JoseSantosAMD
e664f7abf4
* 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>
[ROCm/rocprofiler-compute commit: da506ad9b5]
448 lines
27 KiB
Plaintext
448 lines
27 KiB
Plaintext
Omniperf version: 2.0.0-RC1
|
|
Profiler choice: rocprofv1
|
|
Path: /home1/josantos/omniperf/tests/workloads/ipblocks_SQ/MI100
|
|
Target: MI100
|
|
Command: ./tests/vcopy -n 1048576 -b 256 -i 3
|
|
Kernel Selection: None
|
|
Dispatch Selection: None
|
|
IP Blocks: ['sq']
|
|
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
Collecting Performance Counters
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_IFETCH_LEVEL.txt
|
|
|-> [rocprof] RPL: on '240321_155433' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_IFETCH_LEVEL.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155433_1271818'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155433_1271818/input0_results_240321_155433'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155433_1271818/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 6 metrics
|
|
|-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, SQ_WAVES, SQ_IFETCH, SQ_IFETCH_LEVEL, SQ_ACCUM_PREV_HIRES
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155433_1271818/input0_results_240321_155433
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_IFETCH_LEVEL.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_LDS.txt
|
|
|-> [rocprof] RPL: on '240321_155434' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_LDS.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155434_1272002'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155434_1272002/input0_results_240321_155434'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155434_1272002/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 3 metrics
|
|
|-> [rocprof] SQ_INSTS_LDS, SQ_INST_LEVEL_LDS, SQ_ACCUM_PREV_HIRES
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155434_1272002/input0_results_240321_155434
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_LDS.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt
|
|
|-> [rocprof] RPL: on '240321_155434' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_SMEM.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155434_1272189'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155434_1272189/input0_results_240321_155434'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155434_1272189/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 3 metrics
|
|
|-> [rocprof] SQ_INSTS_SMEM, SQ_INST_LEVEL_SMEM, SQ_ACCUM_PREV_HIRES
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155434_1272189/input0_results_240321_155434
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_SMEM.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt
|
|
|-> [rocprof] RPL: on '240321_155435' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_INST_LEVEL_VMEM.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155435_1272372'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155435_1272372/input0_results_240321_155435'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155435_1272372/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 3 metrics
|
|
|-> [rocprof] SQ_INSTS_VMEM, SQ_INST_LEVEL_VMEM, SQ_ACCUM_PREV_HIRES
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155435_1272372/input0_results_240321_155435
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_INST_LEVEL_VMEM.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_LEVEL_WAVES.txt
|
|
|-> [rocprof] RPL: on '240321_155435' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/SQ_LEVEL_WAVES.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155435_1272555'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155435_1272555/input0_results_240321_155435'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155435_1272555/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 9 metrics
|
|
|-> [rocprof] GRBM_COUNT, GRBM_GUI_ACTIVE, CPC_ME1_BUSY_FOR_PACKET_DECODE, SQ_CYCLES, SQ_WAVES, SQ_WAVE_CYCLES, SQ_BUSY_CYCLES, SQ_LEVEL_WAVES, SQ_ACCUM_PREV_HIRES
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155435_1272555/input0_results_240321_155435
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/SQ_LEVEL_WAVES.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_0.txt
|
|
|-> [rocprof] RPL: on '240321_155435' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_0.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155435_1272740'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155435_1272740/input0_results_240321_155435'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155435_1272740/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 10 metrics
|
|
|-> [rocprof] SQ_INSTS_VMEM_WR, SQ_INSTS_VMEM_RD, SQ_INSTS_VMEM, SQ_INSTS_SALU, SQ_INSTS_VSKIPPED, SQ_INSTS_SMEM, SQ_INSTS_FLAT, SQ_INSTS_LDS, GRBM_COUNT, GRBM_GUI_ACTIVE
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155435_1272740/input0_results_240321_155435
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_0.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_1.txt
|
|
|-> [rocprof] RPL: on '240321_155436' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_1.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155436_1272924'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155436_1272924/input0_results_240321_155436'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155436_1272924/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 8 metrics
|
|
|-> [rocprof] SQ_INSTS_GDS, SQ_INSTS_EXP_GDS, SQ_INSTS_BRANCH, SQ_INSTS_SENDMSG, SQ_INSTS, SQ_WAVE_CYCLES, SQ_WAIT_ANY, SQ_WAIT_INST_ANY
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155436_1272924/input0_results_240321_155436
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_1.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_2.txt
|
|
|-> [rocprof] RPL: on '240321_155436' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_2.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155436_1273109'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155436_1273109/input0_results_240321_155436'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155436_1273109/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 8 metrics
|
|
|-> [rocprof] SQ_ACTIVE_INST_ANY, SQ_CYCLES, SQ_BUSY_CYCLES, SQ_BUSY_CU_CYCLES, SQ_INSTS_VALU, SQ_ACTIVE_INST_VMEM, SQ_ACTIVE_INST_LDS, SQ_ACTIVE_INST_VALU
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155436_1273109/input0_results_240321_155436
