name: Continuous Integration

on:
  workflow_dispatch:
  push:
    branches: [ "main" ]
    paths-ignore:
      - '*.md'
      - 'source/docs/**'
  pull_request:
    branches: [ "main" ]
    paths-ignore:
      - '*.md'
      - 'source/docs/**'

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

env:
  # TODO(jrmadsen): replace LD_RUNPATH_FLAG, GPU_LIST, etc. with internal handling in cmake
  ROCM_PATH: "/opt/rocm"
  GPU_LIST: "gfx900 gfx906 gfx908 gfx90a gfx940 gfx941 gfx942 gfx1030 gfx1100 gfx1101 gfx1102"
  PATH: "/usr/bin:$PATH"

jobs:
  get_latest_mainline_build_number:
    # Run job on vega20 instead of mi200 as mi200 is unstable, as per ammar's instructions.
    # TODO: Change it back when re-enabling on mi200
    #runs-on: mi200
    runs-on: vega20

    outputs:
      LATEST_BUILD_NUMBER: ${{ steps.get_build_number.outputs.LATEST_BUILD_NUMBER }}

    steps:
      - id: get_build_number
        run: echo "LATEST_BUILD_NUMBER=$(wget -qO- 'http://rocm-ci.amd.com/job/compute-rocm-dkms-no-npi-hipclang/lastSuccessfulBuild/buildNumber')" >> $GITHUB_OUTPUT

  # Changed job name from mi200-ubuntu to vega20-ubuntu
  # TODO: Change it back when re-enabling on mi200
  vega20-ubuntu:
    # See: https://docs.github.com/en/free-pro-team@latest/actions/learn-github-actions/managing-complex-workflows#using-a-build-matrix
    strategy:
      fail-fast: true
      max-parallel: 4
      matrix:
        include:
          # Run job on vega20 instead of mi200 as mi200 is unstable, as per ammar's instructions.
          # TODO: Change it back when re-enabling on mi200
          # - os: 'ubuntu-22.04'
          #   runner: 'renderD131'
          #   device: '/renderD131'
          #   build-type: 'RelWithDebInfo'
          #   ci-flags: '--linter clang-tidy'
          #   name-tag: ''
          - os: 'ubuntu-22.04'
            runner: 'vega20'
            build-type: 'RelWithDebInfo'
            ci-flags: '--linter clang-tidy'
            name-tag: ''

    runs-on: ${{ matrix.runner }}

    # define this for containers
    env:
      GIT_DISCOVERY_ACROSS_FILESYSTEM: 1

    # TODO: Uncomment this when re-enabling tests on the mi200 as it contains --memory and --cpus flag for the mi200. Remove these 2 options when running on vega20.
    # vega20 machine only has 24 cpus available.
    # container:
    #   image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-no-npi-hipclang:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1
    #   options: --memory=128g --cpus=32 --ipc=host --device=/dev/kfd --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined

    container:
      image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-no-npi-hipclang:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1
      options: --ipc=host --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined

    needs: get_latest_mainline_build_number

    steps:
    - uses: actions/checkout@v4
      with:
        submodules: true

    - name: Install requirements
      shell: bash
      run: |
        git config --global --add safe.directory '*'
        apt-get update
        apt-get install -y cmake clang-tidy-11 g++-11 g++-12 libgtest-dev python3-pip
        update-alternatives --install /usr/bin/clang-tidy clang-tidy /usr/bin/clang-tidy-11 10
        update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-11 10 --slave /usr/bin/g++ g++ /usr/bin/g++-11
        update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 20 --slave /usr/bin/g++ g++ /usr/bin/g++-12
        python3 -m pip install -r requirements.txt
        python3 -m pip install pytest

    - name: List Files
      shell: bash
      run: |
        which-realpath() { echo "$1 resolves to $(realpath $(which $1))"; }
        for i in python python3 git cmake ctest; do which-realpath $i; done
        ls -la

    - name: Configure, Build, and Test
      timeout-minutes: 30
      shell: bash
      # Replaced 'mi200' with '${{ matrix.runner }}' when disabling jobs on mi200 and running it on vega20.
      # TODO: Change it back when re-enabling on mi200
      run:
        python3 ./source/scripts/run-ci.py -B build
          --name ${{ github.repository }}-${{ github.ref_name }}-${{ matrix.runner }}-${{ matrix.os }}${{ matrix.name-tag }}
          --build-jobs 8
          --site ${{ matrix.runner }}
          --gpu-targets ${{ env.GPU_LIST }}
          ${{ matrix.ci-flags }}
          --
          -DCMAKE_BUILD_TYPE=${{ matrix.build-type }}
          -DCMAKE_INSTALL_PREFIX=/opt/rocprofiler/v2
          -DCPACK_GENERATOR='DEB;RPM;TGZ'
          -DPython3_EXECUTABLE=$(which python3)

