045 194218184455957 1410140689707365 194207852970067 1410130873900159
+702
查看文件
@@ -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]
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2
文件差异因一行或多行过长而隐藏
+1 -1
查看文件
@@ -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
1 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
2 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) Thu 21 Mar 2024 03:53:14 PM (CDT) 2 t008-007.hpcfund 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 527651100 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 154895 1250548 154895 1250548 1048576 256 0 0 8 8 16 64 0x0 0x7f26e5422e80 0x7f5d3a178ec0 194218184405603 1410140689657401 194218184431477 1410140689683045 194218184455957 1410140689707365 194218184468662 1410140689720210
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 306015 4129674 306015 4129674 1048576 256 0 0 8 0 16 64 0x0 0x7fd36d3a0ec0 0x7fd6b0670ec0 27553 27647 27553 27647 16384 65536 14040 15995 1568448 1772908 198487811862509 1411974341510867 198500539781025 1411987252061945 198500539801025 1411987252082105 198487828148739 1411974357430774
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 306217 4129876 306217 4129876 1048576 256 0 0 8 0 16 64 0x0 0x7f1d6cb44ec0 0x7fe21d564ec0 0 0 0 198488296151539 1411974838805242 198500539781025 1411987252061945 198500539801025 1411987252082105 198488312049765 1411974854611815
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 306419 4130063 306419 4130063 1048576 256 0 0 8 0 16 64 0x0 0x7efbf7208ec0 0x7f1d223a4ec0 65536 172952 180788 19460368 20162048 198488779287609 1411975328440803 198500539781025 1411987252061945 198500539801025 1411987252082105 198488795365134 1411975344459988
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 306621 4130265 306621 4130265 1048576 256 0 0 8 0 16 64 0x0 0x7f5805234ec0 0x7f0353e08ec0 32768 291597 297669 32660248 33333264 198489259151227 1411975811818671 198500539781025 1411987252061945 198500539801025 1411987252082105 198489275062158 1411975827995623
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 306807 4130456 306807 4130456 1048576 256 0 0 8 0 16 64 0x0 0x7fe505304ec0 0x7f3ef1724ec0 28097 27505 28097 27505 10788 10822 224784 220048 16384 11140767 10699049 132548 127069 0 45073020 43312188 198489738658391 1411976295988936 198500539781025 1411987252061945 198500539801025 1411987252082105 198489754777786 1411976312094343
+764
查看文件
@@ -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...
@@ -0,0 +1,2 @@
Dispatch_ID,Kernel_Name,GPU_ID
0,"vecCopy(double*, double*, double*, int, int) [clone .kd]",2
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
文件差异因一行或多行过长而隐藏
@@ -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
1 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
2 0 1388.2593 1388.7638 1387.6742 1388.2611 1388.8444 1389.2665 5015.6343 5016.8418 5012.4912 5013.7964 5018.7773 5019.8872 9223.3535 9224.1777 9222.6689 9223.6074 9224.0381 9224.748 18050.238 17710.416 18049.146 17707.119 18051.33 17713.713 20933.475 20937.773 20873.053 20877.453 20993.896 20998.094 20262.736 20269.176 20262.088 20268.652 20263.385 20269.699 170396.28 170438.3 170393.2 170435.23 170399.36 170441.36 164844.48 164898.08 164840.03 164893.94 164848.94 164902.22 41410.918 41427.383 41410.391 41426.621 41411.445 41428.145 41466.852 41485.637 41465.879 41485.012 41467.824 41486.262 166299.94 166383.89 165807.45 165891.39 166792.42 166876.39
3 1 1389.0791 1388.9694 1388.4865 1388.4139 1389.6718 1389.5248 5026.2217 5028.8188 5024.4121 5026.9424 5028.0312 5030.6953 9233.2822 9237.1611 9232.6641 9236.4932 9233.9004 9237.8291 18090.092 18241.684 18086.539 18239.088 18093.645 18244.279 20971.795 20984.367 20904.992 20916.609 21038.598 21052.125 20290.67 20301.172 20290.035 20300.59 20291.305 20301.754 170824.69 170908.77 170820.02 170904.42 170829.36 170913.11 165107.66 165165.75 165105.09 165162.45 165110.22 165169.05 41487.414 41492.887 41486.652 41492.227 41488.176 41493.547 41542.918 41552.719 41542 41551.84 41543.836 41553.598 166879.25 166921.41 166876.3 166918.52 166882.2 166924.3
4 2 1388.9591 1388.7931 1388.4004 1388.2235 1389.5178 1389.3627 5035.1958 5035.6152 5033.0864 5033.5068 5037.3052 5037.7236 9261.5215 9259.1699 9260.8203 9258.3154 9262.2227 9260.0244 18107.543 18217.061 18106.791 18216.146 18108.295 18217.975 21047.707 21046.363 21047.246 21045.939 21048.168 21046.787 20351.348 20348.338 20350.775 20347.758 20351.92 20348.918 171110.19 171116.91 171106.17 171113.22 171114.2 171120.59 165507.5 165500.02 165502.62 165496.81 165512.38 165503.22 41583.355 41579.711 41582.031 41579.117 41584.68 41580.305 41637.441 41638.535 41636.102 41637.797 41638.781 41639.273 166941.58 166945.91 166351.8 166353.61 167531.36 167538.2
