open-standards/.github/workflows/wai-quantum-metal.yml

name: wai-quantum Metal member

# The fabric's Metal member: the gate kernels in the Metal shading language,
# compiled at run time by the operating system's own compiler for the device,
# and certified bit-exact against the CPU reference's pinned corpus digests.
#
# - metal-hw (the macOS runner's GPU): the device tests must find exactly the
#   declared device, agree with the CPU on the arithmetic probe and on random
#   states (out-of-range runs included), reproduce all four pinned certificates
#   (two gatesets, random-v1 and fabric-v1), and catch every kernel mutant; and
#   the matrix kernel, every product formed by the GPU's SIMD-group matrix
#   multiply from 8-bit limbs, must do all of the same under its own
#   implementation id, with its own mutants caught; and so must the
#   tensor-operation kernel, every product formed by the shading language's
#   tensor operation from offset-binary 8-bit limbs.
# - metal-absent (a container with no Metal): the same build finds no member
#   and says why, rather than failing; the device tests run over no member with
#   the declaration `none`.

concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

on:
  pull_request:
    paths:
      - 'wai/wai-quantum/**'
      - 'rust-toolchain.toml'
      - '.github/workflows/wai-quantum-metal.yml'
  schedule:
    - cron: '56 7 * * *'

jobs:
  relevant:
    name: does this change touch it
    runs-on: linux-arm64
    outputs:
      run: ${{ steps.gate.outputs.run }}
    steps:
      - uses: actions/checkout@v5
        with:
          fetch-depth: 0
      - id: gate
        run: |
          set -euo pipefail
          r=$(python3 scripts/pr-touches-paths.py .github/workflows/wai-quantum-metal.yml \
                "${{ github.event.pull_request.base.sha }}" \
                "${{ github.event.pull_request.head.sha }}")
          echo "this change touches wai-quantum-metal: $r"
          echo "run=$r" >> "$GITHUB_OUTPUT"

