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

name: wai-quantum WebGPU member

# The fabric's WebGPU member: one WGSL gate kernel, compiled for every adapter a
# runner has, certified against the CPU reference's pinned corpus digests. A
# second implementation, tile runs (the same kernel followed by apply_tile, which
# applies a run of gates tile by tile in one dispatch), is certified on its own
# against the same digests, on every adapter and in the browser.
#
# Each member job declares the adapters its runner must have in
# WAI_QUANTUM_WEBGPU_EXPECT. The device test fails if the adapters found differ,
# and scripts/wai-quantum-webgpu-member.sh fails unless all tests ran, every
# declared adapter earned one bit-exact certificate per pinned digest, and every
# declared adapter killed every shader mutant.
#
# The GPU jobs then run the quantum conformance corpus through each member
# (`wai_quantum_vectors verify --webgpu`). wai-rs is built there with
# --no-default-features: its default feature, `codecs`, links system codec
# libraries that no GPU host has, and the corpus needs none of them. The GPU
# hosts: jetson-hub (a discrete and an integrated GPU) and framework-128gb (an
# integrated GPU).
#
# The browser job runs the same kernel through a browser's WebGPU, compiled by the
# browser's own WGSL compiler: wai-web's `quantum_webgpu` bundle in a headless page
# (wai/quantum-conformance/browser_webgpu.mjs), which must certify a GPU member with
# the four pinned digests, reproduce every vector and refuse every reject file with
# its class. It is not a required status until it has been green three runs in a row.
#
# The meter (wai/tools/quantum-meter) is wai-quantum's RunMeter over a process's own
# CPU and GPU energy counters. On the Metal host, where those counters exist, it meters
# a member's runs and the CPU reference's over windows they resolve, and its test must
# print what it read; on the software Vulkan host, where they do not, every window must
# come out unmetered.
#
# There is no windows job while the windows runner is offline: a job queued on an
# offline runner never settles. Add it back from the comment at the end when the
# runner has survived a reboot.

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

on:
  pull_request:
    paths:
      - 'wai/wai-quantum/**'
      - 'wai/quantum-conformance/**'
      - 'wai/tools/quantum-wgsl-check/**'
      # The meter, and the counters it reads.
      - 'wai/tools/quantum-meter/**'
      - 'jouleclaw/jouleclaw-rs/Cargo.toml'
      - 'jouleclaw/jouleclaw-rs/crates/jouleclaw-core/**'
      - 'jouleclaw/jouleclaw-rs/crates/jouleclaw-energy/**'
      - 'wai/wai-rs/src/bin/wai_quantum_vectors.rs'
      # The GPU jobs build wai-rs with the forwarded feature, --locked.
      - 'wai/wai-rs/Cargo.lock'
      - 'rust-toolchain.toml'
      # The checks and browser jobs build wai-web with its feature, --locked.
      - 'wai/wai-web/Cargo.toml'
      - 'wai/wai-web/Cargo.lock'
      - 'wai/wai-web/src/quantum_webgpu.rs'
      - 'wai/wai-web/src/lib.rs'
      - 'wai/wai-web/demo/quantum_webgpu*'
      - 'scripts/wai-quantum-webgpu-member.sh'
      - '.github/workflows/wai-quantum-webgpu.yml'
  schedule:
    - cron: '6 7 * * *'

jobs:
  # Does this pull request's own diff touch the paths below? This forge matches a
  # workflow's `paths:` against the push, so a merge of main into a branch fires the
  # workflow whatever the pull request changes; every job here waits on this answer.
  # A push to main, a schedule, or anything the script cannot determine answers
  # `true` (scripts/pr-touches-paths.py).
  relevant:
    name: does this change touch it
    runs-on: gate
    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-webgpu.yml \
                "${{ github.event.pull_request.base.sha }}" \
                "${{ github.event.pull_request.head.sha }}")
          echo "this change touches wai-quantum-webgpu: $r"
          echo "run=$r" >> "$GITHUB_OUTPUT"