5 3 1389.1071 1388.9321 1388.4954 1388.3486 1389.7188 1389.5156 5030.6714 5033.4414 5029.2788 5031.8975 5032.064 5034.9854 9241.2998 9238.9033 9240.582 9238.1846 9242.0176 9239.6221 18023.967 18333.842 18020.326 18332.98 18027.607 18334.703 21036.178 21036.322 21035.668 21036.035 21036.688 21036.609 20311.578 20310.521 20310.953 20309.934 20312.203 20311.109 171023.28 171059.27 171018.56 171054.39 171028 171064.14 165224.14 165193.59 165220.2 165187.11 165228.08 165200.08 41439.121 41439.648 41285.898 41286.48 41592.344 41592.816 41578.496 41576.109 41577.977 41574.953 41579.016 41577.266 166999.5 166995.31 166997.89 166989.83 167001.11 167000.8
+1 -1
查看文件
@@ -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
1 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
2 dispatch_0 ./sample/vcopy -n 1048576 -b 256 -i 3 ./tests/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) 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 310582 4134249 310582 4134249 1048576 256 0 0 8 0 16 64 0x0 0x7f0fb9e1cec0 0x7f2a3a720ec0 198500539756684 1411987252036982 198500539781025 1411987252061945 198500539801025 1411987252082105 198500539812330 1411987252094040
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 155261 1250911 155261 1250911 1048576 256 0 0 8 8 16 64 0x0 0x7fdace5aee80 0x7f166b404ec0 48843 48346 48843 48346 16384 65536 14557 13303 1859980 1721468 194220648419385 1410143003879101 194232901432521 1410154854825909 194232901456681 1410154854850869 194220656370350 1410143011603459
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 155261 1250911 155261 1250911 1048576 256 0 0 8 8 16 64 0x0 0x7fdace5aee80 0x7f166b404ec0 42042 43911 42042 43911 16384 65536 8064 8117 1048588 194220656392682 1410143011625420 194232901551561 1410154854934389 194232901570601 1410154854953269 194220656709111 1410143011979598
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 155449 1251095 155449 1251095 1048576 256 0 0 8 8 16 64 0x0 0x7f0144e1ee80 0x7f7a7aa0cec0 0 0 0 194221143127145 1410143493832086 194232901432521 1410154854825909 194232901456681 1410154854850869 194221150750408 1410143501573616
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 155449 1251095 155449 1251095 1048576 256 0 0 8 8 16 64 0x0 0x7f0144e1ee80 0x7f7a7aa0cec0 0 0 0 194221150769896 1410143501592832 194232901551561 1410154854934389 194232901570601 1410154854953269 194221151079862 1410143501923235
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 155638 1251284 155638 1251284 1048576 256 0 0 8 8 16 64 0x0 0x7fd3082b2e80 0x7f7f243e8ec0 65536 220822 193338 28203128 24849584 194221637472508 1410143974171880 194232901432521 1410154854825909 194232901456681 1410154854850869 194221645453088 1410143981794526
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 155638 1251284 155638 1251284 1048576 256 0 0 8 8 16 64 0x0 0x7fd3082b2e80 0x7f7f243e8ec0 65536 199286 172672 25574192 22150704 194221645471273 1410143981814644 194232901551561 1410154854934389 194232901570601 1410154854953269 194221645910755 1410143982124227
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 155824 1251471 155824 1251471 1048576 256 0 0 8 8 16 64 0x0 0x7ff8d92c4e80 0x7f201c50cec0 32768 651728 654915 83429440 83820200 194222135704660 1410144454263265 194232901432521 1410154854825909 194232901456681 1410154854850869 194222143498788 1410144462045633
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 155824 1251471 155824 1251471 1048576 256 0 0 8 8 16 64 0x0 0x7ff8d92c4e80 0x7f201c50cec0 32768 664228 662829 85004888 84839104 194222143519427 1410144462066883 194232901551561 1410154854934389 194232901570601 1410154854953269 194222143811741 1410144462370145
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 156011 1251655 156011 1251655 1048576 256 0 0 8 8 16 64 0x0 0x7f6b448cee80 0x7f0a556ccec0 48616 48291 48616 48291 17826 17364 388936 386336 16384 25474846 25414292 236631 236101 0 102389564 102182372 194222631809706 1410144945077695 194232901432521 1410154854825909 194232901456681 1410154854850869 194222639570670 1410144952673600
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 156011 1251655 156011 1251655 1048576 256 0 0 8 8 16 64 0x0 0x7f6b448cee80 0x7f0a556ccec0 42631 42378 42631 42378 13289 13334 341056 339032 16384 25728907 25188655 236499 233462 0 103400652 101275544 194222639598924 1410144952703446 194232901551561 1410154854934389 194232901570601 1410154854953269 194222639909191 1410144953024913
