tfhe-rs/.github/workflows/gpu_full_multi_gpu_tests.yml

# Compile and test tfhe-cuda-backend on an AWS instance
name: TFHE Cuda Backend - Full tests multi-GPU

env:
  CARGO_TERM_COLOR: always
  ACTION_RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
  RUSTFLAGS: "-C target-cpu=native"
  RUST_BACKTRACE: "full"
  RUST_MIN_STACK: "8388608"
  SLACK_CHANNEL: ${{ secrets.SLACK_CHANNEL }}
  SLACK_ICON: https://pbs.twimg.com/profile_images/1274014582265298945/OjBKP9kn_400x400.png
  SLACK_USERNAME: ${{ secrets.BOT_USERNAME }}
  SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
  MSG_MINIMAL: event,action url,commit
  BRANCH: ${{ github.head_ref || github.ref }}
  IS_PULL_REQUEST: ${{ github.event_name == 'pull_request' || github.event_name == 'pull_request_target' }}
  REF: ${{ github.event.pull_request.head.sha || github.sha }}

on:
  # Allows you to run this workflow manually from the Actions tab as an alternative.
  workflow_dispatch:
  # Trigger pull_request event on CI files to be able to test changes before merging to main branch.
  # Workflow would fail if changes come from a forked repository since secrets are not available with this event.
  pull_request:
    types: [ labeled ]
    paths:
      - '.github/**'
      - 'ci/**'
  # General entry point for Zama's pull request as well as contribution from forks.
  pull_request_target:
    types: [ labeled ]
    paths:
      - '**'
      - '!.github/**'
      - '!ci/**'

jobs:
  should-run:
    runs-on: ubuntu-latest
    permissions:
      pull-requests: read
    outputs:
      gpu_test: ${{ env.IS_PULL_REQUEST == 'false' || steps.changed-files.outputs.gpu_any_changed }}
    steps:
      - name: Checkout tfhe-rs
        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
        with:
          fetch-depth: 0
          persist-credentials: 'false'
          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
          ref: ${{ env.REF }}

      - name: Check for file changes
        id: changed-files
        uses: tj-actions/changed-files@d6e91a2266cdb9d62096cebf1e8546899c6aa18f
        with:
          since_last_remote_commit: true
          files_yaml: |
            gpu:
              - tfhe/Cargo.toml
              - tfhe/build.rs
              - backends/tfhe-cuda-backend/**
              - tfhe/src/core_crypto/gpu/**
              - tfhe/src/integer/server_key/radix_parallel/tests_unsigned/**
              - tfhe/src/integer/server_key/radix_parallel/tests_signed/**
              - tfhe/src/integer/server_key/radix_parallel/tests_cases_unsigned.rs
              - tfhe/src/integer/gpu/**
              - tfhe/src/shortint/parameters/**
              - tfhe/src/high_level_api/**
              - tfhe/src/c_api/**
              - 'tfhe/docs/**/**.md'
              - '.github/workflows/**_multi_gpu_tests.yml'
              - scripts/integer-tests.sh
              - ci/slab.toml

  check-ci-files:
    uses: ./.github/workflows/check_ci_files_change.yml
    with:
      checkout_ref: ${{ github.event.pull_request.head.sha || github.sha }}
    secrets:
      REPO_CHECKOUT_TOKEN: ${{ secrets.REPO_CHECKOUT_TOKEN }}

  # Fail if the triggering actor is not part of Zama organization.
  # If pull_request_target is emitted and CI files have changed, skip this job. This would skip following jobs.
  check-user-permission:
    needs: check-ci-files
    if: github.event_name != 'pull_request_target' ||
      (github.event_name == 'pull_request_target' && needs.check-ci-files.outputs.ci_file_changed == 'false')
    uses: ./.github/workflows/check_actor_permissions.yml
    secrets:
      TOKEN: ${{ secrets.GITHUB_TOKEN }}