  checks:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: shader checks · browser build · wasip2 inertness
    runs-on: linux
    timeout-minutes: 60
    steps:
      - uses: actions/checkout@v5
      - name: Install Rust 1.99.1 (wasm32 targets)
        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 1.99.1
          rustup toolchain install 1.99.1 --profile minimal
          rustup default 1.99.1
          rustup target add --toolchain 1.99.1 wasm32-unknown-unknown wasm32-wasip2
          echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
      - name: SPIR-V validator
        shell: bash
        run: |
          set -euo pipefail
          SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo"
          $SUDO apt-get update -qq
          $SUDO apt-get install -y -qq --no-install-recommends spirv-tools
      - name: The shaders under naga 30.0.1
        shell: bash
        working-directory: wai/tools/quantum-wgsl-check
        run: |
          set -euo pipefail
          cargo run --locked --release -- "$RUNNER_TEMP" 2>&1 | tee "$RUNNER_TEMP/wgsl-check.log"
          grep -qx "quantum-wgsl-check: ok" "$RUNNER_TEMP/wgsl-check.log"
          spirv-val --target-env vulkan1.1 "$RUNNER_TEMP/lanes32.spv"
          spirv-val --target-env vulkan1.1 "$RUNNER_TEMP/lanes32_tile.spv"
      - name: The member builds for a browser
        working-directory: wai/wai-quantum
        run: cargo build --locked --lib --target wasm32-unknown-unknown --no-default-features --features quantum_fabric_webgpu
      - name: The browser bundle builds with the member
        working-directory: wai/wai-web
        run: cargo build --locked --release --target wasm32-unknown-unknown --features quantum_webgpu
      - name: On wasm32-wasip2 the feature is inert
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          cargo check --locked --lib --target wasm32-wasip2 --features full,quantum_fabric_webgpu
          w="$RUNNER_TEMP/tree-wasip2.txt"; n="$RUNNER_TEMP/tree-native.txt"
          cargo tree --locked --target wasm32-wasip2 --features full,quantum_fabric_webgpu -e normal --prefix none > "$w"
          cargo tree --locked --target x86_64-unknown-linux-gnu --features quantum_fabric_webgpu -e normal --prefix none > "$n"
          grep -q '^wai-quantum ' "$w" || { echo "::error::cargo tree printed no wasip2 tree"; exit 1; }
          grep -q '^wgpu ' "$n" || { echo "::error::the native tree has no wgpu, so this check cannot see it"; exit 1; }
          if grep -q '^wgpu' "$w"; then echo "::error::wgpu is in the wasm32-wasip2 tree"; exit 1; fi
      - name: The package carries the shader
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          cargo package --locked --list --allow-dirty > "$RUNNER_TEMP/package.txt"
          grep -qx 'src/quantum_fabric/lanes32.wgsl' "$RUNNER_TEMP/package.txt"
          grep -qx 'src/quantum_fabric/lanes32_tile.wgsl' "$RUNNER_TEMP/package.txt"
      # The member's unit tests need no GPU (a failed native wait is fed to the
      # guard as a panicking closure), and only the feature build compiles them.
      - name: The member's unit tests, without a device
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          cargo test --locked --lib --features quantum_fabric_webgpu -- quantum_fabric_webgpu:: 2>&1 \
            | tee "$RUNNER_TEMP/member-unit.log"
          grep -q '^test quantum_fabric_webgpu::tests::a_failed_native_wait_is_a_typed_loss \.\.\. ok$' \
            "$RUNNER_TEMP/member-unit.log" \
            || { echo "::error::the member's unit test did not run"; exit 1; }

  member-software:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: member · software Vulkan (linux)
    runs-on: linux
    timeout-minutes: 120
    env:
      WAI_QUANTUM_WEBGPU_EXPECT: swgpu-vulkan-10005
    steps:
      - uses: actions/checkout@v5
      - name: Install Rust 1.99.1
        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 1.99.1
          rustup toolchain install 1.99.1 --profile minimal
          rustup default 1.99.1
          echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
      - name: The Vulkan loader and a software Vulkan driver
        shell: bash
        run: |
          set -euo pipefail
          SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo"
          $SUDO apt-get update -qq
          $SUDO apt-get install -y -qq --no-install-recommends libvulkan1 mesa-vulkan-drivers
      - name: The member's tests
        shell: bash
        run: scripts/wai-quantum-webgpu-member.sh
      # No per-process energy counter exists here: the meter must find none, and a
      # run of the member through it must be unmetered.
      - name: The meter, where its counters do not exist
        shell: bash
        working-directory: wai/tools/quantum-meter
        run: |
          set -euo pipefail
          cargo test --locked -- --nocapture 2>&1 | tee "$RUNNER_TEMP/meter.log"
          grep -q '^test a_members_runs_are_metered_over_a_window_the_counters_resolve \.\.\. ok$' "$RUNNER_TEMP/meter.log" \
            || { echo "::error::the meter's device test did not run"; exit 1; }
          grep -q '^quantum-meter: the counters are not live here' "$RUNNER_TEMP/meter.log" \
            || { echo "::error::the meter's device test found no adapter, so it checked nothing"; exit 1; }

