Skip to content

Support get-platform-details for mlperf-inference #373

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
arjunsuresh merged 3 commits into from
Oct 11, 2024
Merged

Support get-platform-details for mlperf-inference #373

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bc8b552
Update test-mlperf-inference-gptj.yml
arjunsuresh Oct 11, 2024
551bd08
Support get-platform-details for mlperf-inference
arjunsuresh Oct 11, 2024
b226b11
Merge branch 'mlcommons:mlperf-inference' into mlperf-inference
arjunsuresh Oct 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion .github/workflows/test-mlperf-inference-gptj.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,6 @@ jobs:
export CM_REPOS=$HOME/GH_CM
python3 -m pip install cm4mlops
cm pull repo
cm run script --tags=run-mlperf,inference,_submission,_short --submitter="MLCommons" --docker --model=gptj-99 --backend=${{ matrix.backend }} --device=cuda --scenario=Offline --test_query_count=1 --precision=${{ matrix.precision }} --target_qps=1 --quiet --docker_it=no --docker_cm_repo=gateoverflow@cm4mlops --adr.compiler.tags=gcc --beam_size=1 --hw_name=gh_action --docker_dt=yes --results_dir=$HOME/gh_action_results --submission_dir=$HOME/gh_action_submissions --implementation=reference --clean
cm run script --tags=run-mlperf,inference,_submission,_short --submitter="MLCommons" --docker --model=gptj-99 --backend=${{ matrix.backend }} --device=cuda --scenario=Offline --test_query_count=1 --precision=${{ matrix.precision }} --target_qps=1 --quiet --docker_it=no --docker_cm_repo=gateoverflow@cm4mlops --adr.compiler.tags=gcc --beam_size=1 --hw_name=gh_action --docker_dt=yes --results_dir=$HOME/gh_action_results --submission_dir=$HOME/gh_action_submissions --get_platform_details=yes --implementation=reference --clean
cm run script --tags=push,github,mlperf,inference,submission --repo_url=https://github.com/gateoverflow/mlperf_inference_test_submissions_v5.0 --repo_branch=main --commit_message="Results from self hosted Github actions - NVIDIARTX4090" --quiet --submission_dir=$HOME/gh_action_submissions

8 changes: 8 additions & 0 deletions script/app-mlperf-inference/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1052,6 +1052,14 @@ variations:
- mlperf-accuracy-script
- imagenet-accuracy-script
tags: run,accuracy,mlperf,_imagenet
- tags: get,platform,details
enable_if_any_env:
CM_SUDO_USER:
- yes
CM_GET_PLATFORM_DETAILS:
- yes
env:
CM_PLATFORM_DETAILS_FILE_PATH: '<<<CM_MLPERF_OUTPUT_DIR>>>/system_info.txt'

onnxruntime:
group: backend
Expand Down
5 changes: 4 additions & 1 deletion script/get-platform-details/customize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,10 @@ def preprocess(i):
#if not check_installation("cpupower",os_info):
env['CM_INSTALL_CPUPOWER'] = 'True'

return {'return':0}
if env.get('CM_PLATFORM_DETAILS_FILE_PATH', '') == '':
env['CM_GET_PLATFORM_DETAILS_FILE_PATH'] = os.path.join(os.getcwd(), "system_info.txt")

return {'return':0}


def postprocess(i):
Expand Down
1 change: 1 addition & 0 deletions script/run-mlperf-inference-app/_cm.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,7 @@ input_mapping:
find_performance: CM_MLPERF_FIND_PERFORMANCE_MODE
framework: CM_MLPERF_BACKEND
docker_keep_alive: CM_DOCKER_CONTAINER_KEEP_ALIVE
get_platform_details: CM_GET_PLATFORM_DETAILS
gpu_name: CM_NVIDIA_GPU_NAME
hw_name: CM_HW_NAME
pip_loadgen: CM_MLPERF_INFERENCE_LOADGEN_INSTALL_FROM_PIP
Expand Down