trigger CI #1
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: "GPU AT2 gcc 12.3 cuda 12.1" | ||
| on: | ||
| workflow_call | ||
| inputs: | ||
| precision: | ||
| required: false | ||
| type: string | ||
| build_type: | ||
| required: false | ||
| type: string | ||
| jobs: | ||
| # this is more work than I'd expect, but this is how you pass info after | ||
| # operating on it in a job/step | ||
| # TODO: factor this out into an action? | ||
| # parse the inputs from the workflow call that'll be used by strategy.matrix | ||
| define_matrix: | ||
| runs-on: ubuntu-22.04 | ||
| # define the outputs that will come from the steps below | ||
| outputs: | ||
| build_type: ${{ steps.build_type.outputs.build_type }} | ||
| precision: ${{ steps.precision.outputs.precision }} | ||
| steps: | ||
| - name: Define build_type | ||
| id: build_type | ||
| env: | ||
| # if empty (i.e., triggered by PR) make ALL default | ||
| btype: ${{ inputs.build_type || 'ALL' }} | ||
| # this is a little over-cautious, since the 'else' should never happen | ||
| run: | | ||
| case ${{ env.btype }} in | ||
| "Debug") | ||
| echo 'build_type=["Debug"]' >> "$GITHUB_OUTPUT" ;; | ||
| "Release") | ||
| echo 'build_type=["Release"]' >> "$GITHUB_OUTPUT" ;; | ||
| "ALL") | ||
| echo 'build_type=["Debug", "Release"]' >> "$GITHUB_OUTPUT" ;; | ||
| *) | ||
| echo 'build_type=["Debug", "Release"]' >> "$GITHUB_OUTPUT" ;; | ||
| esac | ||
| - name: Define precision | ||
| id: precision | ||
| env: | ||
| prec: ${{ inputs.precision || 'ALL' }} | ||
| run: | | ||
| case ${{ env.prec }} in | ||
| "Debug") | ||
| echo 'precision=["single"]' >> "$GITHUB_OUTPUT" ;; | ||
| "Release") | ||
| echo 'precision=["double"]' >> "$GITHUB_OUTPUT" ;; | ||
| "ALL") | ||
| echo 'precision=["single", "double"]' >> "$GITHUB_OUTPUT" ;; | ||
| *) | ||
| echo 'precision=["single", "double"]' >> "$GITHUB_OUTPUT" ;; | ||
| esac | ||
| gcc-cuda: | ||
| runs-on: [self-hosted, m4xci-snl-cuda, cuda, gcc] | ||
| # will run other tests in the matrix even if one fails | ||
| # NOTE: prioritizes extra info over speed, so consider whether this makes sense | ||
| continue-on-error: false | ||
| needs: define_matrix | ||
| # A build matrix storing all desired configurations. | ||
| strategy: | ||
| fail-fast: true | ||
| matrix: | ||
| # to get the array instead of a string, need the fromJSON() | ||
| build-type: ${{ fromJSON(needs.define_matrix.outputs.build_type) }} | ||
| fp-precision: ${{ fromJSON(needs.define_matrix.outputs.precision) }} | ||
| name: gcc-cuda / ${{ matrix.build-type }} - ${{ matrix.fp-precision }} | ||
| steps: | ||
| - name: Check out the repository | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| persist-credentials: false | ||
| show-progress: false | ||
| submodules: recursive | ||
| - name: Cloning Haero | ||
| uses: actions/checkout@v4 | ||
| with: | ||
| repository: eagles-project/haero | ||
