ci-linux.yml

name: CI Linux

on:
  workflow_call:
  workflow_dispatch:
  pull_request:
  merge_group:
  push:
    branches:
      - main

concurrency:
  # A PR number if a pull request and otherwise the commit hash. This cancels
  # queued and in-progress runs for the same PR (presubmit) or commit
  # (postsubmit).
  group: ci-build-test-cpp-linux-${{ github.event.number || github.sha }}
  cancel-in-progress: true

jobs:
  build_and_ctest:
    name: Build and Test (linux, ASSERTIONS)
    runs-on: nod-ai-shared-cpubuilder-manylinux-x86_64
    strategy:
      fail-fast: true
    env:
      CACHE_DIR: ${{ github.workspace }}/.container-cache
      # either the PR number or `branch-N` where N always increments
      CACHE_KEY: linux-build-test-cpp-asserts-manylinux-v2-${{ format('{0}-{1}', github.ref_name, github.run_number) }}
    steps:
      - name: Set unified TZ
        uses: szenius/set-timezone@v2.0
        with:
          # this is an arbitrary choice
          timezoneLinux: "Asia/Singapore"
          timezoneMacos: "Asia/Singapore"
          timezoneWindows: "Singapore Standard Time"

      - name: Configure local git mirrors
        run: |
          /gitmirror/scripts/trigger_update_mirrors.sh
          /gitmirror/scripts/git_config.sh

      - name: "Checking out repository"
        env:
          BRANCH_NAME: ${{ github.ref }}
          REPO_ADDRESS: ${{ github.server_url }}/${{ github.repository }}
        run: |
          git init
          git remote add origin $REPO_ADDRESS
          git -c protocol.version=2 fetch --depth 1 origin $BRANCH_NAME
          git reset --hard FETCH_HEAD
          git -c submodule."third_party/torch-mlir".update=none \
              -c submodule."third_party/stablehlo".update=none \
              -c submodule."third_party/XRT".update=none \
              submodule update --init --recursive --depth 1 --single-branch -j 10

      - name: Python deps
        run: |
          pip install -r third_party/iree/runtime/bindings/python/iree/runtime/build_requirements.txt
          pip install pyyaml pybind11==2.13.6 nanobind==2.2.0

      - name: Enable cache
        uses: actions/cache/restore@v3
        with:
          path: ${{ env.CACHE_DIR }}
          key:  ${{ env.CACHE_KEY }}
          restore-keys: linux-build-test-cpp-

      - name: Peano dep
        run: |
          bash build_tools/download_peano.sh
          echo "PEANO_INSTALL_DIR=$PWD/llvm-aie" >> $GITHUB_ENV
          echo "ENABLE_XRT_LITE_CTS_TESTS=ON" >> $GITHUB_ENV

      - name: Build packages
        run: |
          export cache_dir="${{ env.CACHE_DIR }}"
          export CCACHE_COMPILERCHECK="string:$(clang --version)"
          bash build_tools/build_llvm.sh
          rm -rf llvm-build
          export llvm_install_dir=$PWD/llvm-install
          bash build_tools/build_test_cpp.sh

      - name: Create artifacts
        if: ${{ !cancelled() }}
        run: |
          pushd third_party/iree/third_party/llvm-project && llvm_sha_short=$(git rev-parse --short HEAD) && popd
          tar cf llvm-dist-linux-$llvm_sha_short.tar llvm-install
          tar cf iree-dist-linux.tar iree-install

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        if: ${{ !cancelled() }}
        with:
          name: linux_x86_64_llvm_packages
          path: llvm-dist-*.tar
          if-no-files-found: warn

      - name: Upload artifacts
        uses: actions/upload-artifact@v4
        if: ${{ !cancelled() }}
        with:
          name: linux_x86_64_iree_packages
          path: iree-dist-linux.tar
          if-no-files-found: warn

      - name: Save cache
        uses: actions/cache/save@v3
        if: ${{ !cancelled() && github.event_name == 'push' && github.ref_name == 'main' }}
        with:
          path: ${{ env.CACHE_DIR }}
          key: ${{ env.CACHE_KEY }}

  test_linux_phoenix:
    name: E2E Test Linux Phoenix
    needs: build_and_ctest
    strategy:
      fail-fast: false
      matrix:
        runs-on: [linux-phoenix]
    runs-on: ${{ matrix.runs-on }}
    env:
      XILINXD_LICENSE_FILE: /opt/xilinx/Xilinx.lic
    steps:
      - name: "Checking out repository" # for test scripts
        uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0
        with:
          submodules: false # not required for testbench

      - name: Download artifacts
        uses: actions/download-artifact@v4
        with:
          name: linux_x86_64_iree_packages

      - name: Extract artifact
        run: |
          tar -xvf iree-dist-linux.tar
          echo "IREE_INSTALL_DIR=$PWD/iree-install" >> $GITHUB_ENV
          echo "PYTHONPATH=$PWD/iree-install/python_packages/iree_compiler:$PWD/iree-install/python_packages/iree_runtime" >> $GITHUB_ENV
          bash build_tools/download_peano.sh
          echo "PEANO_INSTALL_DIR=$PWD/llvm-aie" >> $GITHUB_ENV

      - uses: actions/setup-python@v4
        with:
          python-version: '3.11'

