open-standards/.github/workflows/wai-quantum-npu-cores.yml

name: wai-quantum npu-cores member

# The fabric's npu-cores member: the gate's fixed-point arithmetic on one
# compute core of a neural processor's tile array, programmed directly. The
# member builds the core's program with the tile array's open toolchain
# (Apache-2.0 with the LLVM exception, pinned below) and its host side with
# the system's C++ compiler against the device runtime, both at run time.
#
# - npu-cores-hw (framework-128gb, its neural processor): 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) on
#   silicon, and catch every kernel mutant, each its own program.
# - npu-cores-absent (a container with no such device): 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-npu-cores.yml'
  schedule:
    - cron: '9 8 * * *'

env:
  # The tile array's toolchain: the compiler and its core back end, the
  # build the compiler's release pins (its utils/peano-requirements.txt).
  TOOLCHAIN_VERSION: 1.4.3
  CORE_COMPILER: llvm-aie==22.0.0.2026090701+3e93bf7b

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

  npu-cores-hw:
    name: member · npu-cores, neural processor (framework-128gb silicon)
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    runs-on: linux-amd
    timeout-minutes: 90
    env:
      CARGO_PROFILE_DEV_DEBUG: '0'
      CARGO_BUILD_JOBS: '12'
    steps:
      - name: Fetch the source
        shell: bash
        run: |
          set -euo pipefail
          want="${{ github.event.pull_request.head.sha || github.sha }}"
          rm -rf src && mkdir src && cd src
          git init -q
          # Fetch the commit itself, not the ref. The host names its own route to
          # the forge (WAI_FORGE_URL).
          git fetch -q --depth 1 "${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 $want"; exit 1; }
      - name: The toolchain (cached)
        shell: bash
        run: |
          set -euo pipefail
          venv="$HOME/aie-$TOOLCHAIN_VERSION"
          if ! "$venv/bin/python" -I -c 'import aie.iron' 2>/dev/null; then
            rm -rf "$venv"
            python3 -m venv "$venv"
            tag="$(python3 -c 'import sys; print(f"cp{sys.version_info.major}{sys.version_info.minor}")')"
            "$venv/bin/pip" install -q "https://github.com/Xilinx/mlir-aie/releases/download/v$TOOLCHAIN_VERSION/mlir_aie-$TOOLCHAIN_VERSION-$tag-$tag-manylinux_2_35_x86_64.whl" # allow-name: the toolchain's release URL
            "$venv/bin/pip" install -q -f https://github.com/Xilinx/llvm-aie/releases/expanded_assets/nightly "$CORE_COMPILER" # allow-name: the core compiler's release index
            "$venv/bin/pip" install -q "numpy>=2.5.2,<3.0" rich ml_dtypes cloudpickle aiofiles
            "$venv/bin/pip" install -q -f https://llvm.github.io/eudsl "eudsl-python-extras==0.1.0.20260801.905+68a0d7a" --config-settings=EUDSL_PYTHON_EXTRAS_HOST_PACKAGE_PREFIX=aie
          fi
          echo "WAI_QUANTUM_NPU_CORES_PYTHON=$venv/bin/python" >> "$GITHUB_ENV"
      - name: The member's unit tests
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-npu-cores" nice -n 10 cargo test --locked --features quantum_fabric_npu_cores --lib -- quantum_fabric_npu_cores:: quantum_fabric::npu_cores:: 2>&1 | tee "$RUNNER_TEMP/unit.log"
          grep -qE '^test result: ok\. [1-9][0-9]* passed; 0 failed' "$RUNNER_TEMP/unit.log" || { echo "::error::no unit test ran"; exit 1; }
      - name: The member's device tests
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          export WAI_QUANTUM_NPU_CORES_CACHE="$HOME/npu-cores-cache"
          # The device this host has, declared here (or by the runner).
          key="${WAI_QUANTUM_AMD_NPU_CORES_EXPECT:-npu-cores-1022-17f0}"
          report="$RUNNER_TEMP/npu-cores-report.txt"; : > "$report"
          WAI_QUANTUM_NPU_CORES_EXPECT="$key" WAI_QUANTUM_NPU_CORES_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-npu-cores" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_npu_cores --test npu_cores_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 "$report"
          grep -qx "npu-cores devices: as declared ($key)" "$report" || { echo "::error::the device found is not the declared one"; exit 1; }
          grep -q "^npu-cores member: key=$key .*; silicon;" "$report" || { echo "::error::the member does not say it ran on silicon"; exit 1; }
          n="$(grep -c "^npu-cores certified: key=$key .* parity=bit-exact " "$report")"
          [ "$n" = 4 ] || { echo "::error::$n of 4 certificates were earned"; exit 1; }
          grep -qx "npu-cores mutants: key=$key killed 3 of 3" "$report" || { echo "::error::a kernel mutant survived"; exit 1; }

  npu-cores-absent:
    name: member · npu-cores absent (linux-arm64)
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    runs-on: linux-arm64
    timeout-minutes: 60
    env:
      WAI_QUANTUM_NPU_CORES_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 neural processor here, and the member says so
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          report="$RUNNER_TEMP/npu-cores-report.txt"; : > "$report"
          cargo test --locked --features quantum_fabric_npu_cores --lib -- quantum_fabric_npu_cores:: quantum_fabric::npu_cores:: 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; }
          WAI_QUANTUM_NPU_CORES_REPORT="$report" cargo test --locked --features quantum_fabric_npu_cores --test npu_cores_member -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/device.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/device.log" || { echo "::error::not every device test ran and passed"; exit 1; }
          grep -qx 'npu-cores devices: as declared (none)' "$report" || { echo "::error::the absent case was not established"; exit 1; }