[rocprof-compute] Automate ctest coverage and test cases on runners with CDash (#1481)

* Add nightly coverage workflow * ruff formatting * temp workflow testing * restore workflow file * add workflow condition * update workflow file * update workflow file * fix typo in run-ci.py * edit run-ci.py * add python deps install * add python deps install * add python deps install * add python deps install * check if enable coverage is on when using workflow * remove github CI breakdown and fix enable coverage * set cache variables must be set before dashboard starts * Update run-ci.py * Update run-ci.py to fix ctest cache * Update rocprofiler-compute-code-coverage.yml to install tests * Update rocprofiler-compute-code-coverage.yml * Restore workflow file * Update run-ci.py * Simplify workflow build command * Update run-ci.py to build tests * edited run-ci script * edit ctest configure commands * edit ctest configure commands to be on one line * edit ctest configure command to include path to amdclang++ * update clang check in tests/cmakelists.txt * update rocm * update rocm * update rocm version 7.0.2 * update tests/CMakeLists.txt * use tarball instead for rocm install * apt install rocm-dev instead for 7.0.0 release * workflow tweaks * update to use new 'tools' dir * install rocm-dev * add CMAKE_CXX_COMPILER as clang * update tests/cmakelists.txt * update cdasg site and build names * remove run automatically on pull requests * ruff format * increased timeouts for tests * add back reruns for workflow testing * fix typo * rename workflow "nightly" -> "code" * added tracks to keep track of gpu (325 vs 355) * remove test_db_connector.py * revert build names and tracking * update workflow pushes * CMake format * changed parallel level back to 1
2025-11-17 09:24:24 -05:00
parent 75ad45d5f1
commit d49e2e35fd
8 changed files with 392 additions and 5996 deletions
@@ -0,0 +1,157 @@
+name: rocprofiler-compute Code Coverage
+run-name: rocprofiler-compute-code-coverage
+
+on:
+  schedule:
+    - cron: '0 2 * * *'
+  workflow_dispatch:
+    inputs:
+      runner_matrix:
+        description: 'Runner configuration'
+        required: false
+        type: string
+
+env:
+  ROCM_PATH: "/opt/rocm"
+  ROCM_VERSION: "7.0.2"
+
+jobs:
+  prepare_matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.generate_matrix.outputs.matrix }}
+
+    steps:
+      - name: Generate matrix
+        id: generate_matrix
+        run: |
+          MATRIX='[{"os-release":"22.04","gpu":"mi355","arch":"gfx950","runner":"linux-mi355-1gpu-ossci-rocm","code-name":"jammy"},{"os-release":"24.04","gpu":"mi355","arch":"gfx950","runner":"linux-mi355-1gpu-ossci-rocm","code-name":"noble"},{"os-release":"22.04","gpu":"mi325","arch":"gfx94X","runner":"linux-mi325-1gpu-ossci-rocm","code-name":"jammy"},{"os-release":"24.04","gpu":"mi325","arch":"gfx94X","runner":"linux-mi325-1gpu-ossci-rocm","code-name":"noble"}]'
+          
+          if [ -n "${{ github.event.inputs.runner_matrix }}" ]; then
+            MATRIX='${{ github.event.inputs.runner_matrix }}'
+          fi
+          
+          echo "matrix=${MATRIX}" >> $GITHUB_OUTPUT
+
+  coverage:
+    name: Coverage • ${{ matrix.system.gpu }} • Ubuntu ${{ matrix.system.os-release }}
+    needs: prepare_matrix
+    strategy:
+      fail-fast: false
+      matrix:
+        system: ${{ fromJSON(needs.prepare_matrix.outputs.matrix) }}
+    runs-on: ${{ matrix.system.runner }}
+    env:
+      HIP_PLATFORM: "amd"
+      OMPI_ALLOW_RUN_AS_ROOT: 1
+      OMPI_ALLOW_RUN_AS_ROOT_CONFIRM: 1
+    permissions:
+      packages: read
+    container:
+      image: ghcr.io/rocm/rocprofiler-ubuntu:${{ matrix.system.os-release }}-systems-ci-${{ matrix.system.arch }}
+      options: 
+        --privileged 
+        --ipc host
+        --group-add video
+        --device /dev/kfd
+        --device /dev/dri
+        --cap-add CAP_SYS_ADMIN
+        
+    steps:
+      - uses: actions/checkout@v5
+        with:
+          sparse-checkout: projects/rocprofiler-compute/
+
+      - name: Update system packages
+        run: |
+          apt-get update
+          apt-get dist-upgrade -y
+          echo "✅ System packages updated!"
