userbenchmark-a100.yml

name: TorchBench Userbenchmark on A100
on:
  schedule:
    - cron: '00 18 * * *' # run at 6:00 PM UTC, K8s containers will roll out at 12PM EST
  workflow_dispatch:
    inputs:
      userbenchmark_name:
        description: "Name of the user benchmark to run"
      userbenchmark_options:
        description: "Option of the user benchmark to run"

jobs:
  run-userbenchmark:
    runs-on: [a100-runner]
    timeout-minutes: 1440 # 24 hours
    environment: docker-s3-upload
    env:
      BASE_CONDA_ENV: "torchbench"
      CONDA_ENV: "userbenchmark-a100"
      PLATFORM_NAME: "gcp_a100"
      TORCHBENCH_USERBENCHMARK_SCRIBE_GRAPHQL_ACCESS_TOKEN: ${{ secrets.TORCHBENCH_USERBENCHMARK_SCRIBE_GRAPHQL_ACCESS_TOKEN }}
      AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
      AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
      SETUP_SCRIPT: "/workspace/setup_instance.sh"
    steps:
      - name: Checkout TorchBench
        uses: actions/checkout@v3
        with:
          path: benchmark
      - name: Tune Nvidia GPU
        run: |
          sudo nvidia-smi -pm 1
          sudo nvidia-smi -ac 1215,1410
          nvidia-smi
      - name: Clone and setup conda env
        run: |
          CONDA_ENV=${BASE_CONDA_ENV} . "${SETUP_SCRIPT}"
          conda create --name "${CONDA_ENV}" --clone "${BASE_CONDA_ENV}"
      - name: Install TorchBench
        run: |
          set -x
          . "${SETUP_SCRIPT}"
          pushd benchmark
          python install.py
      - name: Run user benchmark
        run: |
          set -x
          . "${SETUP_SCRIPT}"
          # remove old results
          if [ -d benchmark-output ]; then rm -Rf benchmark-output; fi
          pushd benchmark
          if [ -d .userbenchmark ]; then rm -Rf .userbenchmark; fi
          MANUAL_WORKFLOW="${{ github.event.inputs.userbenchmark_name }}"
          if [ -z "${MANUAL_WORKFLOW}" ]; then
            # Figure out what userbenchmarks we should run, and run it
            python ./.github/scripts/userbenchmark/schedule-benchmarks.py --platform ${PLATFORM_NAME}
            if [ -d ./.userbenchmark ]; then
              cp -r ./.userbenchmark ../benchmark-output
            else
              mkdir ../benchmark-output
            fi
          else
            python run_benchmark.py "${{ github.event.inputs.userbenchmark_name }}" ${{ github.event.inputs.userbenchmark_options }}
            cp -r ./.userbenchmark/"${{ github.event.inputs.userbenchmark_name }}" ../benchmark-output
          fi
      - name: Upload artifact
        uses: actions/upload-artifact@v3
        with:
          name: TorchBench result
          path: benchmark-output/
      - name: Upload result jsons to Scribe and S3
        run: |
          . "${SETUP_SCRIPT}"
          pushd benchmark
          RESULTS=($(find ${PWD}/../benchmark-output -name "metrics-*.json" -maxdepth 2 | sort -r))
          echo "Uploading result jsons: ${RESULTS}"
          for r in ${RESULTS[@]}; do
            python ./scripts/userbenchmark/upload_scribe.py --userbenchmark_json "${r}" --userbenchmark_platform "${PLATFORM_NAME}"
            python ./scripts/userbenchmark/upload_s3.py --upload-file "${r}" --userbenchmark_platform "${PLATFORM_NAME}"
          done
      - name: Clean up Conda env
        if: always()
        run: |
          . "${SETUP_SCRIPT}"
          conda deactivate && conda deactivate
          conda remove -n "${CONDA_ENV}" --all