+702
查看文件
@@ -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]
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2
文件差异因一行或多行过长而隐藏
@@ -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
1 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
2 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) Thu 21 Mar 2024 03:53:28 PM (CDT) 2 t008-007.hpcfund 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 527651100 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 159380 1255002 159380 1255002 1048576 256 0 0 8 8 16 64 0x0 0x7fd3f9e04e80 0x7f1e2ca68ec0 194232901406934 1410154854801159 194232901432521 1410154854825909 194232901456681 1410154854850869 194232901471346 1410154854861473
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 159380 1255002 159380 1255002 1048576 256 0 0 8 8 16 64 0x0 0x7fd3f9e04e80 0x7f1e2ca68ec0 194232901470003 1410154854863637 194232901551561 1410154854934389 194232901570601 1410154854953269 194232901571726 1410154854954889
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 311135 4135708 311135 4135708 1048576 256 0 0 8 0 16 64 0x0 0x7f20e5dd0ec0 0x7f60c4920ec0 27333 27801 27333 27801 16384 65536 13914 13980 1566164 1568136 198596821057709 1412176982271587 198609512940794 1412189920581155 198609512961274 1412189920601635 198596836842831 1412176998152690
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 311135 4135708 311135 4135708 1048576 256 0 0 8 0 16 64 0x0 0x7f20e5dd0ec0 0x7f60c4920ec0 41896 42553 41896 42553 16384 65536 9440 9218 1048676 1048704 198596836864582 1412176998167588 198609513046074 1412189920620835 198609513062554 1412189920636515 198596837190358 1412176998470521
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 311337 4135910 311337 4135910 1048576 256 0 0 8 0 16 64 0x0 0x7fef76aa8ec0 0x7f540aed0ec0 0 0 0 198597300509498 1412177470467990 198609512940794 1412189920581155 198609512961274 1412189920601635 198597316434836 1412177486378819
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 311337 4135910 311337 4135910 1048576 256 0 0 8 0 16 64 0x0 0x7fef76aa8ec0 0x7f540aed0ec0 0 0 0 198597316453451 1412177486396252 198609513046074 1412189920620835 198609513062554 1412189920636515 198597316756414 1412177486675320
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 311539 4136108 311539 4136108 1048576 256 0 0 8 0 16 64 0x0 0x7f00c60b0ec0 0x7f950a7d8ec0 65536 178908 197906 19932664 22151624 198597783544016 1412177954983531 198609512940794 1412189920581155 198609512961274 1412189920601635 198597799509239 1412177971006002
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 311539 4136108 311539 4136108 1048576 256 0 0 8 0 16 64 0x0 0x7f00c60b0ec0 0x7f950a7d8ec0 65536 228948 277686 25571704 31031360 198597799526401 1412177971031811 198609513046074 1412189920620835 198609513062554 1412189920636515 198597799830967 1412177971316119
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 311741 4136306 311741 4136306 1048576 256 0 0 8 0 16 64 0x0 0x7f8f6070cec0 0x7f2dc569cec0 32768 295724 288723 33126508 32327348 198598264016216 1412178439025999 198609512940794 1412189920581155 198609512961274 1412189920601635 198598279668286 1412178454937981
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 311741 4136306 311741 4136306 1048576 256 0 0 8 0 16 64 0x0 0x7f8f6070cec0 0x7f2dc569cec0 32768 579022 583337 64857248 65324164 198598279691300 1412178454959211 198609513046074 1412189920620835 198609513062554 1412189920636515 198598279967252 1412178455321756
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 311942 4136505 311942 4136505 1048576 256 0 0 8 0 16 64 0x0 0x7fecfef2cec0 0x7febaa5a0ec0 28002 27465 28002 27465 11107 10867 224024 219728 16384 11099231 10783574 131393 127969 0 44906916 43629176 198598744115260 1412178931644254 198609512940794 1412189920581155 198609512961274 1412189920601635 198598759705213 1412178947860341
3 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 311942 4136505 311942 4136505 1048576 256 0 0 8 0 16 64 0x0 0x7fecfef2cec0 0x7febaa5a0ec0 42307 41440 42307 41440 13512 13373 338464 331528 16384 20301423 19852449 231106 226122 0 81693968 79898484 198598759736312 1412178947889406 198609513046074 1412189920620835 198609513062554 1412189920636515 198598760106662 1412178948181669
+764
查看文件
@@ -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...