+
+      - name: Install amdgpu and dependencies
+        shell: bash
+        run: |
+          ROCM_MAJOR=$(echo ${{ env.ROCM_VERSION }} | sed 's/\./ /g' | awk '{print $1}')
+          ROCM_MINOR=$(echo ${{ env.ROCM_VERSION }} | sed 's/\./ /g' | awk '{print $2}')
+          ROCM_VERSN=$(( (${ROCM_MAJOR}*10000)+(${ROCM_MINOR}*100) ))
+          wget -N -P /tmp/ https://repo.radeon.com/amdgpu-install/${ROCM_MAJOR}.${ROCM_MINOR}/ubuntu/${{ matrix.system.code-name }}/amdgpu-install_${ROCM_MAJOR}.${ROCM_MINOR}.${ROCM_VERSN}-1_all.deb
+          apt-get install -y /tmp/amdgpu-install_${ROCM_MAJOR}.${ROCM_MINOR}.${ROCM_VERSN}-1_all.deb
+          apt-get update
+          apt install -y amd-smi-lib libdw-dev
+          echo "✅ amdgpu and dependencies Installed!"
+
+      - name: Install MPI
+        run: |
+          apt install -y libopenmpi-dev
+          echo "✅ MPI Installed!"
+
+      - name: Install ROCm
+        run: |
+          apt install -y rocm-dev
+          echo "✅ ROCm Installation Complete!"
+
+      - name: Install Python Dependencies
+        working-directory: projects/rocprofiler-compute
+        run: |
+          pip install -r requirements.txt --break-system-packages --ignore-installed
+          pip install -r requirements-test.txt --break-system-packages --ignore-installed
+          echo "✅ Python dependencies installed!"
+
+      - name: Configure, Build, Test, and Upload Coverage
+        id: run_coverage
+        timeout-minutes: 120
+        working-directory: projects/rocprofiler-compute
+        continue-on-error: true
+        run: |
+          set -e
+          git config --global --add safe.directory ${GITHUB_WORKSPACE}
+          git config --global --add safe.directory ${PWD}
+
+          BUILD_NAME="ROCm/rocprofiler-compute-${{ github.ref_name }}-ubuntu-${{ matrix.system.os-release }}-${{ matrix.system.gpu }}"
+          SITE_NAME="${{ matrix.system.runner }}"
+
+          PATH=${{ env.ROCM_PATH }}/bin:${{ env.ROCM_PATH }}/llvm/bin:$PATH \
+          LD_LIBRARY_PATH=${{ env.ROCM_PATH }}/lib:${{ env.ROCM_PATH }}/llvm/lib:$LD_LIBRARY_PATH \
+          python3 ./tools/run-ci.py \
+            --build-name "${BUILD_NAME}" \
+            --site "${SITE_NAME}" \
+            --mode "Nightly" \
+            --build-jobs 16 \
+            --pytest-numprocs 8 \
+            --install
+
+      - name: Check Coverage Configuration
+        if: always()
+        working-directory: projects/rocprofiler-compute
+        run: |
+          echo "=== Checking Build Configuration ==="
+          if [ -f "build/CMakeCache.txt" ]; then
+            echo "CMakeCache.txt contents (relevant variables):"
+            grep -E "ENABLE_TESTS|ENABLE_COVERAGE|INSTALL_TESTS|PYTEST_NUMPROCS" build/CMakeCache.txt || echo "⚠️ Coverage variables not found!"
+            echo ""
+            echo "=== Checking for coverage.xml ==="
+            if [ -f "build/coverage.xml" ]; then
+              echo "✅ coverage.xml found!"
+              ls -lh build/coverage.xml
+            else
+              echo "❌ coverage.xml NOT found!"
+            fi
+            echo ""
+            echo "=== Checking CTest results ==="
+            if [ -f "build/Testing/Temporary/LastTest.log" ]; then
+              echo "Last 50 lines of test log:"
+              tail -n 50 build/Testing/Temporary/LastTest.log
+            fi
+          else
+            echo "❌ build/CMakeCache.txt not found - build may have failed!"
+          fi
+
+      - name: Upload Logs on Failure
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-logs-${{ matrix.system.gpu }}-${{ matrix.system.os-release }}
+          path: |
+            projects/rocprofiler-compute/build/Testing/Temporary/LastTest*.log
+            projects/rocprofiler-compute/build/coverage.xml
+          retention-days: 7