ColossalAI/.github/workflows/build_on_pr.yml

name: Build on PR

on:
  pull_request:
    types: [synchronize, labeled]

jobs:
  detect:
    name: Detect file change
    if: |
      github.event.pull_request.draft == false &&
      github.base_ref == 'main' &&
      github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' &&
      contains( github.event.pull_request.labels.*.name, 'Run Build and Test')      
    outputs:
      changedExtenisonFiles: ${{ steps.find-extension-change.outputs.all_changed_files }}
      anyExtensionFileChanged: ${{ steps.find-extension-change.outputs.any_changed }}
      changedLibraryFiles: ${{ steps.find-lib-change.outputs.all_changed_files }}
      anyLibraryFileChanged: ${{ steps.find-lib-change.outputs.any_changed }}
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v2
        with:
          fetch-depth: 0
          ref: ${{ github.event.pull_request.head.sha }}

      - name: Locate base commit
        id: locate-base-sha
        run: |
          curBranch=$(git rev-parse --abbrev-ref HEAD)
          commonCommit=$(git merge-base origin/main $curBranch)
          echo $commonCommit
          echo "baseSHA=$commonCommit" >> $GITHUB_OUTPUT          

      - name: Find the changed extension-related files
        id: find-extension-change
        uses: tj-actions/changed-files@v35
        with:
          base_sha: ${{ steps.locate-base-sha.outputs.baseSHA }}
          files: |
            op_builder/**
            colossalai/kernel/**
            setup.py            

      - name: Find the changed library-related files
        id: find-lib-change
        uses: tj-actions/changed-files@v35
        with:
          base_sha: ${{ steps.locate-base-sha.outputs.baseSHA }}
          files: |
            **/*.py
            **/*.h
            **/*.cpp
            **/*.cu
            **/*.txt            

      - name: List changed files
        run: |
          for file in ${{ steps.find-extension-change.outputs.all_changed_files }}; do
            echo "$file was changed"
          done
          for file in ${{ steps.find-lib-change.outputs.all_changed_files }}; do
            echo "$file was changed"
          done          

  build:
    name: Build and Test Colossal-AI
    needs: detect
    runs-on: [self-hosted, gpu]
    container:
      image: hpcaitech/pytorch-cuda:1.12.0-11.3.0
      options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
    timeout-minutes: 60
    defaults:
      run:
        shell: bash
    steps:
      - name: Checkout TensorNVMe
        uses: actions/checkout@v2
        with:
          repository: hpcaitech/TensorNVMe
          ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
          path: TensorNVMe

      - name: Restore TensorNVMe Cache
        run: |
          [ ! -z "$(ls -A /github/home/tensornvme_cache/)" ] && cp -p -r /github/home/tensornvme_cache/* /__w/ColossalAI/ColossalAI/TensorNVMe          

      - name: Install TensorNVMe
        run: |
          cd TensorNVMe
          conda install cmake
          pip install -r requirements.txt
          pip install -v .          

      - name: Store TensorNVMe Cache
        run: |
          cd TensorNVMe
          cp -p -r ./build /github/home/tensornvme_cache/          

      - name: Checkout Colossal-AI
        uses: actions/checkout@v2
        with:
          ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}

      - name: Restore Colossal-AI Cache
        if: needs.detect.outputs.anyExtensionFileChanged != 'true'
        run: |
          # -p flag is required to preserve the file timestamp to avoid ninja rebuild
          [ ! -z "$(ls -A /github/home/cuda_ext_cache/)" ] && cp -p -r /github/home/cuda_ext_cache/* /__w/ColossalAI/ColossalAI/          

      - name: Install Colossal-AI
        if: needs.detect.outputs.anyLibraryFileChanged == 'true'
        run: |
          CUDA_EXT=1 pip install -v -e .
          pip install -r requirements/requirements-test.txt          

      - name: Store Colossal-AI Cache
        run: |
          # -p flag is required to preserve the file timestamp to avoid ninja rebuild
          cp -p -r /__w/ColossalAI/ColossalAI/build /github/home/cuda_ext_cache/          

      - name: Restore Testmon Cache
        run: |
          if [ -d /github/home/testmon_cache ]; then
            [ ! -z "$(ls -A /github/home/testmon_cache)" ] && cp -p -r /github/home/testmon_cache/.testmondata /__w/ColossalAI/ColossalAI/
          fi          

      - name: Execute Unit Testing
        if: needs.detect.outputs.anyLibraryFileChanged == 'true'
        run: |
          CURL_CA_BUNDLE="" PYTHONPATH=$PWD pytest --testmon --testmon-cov=. tests/          
        env:
          DATA: /data/scratch/cifar-10
          NCCL_SHM_DISABLE: 1
          LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64

      - name: Store Testmon Cache
        run: |
          [ -d /github/home/testmon_cache ] || mkdir /github/home/testmon_cache
          cp -p -r /__w/ColossalAI/ColossalAI/.testmondata /github/home/testmon_cache/          

      - name: Collate artifact
        env:
          PR_NUMBER: ${{ github.event.number }}
          changedLibraryFiles: ${{ needs.detect.outputs.changedLibraryFiles }}
          anyLibraryFileChanged: ${{ needs.detect.outputs.anyLibraryFileChanged }}
          changedExtenisonFiles: ${{ needs.detect.outputs.changedExtenisonFiles }}
        run: |
          mkdir report
          echo $PR_NUMBER > ./report/pr_number

          # generate coverage.xml if any
          if [ "$anyLibraryFileChanged" == "true" ] && [ -e .coverage ]; then
            allFiles=""
            for file in $changedLibraryFiles; do
              if [ "$allFiles" == "" ]; then
                allFiles=$file
              else
                allFiles=$allFiles,$file
              fi
            done

            coverage report --data-file .coverage --include $allFiles > ./coverage.txt

            covPercentage=$(tail -n 1 coverage.txt  | grep -o '[1-9]*%$')
            covNum=${covPercentage::-1}
            mv coverage.txt ./report
            echo $covNum > ./report/cov_number
          else
            echo "No coverage report is generated"
          fi          

      - name: Upload test coverage artifact
        uses: actions/upload-artifact@v3
        with:
          name: report
          path: report/