Benchmark #2
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: Benchmark | |
| on: | |
| release: | |
| types: | |
| - published | |
| workflow_dispatch: | |
| inputs: | |
| group_selection: | |
| description: "Group of Benchmarks to Run:" | |
| required: true | |
| default: "All" | |
| type: choice | |
| options: | |
| - "All" | |
| - "Transfer Learning" | |
| - "Synthetic" | |
| - "Non Transfer Learning" | |
| env: | |
| TRANSFER_LEARNING_BENCHMARKS: '["aryl_halide_CT_IM_tl","aryl_halide_IP_CP_tl","aryl_halide_CT_I_BM_tl","direct_arylation_tl_temperature","easom_tl_47_negate_noise5","hartmann_tl_3_20_15","michalewicz_tl_continuous"]' | |
| SYNTHETIC_BENCHMARKS: '["synthetic_2C1D_1C","hartmann_3d_discretized","hartmann_6d","hartmann_3d"]' | |
| ALL_BENCHMARKS: '["direct_arylation_multi_batch","direct_arylation_single_batch","aryl_halide_CT_IM_tl","aryl_halide_IP_CP_tl","aryl_halide_CT_I_BM_tl","direct_arylation_tl_temperature","easom_tl_47_negate_noise5","hartmann_tl_3_20_15","michalewicz_tl_continuous","synthetic_2C1D_1C","hartmann_3d_discretized","hartmann_6d","hartmann_3d"]' | |
| NON_TL_BENCHMARKS: '["direct_arylation_multi_batch","direct_arylation_single_batch","synthetic_2C1D_1C","hartmann_3d_discretized","hartmann_6d","hartmann_3d"]' | |
| permissions: | |
| contents: read | |
| id-token: write | |
| jobs: | |
| prepare: | |
| runs-on: ubuntu-latest | |
| outputs: | |
| benchmarks_to_execute: ${{ steps.set_benchmarks.outputs.benchmarks_to_execute }} | |
| env: | |
| RUN_GROUP: ${{ github.event.inputs.group_selection || 'All' }} | |
| steps: | |
| - name: Build matrix from group | |
| id: build_matrix_from_group | |
| run: | | |
| benchmarks_to_execute='{"benchmark_list": []}' | |
| if [ "$RUN_GROUP" = "Transfer Learning" ]; then | |
| benchmarks_to_execute='{"benchmark_list": ${{ env.TRANSFER_LEARNING_BENCHMARKS }} }' | |
| fi | |
| if [ "$RUN_GROUP" = "Non Transfer Learning" ]; then | |
| benchmarks_to_execute='{"benchmark_list": ${{ env.NON_TL_BENCHMARKS }} }' | |
| fi | |
| if [ "$RUN_GROUP" = "Synthetic" ]; then | |
| benchmarks_to_execute='{"benchmark_list": ${{ env.SYNTHETIC_BENCHMARKS }} }' | |
| fi | |
| if [ "$RUN_GROUP" = "All" ]; then | |
| benchmarks_to_execute='{"benchmark_list": ${{ env.ALL_BENCHMARKS }} }' | |
| fi | |
| echo "benchmarks_to_execute=$benchmarks_to_execute" >> "$GITHUB_ENV" | |
| - name: Set benchmarks output | |
| id: set_benchmarks | |
| run: | | |
| echo 'benchmarks_to_execute=${{ env.benchmarks_to_execute }}' >> "$GITHUB_OUTPUT" | |
| number_of_tasks=$(echo '${{ env.benchmarks_to_execute }}' | jq '.benchmark_list | length') | |
| if [ "$number_of_tasks" -le 0 ]; then | |
| echo "Please run at least one benchmark" | |
| exit 1 | |
| fi | |
| add-runner: | |
| needs: prepare | |
| runs-on: ubuntu-latest | |
| strategy: | |
| fail-fast: true | |
| matrix: ${{ fromJson(needs.prepare.outputs.benchmarks_to_execute) }} | |
| steps: | |
| - name: Generate a token | |
| id: generate-token | |
| uses: actions/create-github-app-token@v1 | |
| with: | |
| app-id: ${{ vars.APP_ID }} | |
| private-key: ${{ secrets.APP_PRIVATE_KEY }} | |
| - name: Configure AWS credentials | |
| uses: aws-actions/configure-aws-credentials@v4 | |
| with: | |
| role-to-assume: ${{ secrets.AWS_ROLE_TO_ASSUME }} | |
| role-session-name: Github_Add_Runner | |
| aws-region: eu-central-1 | |
| - name: Login to Amazon ECR | |
| id: login-ecr | |
| uses: aws-actions/amazon-ecr-login@v2 | |
| - name: Execute Lambda function | |
| run: | | |
| aws lambda invoke --function-name jit_runner_register_and_create_runner_container --cli-binary-format raw-in-base64-out --payload '{"github_api_secret": "${{ steps.generate-token.outputs.token }}", "count_container": 1, "container_compute": "M", "repository": "${{ github.repository }}" }' response.json | |
| if ! grep -q '"statusCode": 200' response.json; then | |
| echo "Lambda function failed. statusCode is not 200." | |
| exit 1 | |
| fi | |
| benchmark-test: | |
| name: run | |
| needs: [prepare, add-runner] | |
| runs-on: self-hosted | |
| strategy: | |
| fail-fast: false | |
| matrix: ${{ fromJson(needs.prepare.outputs.benchmarks_to_execute) }} | |
| timeout-minutes: 1440 | |
| env: | |
| BAYBE_BENCHMARKING_PERSISTENCE_PATH: ${{ secrets.TEST_RESULT_S3_BUCKET }} | |
| BAYBE_PARALLEL_SIMULATION_RUNS: false | |
| steps: | |
| - uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 0 | |
| - uses: actions/setup-python@v5 | |
| id: setup-python | |
| with: | |
| python-version: "3.10" | |
| - name: Benchmark | |
| run: | | |
| pip install '.[benchmarking]' | |
| python -W ignore -m benchmarks --benchmark-list "${{ matrix.benchmark_list }}" |