  member-metal:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: member · Metal (macos)
    runs-on: macos
    timeout-minutes: 90
    env:
      WAI_QUANTUM_WEBGPU_EXPECT: gpu-metal-0
    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 tests
        shell: bash
        run: nice -n 10 scripts/wai-quantum-webgpu-member.sh
      - name: The conformance corpus through the member
        shell: bash
        working-directory: wai/wai-rs
        run: nice -n 10 cargo run --locked --no-default-features --features quantum_fabric_webgpu --bin wai_quantum_vectors -- verify ../quantum-conformance --webgpu
      # The counters exist here. The device test prints a `quantum-meter hardware:` line
      # for each window it read: a figure, or why another process's GPU use left it
      # none. The tool then calibrates both members on one circuit and, where both
      # windows earn a figure, places it.
      - name: The meter on this process's counters
        shell: bash
        working-directory: wai/tools/quantum-meter
        run: |
          set -euo pipefail
          nice -n 10 cargo test --locked --release -- --nocapture 2>&1 | tee "$RUNNER_TEMP/meter.log"
          grep -q '^test a_members_runs_are_metered_over_a_window_the_counters_resolve \.\.\. ok$' "$RUNNER_TEMP/meter.log" \
            || { echo "::error::the meter's device test did not run"; exit 1; }
          grep -q '^quantum-meter hardware: ' "$RUNNER_TEMP/meter.log" \
            || { echo "::error::the meter read no window: its counters are not live on this host"; exit 1; }
          nice -n 10 cargo run --locked --release -- --counter-ppm 50000 2>&1 | tee "$RUNNER_TEMP/meter-tool.log"
          grep -q '^quantum-meter: local/cpu-' "$RUNNER_TEMP/meter-tool.log" \
            || { echo "::error::the tool ran no window on the CPU reference"; exit 1; }

  member-hw:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: member · GPU, Vulkan (${{ matrix.host }})
    runs-on: ${{ matrix.runner }}
    timeout-minutes: 150
    strategy:
      fail-fast: false
      matrix:
        include:
          # Each host's adapters, declared here: its GPUs and the software
          # Vulkan driver. The wide sizes run on the GPU only.
          - host: jetson-hub
            runner: linux-hw
            adapters: gpu-vulkan-10de,gpu-vulkan-8086,swgpu-vulkan-10005
          - host: thor
            runner: linux-arm64-hw
            adapters: gpu-vulkan-10de,swgpu-vulkan-10005
    env:
      WAI_QUANTUM_WEBGPU_EXPECT: ${{ matrix.adapters }}
      WAI_QUANTUM_WEBGPU_WIDE: '1'
      CARGO_PROFILE_DEV_DEBUG: '0'
      CARGO_BUILD_JOBS: '8'
    steps:
      - name: Fetch the source
        shell: bash
        run: |
          set -euo pipefail
          want="${{ github.event.pull_request.head.sha || github.sha }}"
          rm -rf src && mkdir src && cd src
          git init -q
          # Fetch the commit itself, not the ref: a later commit on the ref that this
          # workflow's paths do not match would otherwise be fetched instead.
          git fetch -q --depth 1 http://100.64.224.0:3400/Transaction-Science/open-standards.git "$want"
          git checkout -q FETCH_HEAD
          got="$(git rev-parse HEAD)"
          [ "$got" = "$want" ] || { echo "::error::fetched $got, not $want"; exit 1; }
      - name: The member's tests
        shell: bash
        working-directory: src
        run: |
          set -euo pipefail
          echo "adapters declared: $WAI_QUANTUM_WEBGPU_EXPECT"
          CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum" nice -n 10 scripts/wai-quantum-webgpu-member.sh
      - name: The conformance corpus through the member
        shell: bash
        working-directory: src/wai/wai-rs
        run: CARGO_TARGET_DIR="$HOME/hw-target/wai-rs" nice -n 10 cargo run --locked --no-default-features --features quantum_fabric_webgpu --bin wai_quantum_vectors -- verify ../quantum-conformance --webgpu

