name: wai-ops-gpu integer operators on GPUs

# wai-ops/1-i32 on GPUs (wai/wai-ops-gpu): the integer operator set's graph operators
# as WGSL kernels through wgpu, exact at acc32 (one 32-bit word per value) and at acc64
# (64- and 128-bit arithmetic built from 32-bit words), and the integer decoders with
# their graphs on the device (wai-rs `ops_gpu`).
#
#   - metal (the `macos` runner, whose host has a GPU): the arithmetic probe on a
#     million cases; every graph vector of wai/ops-conformance that the subset covers,
#     at both widths, against the committed results and the interpreter; the shader
#     mutants, every one of which the corpus must catch; every committed vector and
#     refusal fixture of every capability that runs a wai-ops/1 graph, the jpegai/v1
#     inputs included, against the decode on the CPU; and the corpus again in a
#     headless browser's WebGPU, the kernels compiled by the browser's own WGSL
#     compiler. WAI_OPS_GPU_EXPECT declares the one adapter the host must offer, and
#     WAI_OPS_GPU_REQUIRE makes an absent adapter a failure, never a skip; each step
#     then requires the report lines with their counts, so a filtered or empty run
#     fails too.
#   - checks (`linux`, a container with no GPU): the crate and its tests build, the
#     device tests print SKIPPED and pass, and the same tests under
#     WAI_OPS_GPU_REQUIRE=1 fail: an absent adapter is not a pass. The browser module
#     builds for wasm32-unknown-unknown; the bench tool builds.
#
# The equality on other adapters (a discrete and an integrated GPU on Vulkan, an
# integrated GPU on Vulkan elsewhere, software Vulkan) was run by hand and is recorded in
# wai/extensions/determinism-tiers.md §6; this workflow runs no job on those hosts.

# One run per branch at a time; a push supersedes the run before it.
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

on:
  pull_request:
    paths:
      - 'wai/wai-ops-gpu/**'
      - 'wai/wai-ops/**'
      - 'wai/ops-conformance/**'
      # The decoders whose graphs run on the device, and what they decode.
      - 'wai/wai-rs/Cargo.toml'
      - 'wai/wai-rs/Cargo.lock'
      - 'wai/wai-rs/src/int_*.rs'
      - 'wai/wai-rs/src/int_payload/**'
      - 'wai/wai-rs/src/jpegai_*.rs'
      - 'wai/wai-rs/tests/ops_gpu.rs'
      # The exact-upscale derivations' graph on the device, under the corpus's priors.
      - 'wai/wai-rs/src/exact_upscale.rs'
      - 'wai/wai-rs/src/exact_upscale/**'
      - 'wai/wai-rs/tests/exact_upscale_gpu.rs'
      - 'wai/live-conformance/upscale/priors/**'
      - 'wai/wai-rs/tests/vectors/**'
      - 'wai/int-payload-conformance/**'
      - 'wai/neural-conformance/**'
      - 'wai/tools/ops-gpu-bench/**'
      - 'wai/tools/wai_jpegai_fetch_e2e_inputs.sh'
      - 'wai/tools/jpegai-e2e-v1.sha256'
      - 'rust-toolchain.toml'
      - '.github/workflows/wai-ops-gpu.yml'
  schedule:
    - cron: '17 6 * * *'

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: 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-ops-gpu.yml \
                "${{ github.event.pull_request.base.sha }}" \
                "${{ github.event.pull_request.head.sha }}")
          echo "this change touches wai-ops-gpu: $r"
          echo "run=$r" >> "$GITHUB_OUTPUT"