  setup-instance:
    name: Setup instance (cuda-tests-multi-gpu)
    needs: [ should-run, check-user-permission ]
    if: github.event_name != 'pull_request_target' ||
      (github.event.action != 'labeled' && needs.should-run.outputs.gpu_test == 'true') ||
      (github.event.action == 'labeled' && github.event.label.name == 'approved' && needs.should-run.outputs.gpu_test == 'true')
    runs-on: ubuntu-latest
    outputs:
      runner-name: ${{ steps.start-instance.outputs.label }}
    steps:
      - name: Start instance
        id: start-instance
        uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
        with:
          mode: start
          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
          slab-url: ${{ secrets.SLAB_BASE_URL }}
          job-secret: ${{ secrets.JOB_SECRET }}
          backend: hyperstack
          profile: multi-gpu-test

  cuda-tests-linux:
    name: CUDA multi-GPU tests
    needs: [ should-run, setup-instance ]
    if: github.event_name != 'pull_request_target' ||
      (github.event_name == 'pull_request_target' && needs.setup-instance.result != 'skipped')
    concurrency:
      group: ${{ github.workflow }}_${{ github.head_ref || github.ref }}
      cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
    runs-on: ${{ needs.setup-instance.outputs.runner-name }}
    strategy:
      fail-fast: false
      # explicit include-based build matrix, of known valid options
      matrix:
        include:
          - os: ubuntu-22.04
            cuda: "12.2"
            gcc: 11 
    steps:
      - name: Checkout tfhe-rs
        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
        with:
          persist-credentials: 'false'
          token: ${{ secrets.REPO_CHECKOUT_TOKEN }}
          ref: ${{ env.REF }}

      - name: Setup Hyperstack dependencies
        uses: ./.github/actions/hyperstack_setup
        with:
          cuda-version: ${{ matrix.cuda }}
          gcc-version: ${{ matrix.gcc }}

      - name: Set up home
        run: |
          echo "HOME=/home/ubuntu" >> "${GITHUB_ENV}"

      - name: Install latest stable
        uses: dtolnay/rust-toolchain@a54c7afa936fefeb4456b2dd8068152669aa8203
        with:
          toolchain: stable

      - name: Run multi-bit CUDA integer compression tests
        run: |
          BIG_TESTS_INSTANCE=TRUE make test_integer_compression_gpu

      # No need to test core_crypto and classic PBS in integer since it's already tested on single GPU.
      - name: Run multi-bit CUDA integer tests
        run: |
          BIG_TESTS_INSTANCE=TRUE make test_integer_multi_bit_gpu_ci

      - name: Run user docs tests
        run: |
          BIG_TESTS_INSTANCE=TRUE make test_user_doc_gpu

      - name: Test C API
        run: |
          BIG_TESTS_INSTANCE=TRUE make test_c_api_gpu

      - name: Run High Level API Tests
        run: |
          BIG_TESTS_INSTANCE=TRUE make test_high_level_api_gpu

  slack-notify:
    name: Slack Notification
    needs: [ setup-instance, cuda-tests-linux ]
    runs-on: ubuntu-latest
    if: ${{ always() && needs.cuda-tests-linux.result != 'skipped' && failure() }}
    continue-on-error: true
    steps:
      - name: Send message
        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
        env:
          SLACK_COLOR: ${{ needs.cuda-tests-linux.result }}
          SLACK_MESSAGE: "Multi-GPU tests finished with status: ${{ needs.cuda-tests-linux.result }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"

  teardown-instance:
    name: Teardown instance (cuda-tests-multi-gpu)
    if: ${{ always() && needs.setup-instance.result == 'success' }}
    needs: [ setup-instance, cuda-tests-linux ]
    runs-on: ubuntu-latest
    steps:
      - name: Stop instance
        id: stop-instance
        uses: zama-ai/slab-github-runner@79939325c3c429837c10d6041e4fd8589d328bac
        with:
          mode: stop
          github-token: ${{ secrets.SLAB_ACTION_TOKEN }}
          slab-url: ${{ secrets.SLAB_BASE_URL }}
          job-secret: ${{ secrets.JOB_SECRET }}
          label: ${{ needs.setup-instance.outputs.runner-name }}

      - name: Slack Notification
        if: ${{ failure() }}
        continue-on-error: true
        uses: rtCamp/action-slack-notify@c33737706dea87cd7784c687dadc9adf1be59990
        env:
          SLACK_COLOR: ${{ job.status }}
          SLACK_MESSAGE: "Instance teardown (cuda-tests-multi-gpu) finished with status: ${{ job.status }} on '${{ env.BRANCH }}'. (${{ env.ACTION_RUN_URL }})"