  member-amd:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: member · integrated GPU, Vulkan (framework-128gb)
    runs-on: linux-amd
    timeout-minutes: 150
    env:
      # The adapters are declared by the host, in its runner's environment
      # (WAI_QUANTUM_AMD_WEBGPU_EXPECT); with no declaration, the integrated GPU
      # and the software Vulkan driver. The wide sizes run on the GPU only.
      WAI_QUANTUM_WEBGPU_WIDE: '1'
      CARGO_PROFILE_DEV_DEBUG: '0'
      CARGO_BUILD_JOBS: '12'
    steps:
      - name: Fetch the source
        shell: bash
        run: |
          set -euo pipefail
          want="${{ github.event.pull_request.head.sha || github.sha }}"
          rm -rf src && mkdir src && cd src
          git init -q
          # Fetch the commit itself, not the ref: a later commit on the ref that this
          # workflow's paths do not match would otherwise be fetched instead. The
          # host names its own route to the forge (WAI_FORGE_URL).
          git fetch -q --depth 1 "${WAI_FORGE_URL:-http://100.64.224.0:3400}/Transaction-Science/open-standards.git" "$want"
          git checkout -q FETCH_HEAD
          got="$(git rev-parse HEAD)"
          [ "$got" = "$want" ] || { echo "::error::fetched $got, not $want"; exit 1; }
      - name: The member's tests
        shell: bash
        working-directory: src
        run: |
          set -euo pipefail
          export WAI_QUANTUM_WEBGPU_EXPECT="${WAI_QUANTUM_AMD_WEBGPU_EXPECT:-gpu-vulkan-1002,swgpu-vulkan-10005}"
          echo "adapters declared: $WAI_QUANTUM_WEBGPU_EXPECT"
          CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum" nice -n 10 scripts/wai-quantum-webgpu-member.sh
      - name: The conformance corpus through the member
        shell: bash
        working-directory: src/wai/wai-rs
        run: CARGO_TARGET_DIR="$HOME/hw-target/wai-rs" nice -n 10 cargo run --locked --no-default-features --features quantum_fabric_webgpu --bin wai_quantum_vectors -- verify ../quantum-conformance --webgpu

  browser:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: member · browser WebGPU (macos)
    runs-on: macos
    timeout-minutes: 60
    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"
      # The page's file is held to the crate by wai-quantum's tests/fabric_expected.rs:
      # exactly the four certificates of the pinned corpora (gateset, corpus, seed,
      # cases, wide circuits and the digest the CPU computes) and both implementation
      # ids. Editing the file alone, say giving fabric-v1 random-v1's digests so that
      # no circuit wider than one tile runs, fails here.
      - name: The page's pins are the crate's
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          nice -n 10 cargo test --locked --features quantum_fabric --test fabric_expected 2>&1 | tee "$RUNNER_TEMP/fabric-expected.log"
          grep -q '^test the_browser_legs_pins_are_the_crates \.\.\. ok$' "$RUNNER_TEMP/fabric-expected.log" \
            || { echo "::error::the pins test did not run"; exit 1; }
      # Pinned to the wasm-bindgen version in wai-web/Cargo.lock: the CLI and the crate
      # must match exactly.
      - name: wasm-bindgen CLI 0.2.127
        shell: bash
        run: |
          set -euo pipefail
          rustup target add wasm32-unknown-unknown
          cargo install --locked wasm-bindgen-cli --version 0.2.127
      - name: The member's bundle
        shell: bash
        working-directory: wai/wai-web
        run: |
          set -euo pipefail
          nice -n 10 cargo build --locked --release --target wasm32-unknown-unknown --features quantum_webgpu
          wasm-bindgen --target web --out-dir demo/pkg-webgpu --out-name wai_quantum_webgpu \
            target/wasm32-unknown-unknown/release/wai_web.wasm
      # Playwright and its headless browser go into the job's temporary directory, not
      # the host's caches. `chromium` is Playwright's name for its engine.
      - name: Playwright 1.60.0 and its headless browser
        shell: bash
        run: |
          set -euo pipefail
          node --version
          pw="$RUNNER_TEMP/playwright"
          mkdir -p "$pw"
          npm install --prefix "$pw" --no-save --no-audit --no-fund [email protected]
          PLAYWRIGHT_BROWSERS_PATH="$pw/browsers" "$pw/node_modules/.bin/playwright" install --only-shell chromium
          echo "PLAYWRIGHT_HOST=$pw/" >> "$GITHUB_ENV"
          echo "PLAYWRIGHT_BROWSERS_PATH=$pw/browsers" >> "$GITHUB_ENV"
      - name: The member in a browser
        shell: bash
        run: |
          set -euo pipefail
          WAI_QUANTUM_WEBGPU_REQUIRE=1 nice -n 10 node wai/quantum-conformance/browser_webgpu.mjs 2>&1 \
            | tee "$RUNNER_TEMP/browser-webgpu.log"
          grep -qE '^browser webgpu: member=local/gpu-webgpu-[0-9a-f]{12} class=gpu certified bit-exact 4 of 4; tiles certified bit-exact 4 of 4; ' \
            "$RUNNER_TEMP/browser-webgpu.log" \
            || { echo "::error::no GPU member certified bit-exact 4 of 4, per-gate and in tile runs, in the browser"; exit 1; }