  checks:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: builds · no adapter is not a pass (linux)
    runs-on: linux
    timeout-minutes: 60
    steps:
      - uses: actions/checkout@v5
      - name: Install Rust 1.98.0 with the wasm32-unknown-unknown target
        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
          rustup target add --toolchain 1.98.0 wasm32-unknown-unknown
          echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
      # This container offers no adapter. The device tests must say so and pass; under
      # WAI_OPS_GPU_REQUIRE=1 the same tests must fail. Were an adapter ever offered
      # here, its results must then be equal instead.
      - name: The crate's tests, and an absent adapter under WAI_OPS_GPU_REQUIRE
        shell: bash
        working-directory: wai/wai-ops-gpu
        run: |
          set -euo pipefail
          log="$RUNNER_TEMP/ops-gpu.log"
          rep="$RUNNER_TEMP/ops-gpu.report"
          : > "$rep"
          WAI_OPS_GPU_REPORT="$rep" cargo test --locked --release -- --nocapture --test-threads=1 2>&1 | tee "$log"
          if grep -q '^ops-gpu corpus: key=' "$rep"; then
            echo "this runner offered an adapter"
            if grep -E '^ops-gpu corpus: key=' "$rep" | grep -vq ' mismatches=0 errors=0 '; then
              echo "::error::an adapter here gave a result that is not the interpreter's"; exit 1
            fi
          else
            grep -q '^ops-gpu corpus: SKIPPED' "$rep" || { echo "::error::the corpus test printed neither a result nor SKIPPED"; exit 1; }
            if WAI_OPS_GPU_REQUIRE=1 cargo test --locked --release --test corpus --test arith --test mutants > "$RUNNER_TEMP/require.log" 2>&1; then
              echo "::error::with no adapter, the device tests passed under WAI_OPS_GPU_REQUIRE=1"; exit 1
            fi
            grep -q 'WAI_OPS_GPU_REQUIRE is set' "$RUNNER_TEMP/require.log" \
              || { echo "::error::the tests failed under WAI_OPS_GPU_REQUIRE=1, but not for the absent adapter"; cat "$RUNNER_TEMP/require.log"; exit 1; }
            echo "no adapter: SKIPPED without WAI_OPS_GPU_REQUIRE, a failure with it"
          fi
      - name: The browser module builds for wasm32-unknown-unknown
        working-directory: wai/wai-ops-gpu/browser
        run: cargo build --locked --release --target wasm32-unknown-unknown
      - name: wai-rs builds with ops_gpu, and its GPU test target
        working-directory: wai/wai-rs
        run: |
          set -euo pipefail
          cargo test --locked --no-default-features --features ops_gpu,video_int,audio_int,splat_int,world_int --test ops_gpu --no-run
          cargo test --locked --no-default-features --features ops_gpu,exact_upscale --test exact_upscale_gpu --no-run
      - name: The bench tool builds
        working-directory: wai/tools/ops-gpu-bench
        run: cargo build --locked --release