    - name: Install
      timeout-minutes: 10
      run:
        cmake --build build --target install --parallel 8

    - name: Test Install Build
      timeout-minutes: 10
      shell: bash
      run: |
        CMAKE_PREFIX_PATH=/opt/rocprofiler/v2 cmake -B build-samples samples
        cmake --build build-samples --target all --parallel 8

    - name: Build Packaging
      timeout-minutes: 10
      run:
        cmake --build build --target package --parallel 8

    - name: Archive production artifacts
      uses: actions/upload-artifact@v3
      with:
        name: artifacts
        path: |
          ${{github.workspace}}/build/*.deb
          ${{github.workspace}}/build/*.rpm
          ${{github.workspace}}/build/*.tgz

  code-coverage:
    strategy:
      fail-fast: true
      max-parallel: 4
      matrix:
      # TODO: Change it back when re-enabling on mi200
        include:
            - os: 'ubuntu-22.04'
              runner: 'vega20'
              build-type: 'Release'
        # include:
        #     - os: 'ubuntu-22.04'
        #       runner: 'renderD131'
        #       device: '/renderD131'
        #       build-type: 'Release'

    runs-on: ${{ matrix.runner }}

    # define this for containers
    env:
      GIT_DISCOVERY_ACROSS_FILESYSTEM: 1

    # TODO: Uncomment this when re-enabling tests on the mi200 as it contains --memory and --cpus flag for the mi200. Remove these 2 options when running on vega20.
    # vega20 machine only has 24 cpus available.
    container:
      image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-no-npi-hipclang:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1
      options: --ipc=host --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined
    
    # container:
    #   image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-no-npi-hipclang:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1
    #   options: --memory=128g --cpus=32 --ipc=host --device=/dev/kfd --device=/dev/dri${{ matrix.device }} --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined

    needs: get_latest_mainline_build_number

    steps:
    - uses: actions/checkout@v4
      with:
        submodules: true

    - name: List Files
      shell: bash
      run: |
        which-realpath() { echo "$1 resolves to $(realpath $(which $1))"; }
        for i in python python3 git cmake ctest; do which-realpath $i; done
        ls -la

    - name: Install requirements
      shell: bash
      run: |
        git config --global --add safe.directory '*'
        apt-get install -y cmake libgtest-dev python3-pip
        python3 -m pip install -r requirements.txt
        python3 -m pip install pytest

    - name: Configure, Build, and Test (Total Code Coverage)
      timeout-minutes: 30
      shell: bash
      # Replaced 'mi200' with '${{ matrix.runner }}' when disabling jobs on mi200 and running it on vega20.
      # TODO: Change it back when re-enabling on mi200
      run:
        python3 ./source/scripts/run-ci.py -B build
          --name ${{ github.repository }}-${{ github.ref_name }}-${{ matrix.runner }}-${{ matrix.os }}-codecov
          --build-jobs 8
          --site ${{ matrix.runner }}
          --gpu-targets ${{ env.GPU_LIST }}
          --coverage all
          --
          -DCMAKE_BUILD_TYPE=${{ matrix.build-type }}
          -DPython3_EXECUTABLE=$(which python3)

    - name: Configure, Build, and Test (Tests Code Coverage)
      timeout-minutes: 30
      shell: bash
      run:
        find build -type f | egrep '\.gcda$' | xargs rm &&
        python3 ./source/scripts/run-ci.py -B build
          --name ${{ github.repository }}-${{ github.ref_name }}-${{ matrix.runner }}-${{ matrix.os }}-codecov-tests
          --build-jobs 8
          --site ${{ matrix.runner }}
          --gpu-targets ${{ env.GPU_LIST }}
          --coverage tests
          --
          -DCMAKE_BUILD_TYPE=${{ matrix.build-type }}
          -DPython3_EXECUTABLE=$(which python3)

    - name: Configure, Build, and Test (Samples Code Coverage)
      timeout-minutes: 30
      shell: bash
      run:
        find build -type f | egrep '\.gcda$' | xargs rm &&
        python3 ./source/scripts/run-ci.py -B build
          --name ${{ github.repository }}-${{ github.ref_name }}-${{ matrix.runner }}-${{ matrix.os }}-codecov-samples
          --build-jobs 8
          --site ${{ matrix.runner }}
          --gpu-targets ${{ env.GPU_LIST }}
          --coverage samples
          --
          -DCMAKE_BUILD_TYPE=${{ matrix.build-type }}
          -DPython3_EXECUTABLE=$(which python3)