      - name: Create venv and install dependencies
        run: |
          python -m venv .venv
          source .venv/bin/activate
          pip install -r tests/requirements.txt

      - name: Query device info
        run: |
          source .venv/bin/activate
          echo "aie-metadata"
          python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --aie-metadata
          echo "aie-version"
          python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --aie-version
          echo "XRT_LITE_N_CORE_ROWS=$(python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --num-rows)" >> $GITHUB_ENV
          echo "XRT_LITE_N_CORE_COLS=$(python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --num-cols)" >> $GITHUB_ENV

      - name: E2E correctness matmul test
        run: |
          # https://stackoverflow.com/a/17567422
          # shim_xdna::bo::map_drm_bo does an mmap with MAP_LOCKED
          # which can fail if limit is to low
          sudo prlimit -lunlimited --pid $$
          source .venv/bin/activate
          bash build_tools/ci/run_matmul_test.sh \
            test_matmuls \
            iree-install \
            $PWD/llvm-aie


      - name : E2E comparison of AIE to llvm-cpu
        run: |
          sudo prlimit -lunlimited --pid $$
          source .venv/bin/activate
          python build_tools/ci/cpu_comparison/run.py \
            test_aie_vs_cpu \
            $PWD/iree-install \
            --peano_dir=$PWD/llvm-aie \
            --vitis_dir=/opt/Xilinx/Vitis/2024.2 \
            --target_device="npu1_4col" \
            --reset_npu_between_runs -v \
            --xrt_lite_n_core_rows=$XRT_LITE_N_CORE_ROWS \
            --xrt_lite_n_core_cols=$XRT_LITE_N_CORE_COLS \
            --skip_tests=Performance

      # Run the 'Performance' tests. These do not check numerical correctness,
      # just measure the time to run some workloads.
      - name : Performance benchmarks
        run: |
          source .venv/bin/activate
          python build_tools/ci/cpu_comparison/run.py \
            test_aie_vs_cpu \
            $PWD/iree-install \
            --peano_dir=$PWD/llvm-aie \
            --vitis_dir=/opt/Xilinx/Vitis/2024.2 \
            --target_device="npu1_4col" \
            --reset_npu_between_runs -v \
            --xrt_lite_n_core_rows=$XRT_LITE_N_CORE_ROWS \
            --xrt_lite_n_core_cols=$XRT_LITE_N_CORE_COLS \
            --tests=Performance > performance.log

          # Print a summary of the findings.
          python build_tools/ci/cpu_comparison/performance_summarizer.py \
            performance.log

      - name: XRT-LITE tests
        run: |
          DEVICE_TEST_DIR="$PWD/iree-install/device_tests"
          for t in $(ls $DEVICE_TEST_DIR); do
            $DEVICE_TEST_DIR/$t --xrt_lite_n_core_rows=$XRT_LITE_N_CORE_ROWS --xrt_lite_n_core_cols=$XRT_LITE_N_CORE_COLS
          done

  test_linux_strix:
    name: E2E Test Linux Strix
    needs: build_and_ctest
    strategy:
      fail-fast: false
      matrix:
        runs-on: [linux-strix]
    runs-on: ${{ matrix.runs-on }}
    env:
      XILINXD_LICENSE_FILE: /opt/xilinx/Xilinx.lic
    steps:
      - name: "Checking out repository" # for test scripts
        uses: actions/checkout@8f4b7f84864484a7bf31766abe9204da3cbe65b3 # v3.5.0
        with:
          submodules: false # not required for testbench

      - name: Download artifacts
        uses: actions/download-artifact@v4
        with:
          name: linux_x86_64_iree_packages

      - name: Extract artifact
        run: |
          tar -xvf iree-dist-linux.tar
          echo "IREE_INSTALL_DIR=$PWD/iree-install" >> $GITHUB_ENV
          echo "PYTHONPATH=$PWD/iree-install/python_packages/iree_compiler:$PWD/iree-install/python_packages/iree_runtime" >> $GITHUB_ENV

      - uses: actions/setup-python@v4
        with:
          python-version: '3.11'

      - name: Create venv and install dependencies
        run: |
          python -m venv .venv
          source .venv/bin/activate
          pip install -r tests/requirements.txt

      - name: Query device info
        run: |
          source .venv/bin/activate
          echo "aie-metadata"
          python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --aie-metadata
          echo "aie-version"
          python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --aie-version
          echo "XRT_LITE_N_CORE_ROWS=$(python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --num-rows)" >> $GITHUB_ENV
          echo "XRT_LITE_N_CORE_COLS=$(python build_tools/ci/amdxdna_driver_utils/amdxdna_ioctl.py --num-cols)" >> $GITHUB_ENV

      - name : E2E comparison of AIE to llvm-cpu
        run: |
          source .venv/bin/activate
          python build_tools/ci/cpu_comparison/run.py \
            test_aie_vs_cpu \
            $PWD/iree-install \
            --vitis_dir=/opt/xilinx/Vitis/2024.2 \
            --target_device="npu4" \
            --reset_npu_between_runs \
            --xrt_lite_n_core_rows=$XRT_LITE_N_CORE_ROWS \
            --xrt_lite_n_core_cols=$XRT_LITE_N_CORE_COLS \
            -v