  metal:
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    name: Metal GPU and browser WebGPU (macos)
    runs-on: macos
    timeout-minutes: 90
    env:
      WAI_OPS_GPU_EXPECT: gpu-metal-0
      WAI_OPS_GPU_REQUIRE: '1'
    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 probe, the corpus at both widths, and the mutants, on the GPU
        shell: bash
        working-directory: wai/wai-ops-gpu
        run: |
          set -euo pipefail
          log="$RUNNER_TEMP/ops-gpu.log"
          export WAI_OPS_GPU_REPORT="$RUNNER_TEMP/ops-gpu.report"
          : > "$WAI_OPS_GPU_REPORT"
          nice -n 10 cargo test --locked --release -- --nocapture --test-threads=1 2>&1 | tee "$log"
          k=gpu-metal-0
          # Six tests in four binaries: the library's one, arith's two, corpus's two and
          # mutants' one, none filtered, ignored or failed.
          ran=$(awk '/^test result: ok\. [0-9]+ passed; 0 failed; 0 ignored; 0 measured; 0 filtered out/ { n += $4 } END { print n + 0 }' "$log")
          [ "$ran" = 6 ] || { echo "::error::$ran tests ran and passed, not 6"; exit 1; }
          ! grep -q '^test result: FAILED' "$log" || { echo "::error::a test failed"; exit 1; }
          grep -qxF "ops-gpu adapters: as declared ($k)" "$WAI_OPS_GPU_REPORT" || { echo "::error::the adapters found are not $k"; exit 1; }
          grep -qE "^ops-gpu arith: key=$k .* cases=[0-9]+ words=[0-9]+ equal$" "$WAI_OPS_GPU_REPORT" || { echo "::error::no probe result for $k"; exit 1; }
          grep -qE "^ops-gpu corpus: key=$k .* acc32 vectors=[1-9][0-9]* decodes=[1-9][0-9]*; acc64 vectors=[1-9][0-9]* decodes=[1-9][0-9]*; .* mismatches=0 errors=0 " "$WAI_OPS_GPU_REPORT" \
            || { echo "::error::no equal corpus run for $k"; exit 1; }
          grep -qxF "ops-gpu mutants: key=$k killed 18 of 18" "$WAI_OPS_GPU_REPORT" || { echo "::error::a mutant survived on $k, or the mutant test did not run"; exit 1; }
      - name: The jpegai/v1 inputs
        shell: bash
        run: bash wai/tools/wai_jpegai_fetch_e2e_inputs.sh "$RUNNER_TEMP/jpegai"
      - name: Every capability that runs a wai-ops/1 graph, with its graphs on the GPU
        shell: bash
        working-directory: wai/wai-rs
        run: |
          set -euo pipefail
          log="$RUNNER_TEMP/ops-gpu-rs.log"
          rep="$RUNNER_TEMP/ops-gpu-rs.report"
          : > "$rep"
          J="$RUNNER_TEMP/jpegai"
          WAI_OPS_GPU_REPORT="$rep" WAI_JPEGAI_CODESTREAM="$J/test256.bin" WAI_JPEGAI_WEIGHTS_DIR="$J" WAI_JPEGAI_NORM="$J/norm.json" WAI_REQUIRE_SOTA_VECTORS=1 \
            nice -n 10 cargo test --locked --release --no-default-features --features ops_gpu,video_int,audio_int,splat_int,world_int \
            --test ops_gpu -- --nocapture 2>&1 | tee "$log"
          grep -q '^test result: ok\. 1 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out' "$log" || { echo "::error::the capability test did not run and pass"; exit 1; }
          for cap in wai.neural.int_hyper wai.video.int_hyper wai.audio.int_codec wai.splat.int_codec wai.neural.int_synth \
                     wai.neural.int_mlicpp wai.world.model wai.image.jpegai; do
            grep -qE "^ops-gpu capability: key=gpu-metal-0 .* cap=$cap cases=[1-9][0-9]* .* differ=0 errors=0$" "$rep" \
              || { echo "::error::$cap: no equal run on the GPU"; exit 1; }
          done
      # The exact-upscale derivations (extensions/exact-upscale.md §3.4): under every prior of the
      # corpus, sr2 and sr4 give the same bytes with their graph on the device as on the CPU,
      # every graph run on the device and compared with the interpreter.
      - name: The exact-upscale derivations with their graph on the GPU
        shell: bash
        working-directory: wai/wai-rs
        run: |
          set -euo pipefail
          log="$RUNNER_TEMP/exact-upscale-gpu.log"
          rep="$RUNNER_TEMP/exact-upscale-gpu.report"
          : > "$rep"
          WAI_OPS_GPU_REPORT="$rep" nice -n 10 cargo test --locked --release --no-default-features --features ops_gpu,exact_upscale \
            --test exact_upscale_gpu -- --nocapture 2>&1 | tee "$log"
          grep -q '^test result: ok\. 1 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out' "$log" || { echo "::error::the test did not run and pass"; exit 1; }
          grep -qE "^exact-upscale gpu: key=gpu-metal-0 .* cases=[1-9][0-9]* .* cpu=0 .* differ=0 errors=0 equal$" "$rep" \
            || { echo "::error::no equal run on the GPU"; exit 1; }
      - name: wasm-bindgen CLI 0.2.127, and the wasm32-unknown-unknown target
        shell: bash
        run: |
          set -euo pipefail
          rustup target add wasm32-unknown-unknown
          cargo install --locked wasm-bindgen-cli --version 0.2.127
      # 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
          pw="$RUNNER_TEMP/playwright"
          mkdir -p "$pw"
          npm install --prefix "$pw" --no-save --no-audit --no-fund playwright@1.60.0
          PLAYWRIGHT_BROWSERS_PATH="$pw/browsers" "$pw/node_modules/.bin/playwright" install --only-shell chromium
          echo "PLAYWRIGHT_HOST=$pw/" >> "$GITHUB_ENV"
          echo "PLAYWRIGHT_BROWSERS_PATH=$pw/browsers" >> "$GITHUB_ENV"
      - name: The corpus in a browser's WebGPU
        shell: bash
        working-directory: wai/wai-ops-gpu/browser
        run: |
          set -euo pipefail
          nice -n 10 cargo build --locked --release --target wasm32-unknown-unknown
          t="${CARGO_TARGET_DIR:-target}"
          wasm-bindgen --target web --out-dir pkg --out-name wai_ops_gpu_browser "$t/wasm32-unknown-unknown/release/wai_ops_gpu_browser.wasm"
          log="$RUNNER_TEMP/browser.log"
          nice -n 10 node run.mjs 2>&1 | tee "$log"
          grep -qE '^browser webgpu: key=gpu-webgpu-[0-9a-f]+ .* acc32 vectors=[1-9][0-9]* decodes=[1-9][0-9]*; acc64 vectors=[1-9][0-9]* decodes=[1-9][0-9]*; .* mismatches=0 errors=0$' "$log" \
            || { echo "::error::no equal corpus run on a GPU adapter in the browser"; exit 1; }