Added support and fixed parallel scan in CSR kernels for Blackwell (SM_120) architecture. Added extra CUDA matrix tests. #268
Workflow file for this run
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: ARM-build | |
| on: | |
| push: | |
| branches: | |
| - 'main' | |
| - 'master' | |
| - 'develop' | |
| - 'release/**' | |
| tags: | |
| - '**' | |
| pull_request: | |
| types: [opened,synchronize] | |
| paths-ignore: | |
| - 'doc/**' | |
| workflow_dispatch: | |
| inputs: | |
| debug_enabled: | |
| description: 'Run the build with tmate debugging enabled by `debug_enabled` keyword (https://github.com/marketplace/actions/debugging-with-tmate)' | |
| required: false | |
| default: false | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ (github.head_ref && github.ref) || github.run_id }} | |
| cancel-in-progress: true | |
| jobs: | |
| arm-omp: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| config: | |
| - {shared: "ON", build_type: "Debug", name: "arm/omp/debug/shared", mixed: "OFF", half: "ON", bfloat16: "OFF"} | |
| - {shared: "OFF", build_type: "Release", name: "arm/omp/release/static", mixed: "ON", half: "ON", bfloat16: "OFF"} | |
| - {shared: "ON", build_type: "Release", name: "arm/omp/release/shared", mixed: "ON", half: "OFF", bfloat16: "ON"} | |
| - {shared: "ON", build_type: "Release", name: "arm/omp/release/shared-16bit", mixed: "ON", half: "ON", bfloat16: "ON"} | |
| name: ${{ matrix.config.name }} | |
| runs-on: [ubuntu-24.04-arm] | |
| steps: | |
| - name: Checkout the latest code (shallow clone) | |
| uses: actions/checkout@v4 | |
| - name: info | |
| run: | | |
| g++ -v | |
| cmake --version | |
| - name: Debug over SSH (tmate) | |
| uses: mxschmitt/action-tmate@v3.5 | |
| if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.debug_enabled }} | |
| - name: configure | |
| run: | | |
| mkdir build | |
| mkdir install | |
| export INSTALL_PREFIX=`pwd`/install | |
| cd build | |
| cmake .. -DCMAKE_CXX_FLAGS="-Wpedantic -ffp-contract=off" -DBUILD_SHARED_LIBS=${{ matrix.config.shared }} -DCMAKE_INSTALL_PREFIX=${INSTALL_PREFIX} -DCMAKE_BUILD_TYPE=${{ matrix.config.build_type }} -DGINKGO_MIXED_PRECISION=${{ matrix.config.mixed }} -DGINKGO_ENABLE_HALF=${{ matrix.config.half }} -DGINKGO_ENABLE_BFLOAT16=${{ matrix.config.bfloat16 }} | |
| make -j4 | |
| ctest -j4 --output-on-failure | |
| - name: install | |
| run: | | |
| cd build | |
| make install | |
| make test_install |