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2
文件差异因一行或多行过长而隐藏
@@ -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
1 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
2 0 1389.0242 1388.8433 1388.5444 1388.2601 1389.5039 1389.4264 5014.0776 5018.3813 5010.7217 5015.4775 5017.4336 5021.2852 9224.2939 9227.8584 9223.6963 9227.1865 9224.8916 9228.5303 18054.982 17717.145 18054.016 17714.176 18055.949 17720.113 20935.725 20947.432 20875.342 20886.881 20996.107 21007.982 20261.689 20274.334 20260.873 20273.65 20262.506 20275.018 170384.81 170521.16 170381.8 170517.47 170387.83 170524.84 164856.69 164937.09 164853.22 164932.44 164860.16 164941.75 41417.711 41442.25 41417.168 41441.645 41418.254 41442.855 41477.18 41499.996 41476.625 41499.133 41477.734 41500.859 166336.23 166424.47 165848.91 165933.94 166823.56 166915
3 1 1388.8065 1389.0067 1388.214 1388.4509 1389.399 1389.5625 5026.9512 5028.1904 5024.9131 5026.1631 5028.9893 5030.2178 9232.082 9237.1016 9231.4229 9236.377 9232.7412 9237.8262 18087.27 18236.582 18083.492 18235.619 18091.047 18237.545 20973.012 20985.395 20906.764 20918.506 21039.26 21052.283 20291.207 20299.889 20290.643 20299.375 20291.771 20300.402 170819.16 170925.2 170814.88 170920.88 170823.44 170929.53 165083.95 165148.95 165080.05 165144.98 165087.86 165152.92 41472.68 41497.691 41471.848 41496.844 41473.512 41498.539 41536.34 41556.211 41535.246 41555.07 41537.434 41557.352 166839.25 166931.45 166835.88 166928.2 166842.62 166934.7
4 2 1389.42 1388.4513 1388.8044 1387.8545 1390.0356 1389.0481 5035.7383 5036.9297 5033.4888 5034.5923 5037.9878 5039.2671 9261.5166 9261.1367 9260.8115 9260.4297 9262.2217 9261.8438 18109.811 18218.844 18108.705 18217.791 18110.916 18219.896 21049.439 21050.777 21049.039 21050.377 21049.84 21051.178 20352.191 20350.275 20351.469 20349.711 20352.914 20350.84 171119.62 171164.12 171114.88 171159.02 171124.38 171169.23 165490.05 165523.23 165485.94 165519.78 165494.16 165526.69 41580.387 41583.496 41579.566 41582.508 41581.207 41584.484 41639.574 41637.641 41638.555 41636.84 41640.594 41638.441 166942.73 166949.61 166357.73 166347.86 167527.73 167551.36
5 3 1388.8628 1389.2191 1388.2523 1388.6479 1389.4733 1389.7903 5032.647 5032.562 5031.3843 5030.8687 5033.9097 5034.2554 9240.2979 9238.0928 9239.7139 9237.4268 9240.8818 9238.7588 18025.895 18328.943 18022.496 18327.766 18029.293 18330.121 21031.047 21034.297 21030.645 21033.963 21031.449 21034.631 20311.537 20307.766 20310.795 20307.223 20312.279 20308.309 171032.64 171036.94 171028.23 171032 171037.05 171041.88 165246.34 165166.28 165241.59 165162.23 165251.09 165170.33 41443.762 41426.504 41292.008 41272.871 41595.516 41580.137 41583.09 41568.695 41582.52 41567.602 41583.66 41569.789 167018.66 166952.53 167016.94 166948.02 167020.38 166957.05
@@ -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
1 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
2 dispatch_0_1 ./sample/vcopy -n 1048576 -b 256 -i 3 ./tests/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) 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 0 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 0 315904 4140363 315904 4140363 1048576 256 0 0 8 0 16 64 0x0 0x7fc0d1ec4ec0 0x7f3c471c4ec0 198609512911564 1412189920555838 198609512940794 1412189920581155 198609512961274 1412189920601635 198609512972029 1412189920615290
3 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 315904 4140363 315904 4140363 1048576 256 0 0 8 0 16 64 0x0 0x7fc0d1ec4ec0 0x7f3c471c4ec0 198609512972319 1412189920612605 198609513046074 1412189920620835 198609513062554 1412189920636515 198609513063973 1412189920769341
