name: wai-quantum CUDA member

# The fabric's CUDA member: the gate kernel in CUDA C, compiled at run time for
# each device's own architecture and certified bit-exact against the CPU
# reference's pinned corpus digests.
#
# - cuda-hw (jetson-hub, the RTX 4050): 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;
#   the tensor-core kernel, every product formed on the tensor cores from 8-bit
#   limbs, must do all of the same under its own implementation id, with its
#   own mutants caught; and the dense f64 state vector must come back with the
#   CPU's bits on its pinned corpus and at 16 and 20 qubits, every state-vector
#   mutant caught.
# - cuda-absent (a container with no GPU and no CUDA libraries): 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-cuda.yml'
  schedule:
    - cron: '51 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: 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-cuda.yml \
                "${{ github.event.pull_request.base.sha }}" \
                "${{ github.event.pull_request.head.sha }}")
          echo "this change touches wai-quantum-cuda: $r"
          echo "run=$r" >> "$GITHUB_OUTPUT"

  cuda-hw:
    name: member · CUDA (jetson-hub)
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    runs-on: linux-hw
    timeout-minutes: 90
    env:
      WAI_QUANTUM_CUDA_EXPECT: gpu-cuda-sm89
      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 $want"; exit 1; }
      - name: The member's unit tests
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-cuda" nice -n 10 cargo test --locked --features quantum_fabric_cuda --lib -- quantum_fabric_cuda:: quantum_fabric::cuda:: 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"
          report="$RUNNER_TEMP/cuda-report.txt"; : > "$report"
          WAI_QUANTUM_CUDA_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-cuda" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_cuda --test cuda_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_CUDA_EXPECT"
          grep -qx "cuda devices: as declared ($key)" "$report" || { echo "::error::the devices found are not the declared ones"; exit 1; }
          n="$(grep -c "^cuda certified: key=$key .* parity=bit-exact " "$report")"
          [ "$n" = 4 ] || { echo "::error::$n of 4 certificates were earned"; exit 1; }
          grep -qx "cuda mutants: key=$key killed 6 of 6" "$report" || { echo "::error::a kernel mutant survived"; exit 1; }
      - name: The tensor-core kernel, every product on the tensor cores
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          report="$RUNNER_TEMP/cuda-tensor-report.txt"; : > "$report"
          WAI_QUANTUM_CUDA_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-cuda" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_cuda --test cuda_tensor -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/tensor.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/tensor.log" || { echo "::error::not every tensor-core test ran and passed"; exit 1; }
          cat "$report"
          key="$WAI_QUANTUM_CUDA_EXPECT"
          grep -qx "cuda tensor devices: as declared ($key)" "$report" || { echo "::error::the devices found are not the declared ones"; exit 1; }
          grep -q "^cuda tensor member: key=$key .* implementation=cuda-tensor-limbs8/[0-9a-f]\{16\} " "$report" || { echo "::error::the device ran no tensor-core member"; exit 1; }
          n="$(grep -c "^cuda tensor certified: key=$key .* implementation=cuda-tensor-limbs8/[0-9a-f]\{16\} parity=bit-exact " "$report")"
          [ "$n" = 4 ] || { echo "::error::$n of 4 tensor-core certificates were earned"; exit 1; }
          grep -qx "cuda tensor mutants: key=$key killed 7 of 7" "$report" || { echo "::error::a tensor-core mutant survived"; exit 1; }
      - name: The dense f64 state vector, bit for bit
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          report="$RUNNER_TEMP/cuda-sv-report.txt"; : > "$report"
          WAI_QUANTUM_CUDA_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-cuda" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_cuda,quantum_sv --test cuda_sv -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/sv.log"
          grep -qE '^test result: ok\. 3 passed; 0 failed' "$RUNNER_TEMP/sv.log" || { echo "::error::not every state-vector test ran and passed"; exit 1; }
          cat "$report"
          key="$WAI_QUANTUM_CUDA_EXPECT"
          grep -q "^cuda sv certified: key=$key .* parity=bit-exact cases=48 digest=b7d129d0593adf70dc164477664970c5c0b8c09f79f1a0573036bd60888dbcd1$" "$report" || { echo "::error::the state vector is not the CPU's bit for bit"; exit 1; }
          grep -qx "cuda sv mutants: key=$key killed 4 of 4" "$report" || { echo "::error::a state-vector mutant survived"; exit 1; }

  cuda-absent:
    name: member · CUDA absent (linux)
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    runs-on: linux
    timeout-minutes: 60
    env:
      WAI_QUANTUM_CUDA_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 CUDA here, and the member says so
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          report="$RUNNER_TEMP/cuda-report.txt"; : > "$report"
          WAI_QUANTUM_CUDA_REPORT="$report" cargo test --locked --features quantum_fabric_cuda --test cuda_member -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/device.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/device.log" || { echo "::error::not every device test ran and passed"; exit 1; }
          grep -qx 'cuda devices: as declared (none)' "$report" || { echo "::error::the absent case was not established"; exit 1; }
          WAI_QUANTUM_CUDA_REPORT="$report" cargo test --locked --features quantum_fabric_cuda --test cuda_tensor -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/tensor.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/tensor.log" || { echo "::error::the tensor-core tests did not run over no device"; exit 1; }
          grep -qx 'cuda tensor devices: as declared (none)' "$report" || { echo "::error::the tensor-core absent case was not established"; exit 1; }
          cargo test --locked --features quantum_fabric_cuda,quantum_sv --test cuda_sv -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/sv.log"
          grep -qE '^test result: ok\. 3 passed; 0 failed' "$RUNNER_TEMP/sv.log" || { echo "::error::the state-vector tests did not run over no device"; exit 1; }