build-rapids.yml

name: Build all RAPIDS repositories

on:
  workflow_call:

jobs:
  check-event:
    name: Check GH Event
    runs-on: ubuntu-latest
    outputs:
      ok: ${{ steps.check_gh_event.outputs.ok }}
    steps:
      - id: check_gh_event
        name: Check GH Event
        shell: bash
        run: |
          [[ '${{ github.event_name }}' == 'push' && '${{ github.repository }}' == 'NVIDIA/cccl' ]] || \
          [[ '${{ github.event_name }}' == 'schedule' && '${{ github.repository }}' == 'NVIDIA/cccl' ]] || \
          [[ '${{ github.event_name }}' == 'pull_request' && '${{ github.repository }}' != 'NVIDIA/cccl' ]] \
          && echo "ok=true"  | tee -a $GITHUB_OUTPUT \
          || echo "ok=false" | tee -a $GITHUB_OUTPUT;

  build-rapids:
    name: "${{ matrix.libs }}"
    if: needs.check-event.outputs.ok == 'true'
    needs: check-event
    runs-on: ${{ fromJSON(github.repository != 'NVIDIA/cccl' && '"ubuntu-latest"' || '"linux-amd64-cpu32"') }}
    strategy:
      fail-fast: false
      matrix:
        include:
          - { cuda: '12.2', libs: 'rmm KvikIO cudf cudf_kafka cuspatial',        }
          - { cuda: '12.2', libs: 'rmm ucxx raft cuvs',                          }
          - { cuda: '12.2', libs: 'rmm ucxx raft cumlprims_mg cuml',             }
          - { cuda: '12.2', libs: 'rmm ucxx raft cugraph-ops wholegraph cugraph' }
    permissions:
      id-token: write
      contents: read
    steps:
      - name: Checkout repo
        uses: actions/checkout@v4
        with:
          fetch-depth: 0
          persist-credentials: false
      - name: Add NVCC problem matcher
        run: echo "::add-matcher::$(pwd)/.github/problem-matchers/problem-matcher.json"
      - uses: aws-actions/configure-aws-credentials@v4
        with:
          role-to-assume: arn:aws:iam::279114543810:role/gha-oidc-NVIDIA
          aws-region: us-east-2
          role-duration-seconds: 43200 # 12h
      - name: Run command # Do not change this step's name, it is checked in parse-job-times.py
        env:
          CI: true
          RAPIDS_LIBS: ${{ matrix.libs }}
          # Uncomment any of these to customize the git repo and branch for a RAPIDS lib:
          # RAPIDS_cmake_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_cudf_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_cudf_kafka_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_cugraph_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_cugraph_ops_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_cuml_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_cumlprims_mg_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_cuspatial_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_cuvs_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_KvikIO_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_raft_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_rmm_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
          # RAPIDS_ucxx_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-0.39"}'
          # RAPIDS_wholegraph_GIT_REPO: '{"upstream": "rapidsai", "tag": "branch-24.08"}'
        run: |
          cat <<"EOF" > "$RUNNER_TEMP/ci-entrypoint.sh"
          #! /usr/bin/env bash
          # Start the ssh-agent and add the repo deploy keys
          if ! pgrep ssh-agent >/dev/null 2>&1; then eval "$(ssh-agent -s)"; fi
          ssh-add - <<< '${{ secrets.RAPIDSAI_CUMLPRIMS_DEPLOY_KEY }}'
          ssh-add - <<< '${{ secrets.RAPIDSAI_CUGRAPH_OPS_DEPLOY_KEY }}'
          devcontainer-utils-init-ssh-deploy-keys || true
          exec "$@"
          EOF

          cat <<"EOF" > "$RUNNER_TEMP/ci.sh"
          #! /usr/bin/env bash
          set -eo pipefail

          . ~/cccl/ci/rapids/post-create-command.sh;

          declare -a failures
          declare -A failures_map

          # Configure and build each lib with -DBUILD_TESTS=OFF, then again with -DBUILD_TESTS=ON
          for RAPIDS_ENABLE_TESTS in OFF ON; do
            _apply_manifest_modifications;
            for lib in ${RAPIDS_LIBS}; do
              sccache -z
              if ! configure-${lib}-cpp || ! build-${lib}-cpp; then
                if ! test -v failures_map["${lib}"]; then
                  failures+=("${lib}")
                  failures_map["${lib}"]=1
                fi
              fi
              sccache --show-adv-stats
            done
          done

          # Print failures and exit
          if test ${#failures[@]} -gt 0; then
            echo "::error:: Failures: ${failures[*]}"
            echo -e "::group::️❗ \e[1;31mInstructions to Reproduce CI Failure Locally\e[0m"
            echo "::error:: To replicate this failure locally, follow the steps below:"
            echo "1. Clone the repository, and navigate to the correct branch and commit:"
            echo "   git clone --branch $GITHUB_REF_NAME --single-branch https://github.com/$GITHUB_REPOSITORY.git && cd $(echo $GITHUB_REPOSITORY | cut -d'/' -f2) && git checkout $GITHUB_SHA"
            echo ""
            echo "2. Run the failed command inside the same Docker container used by this CI job:"
            cat <<__EOF
             RAPIDS_LIBS='${RAPIDS_LIBS}'$(for lib in cmake ${RAPIDS_LIBS}; do var=RAPIDS_${lib//-/_}_GIT_REPO; if test -v "$var" && test -n "${!var}"; then echo -n " $var='${!var}'"; fi; done) \\
               .devcontainer/launch.sh -d -c ${{matrix.cuda}} -H rapids-conda -- ./ci/rapids/rapids-entrypoint.sh \\
               /bin/bash -li -c 'uninstall-all -j -qqq && clean-all -j && build-all -j -v || exec /bin/bash -li'
          __EOF
            echo ""
            echo "For additional information, see:"
            echo "   - DevContainer Documentation: https://github.com/NVIDIA/cccl/blob/main/.devcontainer/README.md"
            echo "   - Continuous Integration (CI) Overview: https://github.com/NVIDIA/cccl/blob/main/ci-overview.md"
            exit 1
          fi
          EOF

          chmod +x "$RUNNER_TEMP"/ci{,-entrypoint}.sh

          mkdir -p .aws

          cat <<EOF > .aws/config
          [default]
          bucket=rapids-sccache-devs
          region=us-east-2
          EOF

          cat <<EOF > .aws/credentials
          [default]
          aws_access_key_id=$AWS_ACCESS_KEY_ID
          aws_session_token=$AWS_SESSION_TOKEN
          aws_secret_access_key=$AWS_SECRET_ACCESS_KEY
          EOF

          chmod 0600 .aws/credentials
          chmod 0664 .aws/config

          .devcontainer/launch.sh \
            --docker \
            --cuda ${{matrix.cuda}} \
            --host rapids-conda \
            --env VAULT_HOST= \
            --env "GITHUB_SHA=$GITHUB_SHA" \
            --env "GITHUB_REF_NAME=$GITHUB_REF_NAME" \
            --env "GITHUB_REPOSITORY=$GITHUB_REPOSITORY" \
            --volume "$RUNNER_TEMP/ci.sh:/ci.sh" \
            --volume "$RUNNER_TEMP/ci-entrypoint.sh:/ci-entrypoint.sh" \
            -- /ci-entrypoint.sh ./ci/rapids/rapids-entrypoint.sh /ci.sh