| submodules: recursive | ||
| path: haero_src | ||
| - name: Show action trigger | ||
| uses: ./.github/actions/show-workflow-trigger | ||
| - name: Get CUDA Arch | ||
| # NOTE: for now, only running on an H100 machine, but keep anyway | ||
| run: | | ||
| # Ensure nvidia-smi is available | ||
| if ! command -v nvidia-smi &> /dev/null; then | ||
| echo "nvidia-smi could not be found. Please ensure you have Nvidia drivers installed." | ||
| exit 1 | ||
| fi | ||
| # Get the GPU model from nvidia-smi, and set env for next step | ||
| gpu_model=$(nvidia-smi --query-gpu=name --format=csv,noheader | head -n 1) | ||
| case "$gpu_model" in | ||
| *"H100"*) | ||
| echo "H100 detected--setting Hopper90 architecture" | ||
| echo "Hopper=ON" >> $GITHUB_ENV | ||
| echo "CUDA_ARCH=90" >> $GITHUB_ENV | ||
| ARCH=90 | ||
| ;; | ||
| *"A100"*) | ||
| echo "A100 detected--setting Ampere80 architecture" | ||
| echo "Ampere=ON" >> $GITHUB_ENV | ||
| echo "CUDA_ARCH=80" >> $GITHUB_ENV | ||
| ;; | ||
| *"V100"*) | ||
| echo "V100 detected--setting Volta70 architecture" | ||
| echo "Volta=ON" >> $GITHUB_ENV | ||
| echo "CUDA_ARCH=70" >> $GITHUB_ENV | ||
| ;; | ||
| *) | ||
| echo "Unsupported GPU model: $gpu_model" | ||
| exit 1 | ||
| ;; | ||
| esac | ||
| - name: Building Haero (${{ matrix.build-type }}, ${{ matrix.fp-precision }} precision) | ||
| run: | | ||
| cmake -S haero_src -B haero_build \ | ||
| -DCMAKE_BUILD_TYPE=${{ matrix.build-type }} \ | ||
| -DCMAKE_INSTALL_PREFIX="haero_install" \ | ||
| -DCMAKE_C_COMPILER=gcc \ | ||
| -DCMAKE_CXX_COMPILER=g++ \ | ||
| -DHAERO_ENABLE_MPI=OFF \ | ||
| -DHAERO_ENABLE_GPU=ON \ | ||
| -DHAERO_PRECISION=${{ matrix.fp-precision }} | ||
| cd haero_build | ||
| make -j | ||
| make install | ||
| - name: Set nvcc_wrapper Arch | ||
| run: | | ||
| sed -i s/default_arch=\"sm_70\"/default_arch=\"sm_"$CUDA_ARCH"\"/g `pwd`/haero_install/bin/nvcc_wrapper | ||
| echo "====================================" | ||
| grep -i "default_arch=" `pwd`/haero_install/bin/nvcc_wrapper | ||
| - name: Configuring MAM4xx (${{ matrix.build-type }}, ${{ matrix.fp-precision }} precision) | ||
| run: | | ||
| cmake -S . -B build \ | ||
| -DCMAKE_CXX_COMPILER=`pwd`/haero_install/bin/nvcc_wrapper \ | ||
| -DCMAKE_C_COMPILER=gcc \ | ||
| -DCMAKE_INSTALL_PREFIX=`pwd`/install \ | ||
| -DCMAKE_BUILD_TYPE=${{ matrix.build-type }} \ | ||
| -DMAM4XX_HAERO_DIR=`pwd`/haero_install \ | ||
| -DNUM_VERTICAL_LEVELS=72 \ | ||
| -DENABLE_COVERAGE=OFF \ | ||
| -DENABLE_SKYWALKER=ON \ | ||
| -DCMAKE_CUDA_ARCHITECTURES=$CUDA_ARCH \ | ||
| -G "Unix Makefiles" | ||
| - name: Building MAM4xx (${{ matrix.build-type }}, ${{ matrix.fp-precision }} precision) | ||
| run: | | ||
| cd build | ||
| make | ||
| - name: Running tests (${{ matrix.build-type }}, ${{ matrix.fp-precision }} precision) | ||
| run: | | ||
| cd build | ||
| ctest -V --output-on-failure | ||