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_2.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_3.txt
|
|
|-> [rocprof] RPL: on '240321_155437' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_3.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155437_1273292'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155437_1273292/input0_results_240321_155437'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155437_1273292/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 8 metrics
|
|
|-> [rocprof] SQ_ACTIVE_INST_SCA, SQ_ACTIVE_INST_EXP_GDS, SQ_ACTIVE_INST_MISC, SQ_ACTIVE_INST_FLAT, SQ_INST_CYCLES_VMEM_WR, SQ_INST_CYCLES_VMEM_RD, SQ_INST_CYCLES_SMEM, SQ_INST_CYCLES_SALU
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155437_1273292/input0_results_240321_155437
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_3.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_4.txt
|
|
|-> [rocprof] RPL: on '240321_155437' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_4.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155437_1273475'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155437_1273475/input0_results_240321_155437'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155437_1273475/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 8 metrics
|
|
|-> [rocprof] SQ_THREAD_CYCLES_VALU, SQ_IFETCH, SQ_LDS_BANK_CONFLICT, SQ_LDS_ADDR_CONFLICT, SQ_LDS_UNALIGNED_STALL, SQ_WAVES, SQ_WAVES_EQ_64, SQ_WAVES_LT_64
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155437_1273475/input0_results_240321_155437
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_4.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_5.txt
|
|
|-> [rocprof] RPL: on '240321_155438' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_5.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155438_1273659'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155438_1273659/input0_results_240321_155438'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155438_1273659/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 8 metrics
|
|
|-> [rocprof] SQ_WAVES_LT_48, SQ_WAVES_LT_32, SQ_WAVES_LT_16, SQ_ITEMS, SQ_LDS_MEM_VIOLATIONS, SQ_LDS_ATOMIC_RETURN, SQ_LDS_IDX_ACTIVE, SQ_WAVES_RESTORED
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155438_1273659/input0_results_240321_155438
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_5.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_6.txt
|
|
|-> [rocprof] RPL: on '240321_155438' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_6.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155438_1273842'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155438_1273842/input0_results_240321_155438'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155438_1273842/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 8 metrics
|
|
|-> [rocprof] SQ_WAVES_SAVED, SQ_INSTS_SMEM_NORM, SQC_TC_INST_REQ, SQC_TC_DATA_READ_REQ, SQC_TC_DATA_WRITE_REQ, SQC_TC_DATA_ATOMIC_REQ, SQC_TC_STALL, SQC_TC_REQ
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155438_1273842/input0_results_240321_155438
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_6.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_7.txt
|
|
|-> [rocprof] RPL: on '240321_155439' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_7.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155439_1274025'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155439_1274025/input0_results_240321_155439'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155439_1274025/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 8 metrics
|
|
|-> [rocprof] SQC_DCACHE_REQ_READ_16, SQC_ICACHE_REQ, SQC_ICACHE_HITS, SQC_ICACHE_MISSES, SQC_ICACHE_MISSES_DUPLICATE, SQC_DCACHE_INPUT_VALID_READYB, SQC_DCACHE_ATOMIC, SQC_DCACHE_REQ_READ_8
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155439_1274025/input0_results_240321_155439
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_7.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_8.txt
|
|
|-> [rocprof] RPL: on '240321_155439' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/pmc_perf_8.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155439_1274210'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155439_1274210/input0_results_240321_155439'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155439_1274210/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 7 metrics
|
|
|-> [rocprof] SQC_DCACHE_REQ, SQC_DCACHE_HITS, SQC_DCACHE_MISSES, SQC_DCACHE_MISSES_DUPLICATE, SQC_DCACHE_REQ_READ_1, SQC_DCACHE_REQ_READ_2, SQC_DCACHE_REQ_READ_4
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155439_1274210/input0_results_240321_155439
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/pmc_perf_8.csv' is generating
|
|
|-> [rocprof]
|
|
[profiling] Current input file: tests/workloads/ipblocks_SQ/MI100/perfmon/timestamps.txt
|
|
|-> [rocprof] RPL: on '240321_155440' from '/opt/rocm-6.0.2' in '/home1/josantos/omniperf'
|
|
|-> [rocprof] RPL: profiling '""./tests/vcopy -n 1048576 -b 256 -i 3""'
|
|
|-> [rocprof] RPL: input file 'tests/workloads/ipblocks_SQ/MI100/perfmon/timestamps.txt'
|
|
|-> [rocprof] RPL: output dir '/tmp/rpl_data_240321_155440_1274394'
|
|
|-> [rocprof] RPL: result dir '/tmp/rpl_data_240321_155440_1274394/input0_results_240321_155440'
|
|
|-> [rocprof] ROCProfiler: input from "/tmp/rpl_data_240321_155440_1274394/input0.xml"
|
|
|-> [rocprof] gpu_index =
|
|
|-> [rocprof] kernel =
|
|
|-> [rocprof] range =
|
|
|-> [rocprof] 0 metrics
|
|
|-> [rocprof] vcopy testing on GCD 0
|
|
|-> [rocprof] Finished allocating vectors on the CPU
|
|
|-> [rocprof] Finished allocating vectors on the GPU
|
|
|-> [rocprof] Finished copying vectors to the GPU
|
|
|-> [rocprof] sw thinks it moved 1.000000 KB per wave
|
|
|-> [rocprof] Total threads: 1048576, Grid Size: 4096 block Size:256, Wavefronts:16384:
|
|
|-> [rocprof] Launching the kernel on the GPU
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished executing kernel
|
|
|-> [rocprof] Finished copying the output vector from the GPU to the CPU
|
|
|-> [rocprof] Releasing GPU memory
|
|
|-> [rocprof] Releasing CPU memory
|
|
|-> [rocprof]
|
|
|-> [rocprof] ROCPRofiler: 3 contexts collected, output directory /tmp/rpl_data_240321_155440_1274394/input0_results_240321_155440
|
|
|-> [rocprof] File 'tests/workloads/ipblocks_SQ/MI100/timestamps.csv' is generating
|
|
|-> [rocprof]
|