    - name: Verify Test Labels
      timeout-minutes: 5
      shell: bash
      run: |
        pushd build
        #
        # if following fails, there is a test that does not have
        # a label identifying it as sample or test (unit or integration).
        # Recommended labels are:
        #   - samples
        #   - unittests
        #   - integration-tests
        #
        ctest -N -LE 'samples|tests' -O ctest.mislabeled.log
        grep 'Total Tests: 0' ctest.mislabeled.log
        #
        # if following fails, then there is overlap between the labels.
        # A test cannot both be a sample and (unit/integration) test.
        #
        ctest -N -O ctest.all.log
        ctest -N -O ctest.samples.log -L samples
        ctest -N -O ctest.tests.log -L tests
        NUM_ALL=$(grep 'Total Tests:' ctest.all.log | awk '{print $NF}')
        NUM_SAMPLE=$(grep 'Total Tests:' ctest.samples.log | awk '{print $NF}')
        NUM_TEST=$(grep 'Total Tests:' ctest.tests.log | awk '{print $NF}')
        NUM_SUM=$((${NUM_SAMPLE} + ${NUM_TEST}))
        echo "Total tests: ${NUM_ALL}"
        echo "Total labeled tests: ${NUM_SUM}"
        if [ ${NUM_ALL} != ${NUM_SUM} ]; then
            echo "Test label overlap"
            exit 1
        fi
        popd

  sanitizers:
    strategy:
      fail-fast: false
      matrix:
        include:
          # Run job on vega20 instead of mi200 as mi200 is unstable, as per ammar's instructions.
          # TODO: Change it back when re-enabling on mi200
          - os: 'ubuntu-22.04'
            runner: 'vega20'
            build-type: 'RelWithDebInfo'
            ci-flags: ''
            sanitizer: 'AddressSanitizer'
          - os: 'ubuntu-22.04'
            runner: 'vega20'
            build-type: 'RelWithDebInfo'
            ci-flags: ''
            sanitizer: 'ThreadSanitizer'
          - os: 'ubuntu-22.04'
            runner: 'vega20'
            build-type: 'RelWithDebInfo'
            ci-flags: ''
            sanitizer: 'LeakSanitizer'
          # - os: 'ubuntu-22.04'
          #   runner: 'renderD131'
          #   device: '/renderD131'
          #   build-type: 'RelWithDebInfo'
          #   ci-flags: ''
          #   sanitizer: 'AddressSanitizer'
          # - os: 'ubuntu-22.04'
          #   runner: 'renderD131'
          #   device: '/renderD131'
          #   build-type: 'RelWithDebInfo'
          #   ci-flags: ''
          #   sanitizer: 'ThreadSanitizer'
          # - os: 'ubuntu-22.04'
          #   runner: 'renderD131'
          #   device: '/renderD131'
          #   build-type: 'RelWithDebInfo'
          #   ci-flags: ''
          #   sanitizer: 'LeakSanitizer'

    runs-on: ${{ matrix.runner }}

    # define this for containers
    env:
      GIT_DISCOVERY_ACROSS_FILESYSTEM: 1

    container:
      image: compute-artifactory.amd.com:5000/rocm-plus-docker/compute-rocm-dkms-no-npi-hipclang:${{ needs.get_latest_mainline_build_number.outputs.LATEST_BUILD_NUMBER }}-${{ matrix.os }}-stg1
      options: --privileged --ipc=host --device=/dev/kfd --device=/dev/dri --group-add video --cap-add=SYS_PTRACE --cap-add CAP_SYS_PTRACE --cap-add CAP_SYS_ADMIN --security-opt seccomp=unconfined

    needs: get_latest_mainline_build_number

    steps:
    - uses: actions/checkout@v4
      with:
        submodules: true

    - name: List Files
      shell: bash
      run: |
        which-realpath() { echo "$1 resolves to $(realpath $(which $1))"; }
        for i in python python3 git cmake ctest; do which-realpath $i; done
        ls -la

    - name: Install requirements
      shell: bash
      run: |
        git config --global --add safe.directory '*'
        apt-get install -y cmake libgtest-dev python3-pip libasan8 libtsan2
        python3 -m pip install -r requirements.txt
        python3 -m pip install pytest

    - name: Configure, Build, and Test
      timeout-minutes: 45
      shell: bash
      run:
        python3 ./source/scripts/run-ci.py -B build
          --name ${{ github.repository }}-${{ github.ref_name }}-${{ matrix.runner }}-${{ matrix.sanitizer }}
          --build-jobs 8
          --site ${{ matrix.runner }}
          --gpu-targets ${{ env.GPU_LIST }}
          --memcheck=${{ matrix.sanitizer }}
          ${{ matrix.ci-flags }}
          --
          -DCMAKE_BUILD_TYPE=${{ matrix.build-type }}
          -DCMAKE_INSTALL_PREFIX="${{ env.ROCM_PATH }}"
          -DPython3_EXECUTABLE=$(which python3)