  metal-hw:
    name: member · Metal (macos)
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    # The pins are the Mac Studio's GPU (gpu-msl-1009). The fleet's other macOS runners
    # (an M4 Max and an M5 Max) have other GPUs, so this member runs on the Studio by its
    # own label; a member for theirs is declared from a run on them.
    runs-on: macos-m3-ultra
    timeout-minutes: 90
    env:
      WAI_QUANTUM_METAL_EXPECT: gpu-msl-1009
    steps:
      - uses: actions/checkout@v5
      # launchd's PATH omits cargo on the macOS host runner.
      - name: Put cargo on PATH
        shell: bash
        run: echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
      - name: The member's unit tests
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          nice -n 10 cargo test --locked --features quantum_fabric_metal --lib -- quantum_fabric_metal:: quantum_fabric::metal:: 2>&1 | tee "$RUNNER_TEMP/unit.log"
          grep -qE '^test result: ok\. [1-9][0-9]* passed; 0 failed' "$RUNNER_TEMP/unit.log" || { echo "::error::no unit test ran"; exit 1; }
      - name: The member's device tests
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          report="$RUNNER_TEMP/metal-report.txt"; : > "$report"
          WAI_QUANTUM_METAL_REPORT="$report" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_metal --test metal_member -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/device.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/device.log" || { echo "::error::not every device test ran and passed"; exit 1; }
          cat "$report"
          key="$WAI_QUANTUM_METAL_EXPECT"
          grep -qx "metal devices: as declared ($key)" "$report" || { echo "::error::the devices found are not the declared ones"; exit 1; }
          n="$(grep -c "^metal certified: key=$key .* implementation=metal-lanes64/[0-9a-f]\{16\} parity=bit-exact " "$report")"
          [ "$n" = 4 ] || { echo "::error::$n of 4 certificates were earned"; exit 1; }
          grep -qx "metal mutants: key=$key killed 6 of 6" "$report" || { echo "::error::a kernel mutant survived"; exit 1; }
      - name: The matrix kernel, every product by the SIMD-group matrix multiply
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          report="$RUNNER_TEMP/metal-matrix-report.txt"; : > "$report"
          WAI_QUANTUM_METAL_REPORT="$report" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_metal --test metal_matrix -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/matrix.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/matrix.log" || { echo "::error::not every matrix test ran and passed"; exit 1; }
          cat "$report"
          key="$WAI_QUANTUM_METAL_EXPECT"
          grep -qx "metal matrix devices: as declared ($key)" "$report" || { echo "::error::the devices found are not the declared ones"; exit 1; }
          grep -q "^metal matrix member: key=$key .* implementation=metal-matrix-limbs8/[0-9a-f]\{16\} " "$report" || { echo "::error::the device ran no matrix member"; exit 1; }
          n="$(grep -c "^metal matrix certified: key=$key .* implementation=metal-matrix-limbs8/[0-9a-f]\{16\} parity=bit-exact " "$report")"
          [ "$n" = 4 ] || { echo "::error::$n of 4 matrix certificates were earned"; exit 1; }
          grep -qx "metal matrix mutants: key=$key killed 7 of 7" "$report" || { echo "::error::a matrix mutant survived"; exit 1; }
      - name: The tensor-operation kernel, every product by the tensor operation
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          report="$RUNNER_TEMP/metal-tensor-ops-report.txt"; : > "$report"
          WAI_QUANTUM_METAL_REPORT="$report" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_metal --test metal_tensor_ops -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/tensor-ops.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/tensor-ops.log" || { echo "::error::not every tensor-operation test ran and passed"; exit 1; }
          cat "$report"
          key="$WAI_QUANTUM_METAL_EXPECT"
          grep -qx "metal tensor-ops devices: as declared ($key)" "$report" || { echo "::error::the devices found are not the declared ones"; exit 1; }
          grep -q "^metal tensor-ops member: key=$key .* implementation=metal-tensor-ops-limbs8/[0-9a-f]\{16\} " "$report" || { echo "::error::the device ran no tensor-operation member"; exit 1; }
          n="$(grep -c "^metal tensor-ops certified: key=$key .* implementation=metal-tensor-ops-limbs8/[0-9a-f]\{16\} parity=bit-exact " "$report")"
          [ "$n" = 4 ] || { echo "::error::$n of 4 tensor-operation certificates were earned"; exit 1; }
          grep -qx "metal tensor-ops mutants: key=$key killed 8 of 8" "$report" || { echo "::error::a tensor-operation mutant survived"; exit 1; }

  metal-absent:
    name: member · Metal absent (linux)
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    runs-on: linux
    timeout-minutes: 60
    env:
      WAI_QUANTUM_METAL_EXPECT: none
    steps:
      - uses: actions/checkout@v5
      - name: Install Rust 1.98.0
        shell: bash
        run: |
          export PATH="$HOME/.cargo/bin:$PATH"
          command -v rustup >/dev/null 2>&1 || \
            curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal --default-toolchain 1.98.0
          rustup toolchain install 1.98.0 --profile minimal
          rustup default 1.98.0
          echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
      - name: No Metal here, and the member says so
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          cargo test --locked --features quantum_fabric_metal --lib -- quantum_fabric_metal:: quantum_fabric::metal:: 2>&1 | tee "$RUNNER_TEMP/unit.log"
          grep -qE '^test quantum_fabric_metal::tests::off_macos_nothing_is_found_and_discovery_says_why \.\.\. ok$' "$RUNNER_TEMP/unit.log" || { echo "::error::the off-platform discovery test did not run"; exit 1; }
          report="$RUNNER_TEMP/metal-report.txt"; : > "$report"
          for t in metal_member metal_matrix metal_tensor_ops; do
            WAI_QUANTUM_METAL_REPORT="$report" cargo test --locked --features quantum_fabric_metal --test "$t" -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/$t.log"
            grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/$t.log" || { echo "::error::$t did not run over no device"; exit 1; }
          done
          grep -qx 'metal devices: as declared (none)' "$report" || { echo "::error::the absent case was not established"; exit 1; }
          grep -qx 'metal matrix devices: as declared (none)' "$report" || { echo "::error::the matrix absent case was not established"; exit 1; }
          grep -qx 'metal tensor-ops devices: as declared (none)' "$report" || { echo "::error::the tensor-operation absent case was not established"; exit 1; }