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 146368 1242050 146368 1242050 1048576 256 0 0 8 8 16 64 0x0 0x7f9f83152e80 0x7fc6f4208ec0 38682 38821 38682 38821 16384 65536 8172 8109 1048640 1048656 194190802937007 1410114557095333 194203146753468 1410127432590948 194203146772188 1410127432609509 194190810926274 1410114564821895
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 146556 1242238 146556 1242238 1048576 256 0 0 8 8 16 64 0x0 0x7f9214dece80 0x7fe8146b0ec0 0 0 0 194191303483541 1410115049761835 194203146753468 1410127432590948 194203146772188 1410127432609509 194191311114590 1410115057489720
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 146743 1242423 146743 1242423 1048576 256 0 0 8 8 16 64 0x0 0x7fdb01522e80 0x7f6929238ec0 65536 83590 91980 10693168 11724504 194191799460013 1410115535741786 194203146753468 1410127432590948 194203146772188 1410127432609509 194191807333481 1410115543260466
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 146928 1242619 146928 1242619 1048576 256 0 0 8 8 16 64 0x0 0x7fe5463eae80 0x7fc33f83cec0 32768 663275 653996 84884088 83707028 194192296631898 1410116022813727 194203146753468 1410127432590948 194203146772188 1410127432609509 194192304449200 1410116030517617
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 147115 1242805 147115 1242805 1048576 256 0 0 8 8 16 64 0x0 0x7fd659050e80 0x7fcc21518ec0 38457 38554 38457 38554 11850 11832 307664 308440 16384 22285112 22714635 212347 211906 0 89633484 91397252 194192793995967 1410116516938870 194203146753468 1410127432590948 194203146772188 1410127432609509 194192801697780 1410116524589600
+702
查看文件
@@ -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]
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2
文件差异因一行或多行过长而隐藏
+1 -1
查看文件
@@ -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
1 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
2 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) Thu 21 Mar 2024 03:53:00 PM (CDT) 2 t008-007.hpcfund 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 527651100 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
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 150477 1246155 150477 1246155 1048576 256 0 0 8 8 16 64 0x0 0x7fb6015c6e80 0x7fd9c2848ec0 194203146739938 1410127432560491 194203146753468 1410127432590948 194203146772188 1410127432609509 194203146784432 1410127432620744
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 301053 4124736 301053 4124736 1048576 256 0 0 8 0 16 64 0x0 0x7f90d6404ec0 0x7f7cc2578ec0 22880 22637 22880 22637 16384 65536 9554 9404 1048680 1048700 198381671765204 1411868153949415 198394440082212 1411881076677985 198394440098052 1411881076693505 198381687536921 1411868170088366
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 301243 4124923 301243 4124923 1048576 256 0 0 8 0 16 64 0x0 0x7f58b1578ec0 0x7f10f6d40ec0 0 0 0 198382158268734 1411868641572741 198394440082212 1411881076677985 198394440098052 1411881076693505 198382174223788 1411868657447011
@@ -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
1 Dispatch_ID Kernel_Name GPU_ID queue-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
2 1 vecCopy(double*, double*, double*, int, int) vecCopy(double*, double*, double*, int, int) [clone .kd] 2 0 2 301429 4125108 301429 4125108 1048576 256 0 0 8 0 16 64 0x0 0x7f7811c08ec0 0x7fe12a7b0ec0 65536 72322 76600 8038296 8662264 198382637273097 1411869123353968 198394440082212 1411881076677985 198394440098052 1411881076693505 198382653420274 1411869139369646

某些文件未显示,因为此 diff 中更改的文件太多 显示更多