  # Windows reaches both of this host's GPUs through both backends, so one job
  # certifies five adapters rather than one per backend: the member test
  # enumerates every adapter in the one process, and the DX12 keys exercise the
  # WGSL -> HLSL path (naga) that no other member covers. Not a required status.
  member-windows:
    name: member · DX12 and Vulkan (cbio-windows)
    runs-on: windows
    timeout-minutes: 150
    env:
      # The key list this host's first run printed:
      #   gpu-dx12-10de    discrete NVIDIA, DX12
      #   gpu-dx12-8086    integrated Intel, DX12
      #   gpu-vulkan-10de  discrete NVIDIA, Vulkan
      #   gpu-vulkan-8086  integrated Intel, Vulkan
      #   swgpu-dx12-1414  Microsoft's software adapter (WARP), class Cpu
      # Adding or removing a driver changes this set, and the member test fails
      # until this line matches it again.
      WAI_QUANTUM_WEBGPU_EXPECT: gpu-dx12-10de,gpu-dx12-8086,gpu-vulkan-10de,gpu-vulkan-8086,swgpu-dx12-1414
    steps:
      - uses: actions/checkout@v5
      # The runner writes an unsigned .ps1 per step, which the default policy
      # refuses. pwsh, not Windows PowerShell: the 5.1 parser rejects the PS7
      # syntax this repo's scripts use.
      - name: Allow the runner's generated scripts to run
        shell: pwsh
        run: Set-ExecutionPolicy -Scope Process -ExecutionPolicy Bypass -Force
      # `bash` on this host resolves to the WindowsApps WSL stub, and the machine
      # PATH carries Git\cmd (git.exe) but not Git\bin (bash.exe). Without this
      # every `shell: bash` step below would run under WSL, which reaches none of
      # the Windows GPU drivers.
      - name: Put Git Bash on PATH
        shell: pwsh
        run: |
          $gitBash = 'C:\Program Files\Git\bin'
          if (-not (Test-Path "$gitBash\bash.exe")) { throw "Git Bash is missing at $gitBash" }
          $gitBash | Out-File -FilePath $env:GITHUB_PATH -Encoding utf8 -Append
      - name: The shell is Git Bash, not WSL
        shell: bash
        run: |
          set -euo pipefail
          command -v bash
          # A WSL bash reports Linux; Git Bash reports MINGW or MSYS.
          case "$(uname -s)" in
            MINGW*|MSYS*) ;;
            *) echo "::error::bash is $(uname -s), not Git Bash"; exit 1 ;;
          esac
      - name: The member's tests
        shell: bash
        run: scripts/wai-quantum-webgpu-member.sh
      # wai-rs is built with --no-default-features here for the same reason as the
      # other GPU members: its default `codecs` feature links system codec
      # libraries this host does not have, and the corpus needs none of them.
      - name: The conformance corpus through the member
        shell: bash
        working-directory: wai/wai-rs
        run: cargo run --locked --no-default-features --features quantum_fabric_webgpu --bin wai_quantum_vectors -- verify ../quantum-conformance --webgpu