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

name: wai-quantum HIP member

# The fabric's HIP member: the CUDA member's kernel text, unchanged, compiled at
# run time by HIP's runtime compiler for each device's own architecture and
# certified bit-exact against the CPU reference's pinned corpus digests.
#
# - hip-hw (framework-128gb, its integrated 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; the matrix-instruction kernel, every product formed by the
#   GPU's bf16 matrix instruction from offset-binary 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, run resident (the state on the device for
#   the whole run), must come back with the CPU's bits on its pinned corpus,
#   on the wider kernels' own corpus, at 16 and 20 qubits and on random
#   circuits from |0...0> and from a given state, every state-vector mutant
#   caught; and jobs placed on the fabric's members found there (the GPU by
#   HIP and by OpenCL) must give the CPU's answers byte for byte, asked for by
#   key and by `accelerator`, alone and with one state split over them, a
#   state past a member refused, a job of wider gates placed, and auto
#   placing a state on the GPU where the committed measurements say it is
#   faster here, and on the CPU elsewhere.
# - hip-absent (a container with no GPU and no HIP 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.event_name == 'push' && github.sha || github.ref }}
  cancel-in-progress: true

on:
  pull_request:
    paths:
      - 'wai/wai-quantum/**'
      - 'rust-toolchain.toml'
      - '.github/workflows/wai-quantum-hip.yml'
  schedule:
    - cron: '43 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: 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-hip.yml \
                "${{ github.event.pull_request.base.sha }}" \
                "${{ github.event.pull_request.head.sha }}")
          echo "this change touches wai-quantum-hip: $r"
          echo "run=$r" >> "$GITHUB_OUTPUT"

  hip-hw:
    name: member · HIP (framework-128gb)
    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="${{ github.event.pull_request.head.sha || github.sha }}"
          rm -rf src && mkdir src && cd src
          git init -q
          # Fetch the commit itself, not the ref: a later commit on the ref that this
          # workflow's paths do not match would otherwise be fetched instead. The
          # host names its own route to the forge (WAI_FORGE_URL).
          git fetch -q --depth 1 "${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 $want"; exit 1; }
      - name: The member's unit tests
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-hip" nice -n 10 cargo test --locked --features quantum_fabric_hip,quantum_sv --lib -- quantum_fabric_hip:: quantum_fabric::hip:: quantum_fabric::sv64:: 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"
          # The devices this host has, declared here (or by the runner, so a GPU
          # and its declaration change in one place).
          key="${WAI_QUANTUM_AMD_HIP_EXPECT:-gpu-hip-gfx1151}"
          report="$RUNNER_TEMP/hip-report.txt"; : > "$report"
          WAI_QUANTUM_HIP_EXPECT="$key" WAI_QUANTUM_HIP_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-hip" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_hip --test hip_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 "$report"
          grep -qx "hip devices: as declared ($key)" "$report" || { echo "::error::the devices found are not the declared ones"; exit 1; }
          n="$(grep -c "^hip certified: key=$key .* parity=bit-exact " "$report")"
          [ "$n" = 4 ] || { echo "::error::$n of 4 certificates were earned"; exit 1; }
          grep -qx "hip mutants: key=$key killed 6 of 6" "$report" || { echo "::error::a kernel mutant survived"; exit 1; }
      - name: The matrix-instruction kernel, every product by the instruction
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          key="${WAI_QUANTUM_AMD_HIP_EXPECT:-gpu-hip-gfx1151}"
          report="$RUNNER_TEMP/hip-wmma-report.txt"; : > "$report"
          WAI_QUANTUM_HIP_EXPECT="$key" WAI_QUANTUM_HIP_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-hip" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_hip --test hip_wmma -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/wmma.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/wmma.log" || { echo "::error::not every matrix-instruction test ran and passed"; exit 1; }
          cat "$report"
          grep -qx "hip wmma devices: as declared ($key)" "$report" || { echo "::error::the devices found are not the declared ones"; exit 1; }
          grep -q "^hip wmma member: key=$key .* implementation=hip-wmma-limbs8/[0-9a-f]\{16\} " "$report" || { echo "::error::the device ran no matrix-instruction member"; exit 1; }
          n="$(grep -c "^hip wmma certified: key=$key .* implementation=hip-wmma-limbs8/[0-9a-f]\{16\} parity=bit-exact " "$report")"
          [ "$n" = 4 ] || { echo "::error::$n of 4 matrix-instruction certificates were earned"; exit 1; }
          grep -qx "hip wmma mutants: key=$key killed 8 of 8" "$report" || { echo "::error::a matrix-instruction 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"
          key="${WAI_QUANTUM_AMD_HIP_EXPECT:-gpu-hip-gfx1151}"
          report="$RUNNER_TEMP/hip-sv-report.txt"; : > "$report"
          WAI_QUANTUM_HIP_EXPECT="$key" WAI_QUANTUM_HIP_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-hip" nice -n 10 \
            cargo test --locked --release --features quantum_fabric_hip,quantum_sv --test hip_sv -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/sv.log"
          grep -qE '^test result: ok\. 4 passed; 0 failed' "$RUNNER_TEMP/sv.log" || { echo "::error::not every state-vector test ran and passed"; exit 1; }
          cat "$report"
          grep -q "^hip sv certified: key=$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 -q "^hip sv wide certified: key=$key .* kernel=wai.quantum.sv/run-wide .* parity=bit-exact cases=120 digest=093614f2386ec5120ab6ccde5187a544518432751591535a6f58c7a44061ebaf$" "$report" || { echo "::error::the wider kernels are not the CPU's bit for bit"; exit 1; }
          grep -qx "hip sv mutants: key=$key killed 4 of 4" "$report" || { echo "::error::a state-vector mutant survived"; exit 1; }
          grep -qx "hip sv random: key=$key 140 resident runs on every kernel match the CPU bit for bit" "$report" || { echo "::error::a random circuit's resident run is not the CPU's"; exit 1; }
      - name: Jobs placed on the fabric's members, and a state split over them
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          # The members placement finds here, sorted (the GPU by HIP and by OpenCL),
          # declared here or by the runner; one state is split over them.
          keys="${WAI_QUANTUM_AMD_FABRIC_KEYS:-gpu-hip-gfx1151,opencl-gpu-1002}"
          report="$RUNNER_TEMP/fabric-report.txt"; : > "$report"
          WAI_QUANTUM_FABRIC_EXPECT="$keys" WAI_QUANTUM_FABRIC_SPLIT="$keys" WAI_QUANTUM_FABRIC_PAULI_EXPECT=none WAI_QUANTUM_FABRIC_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-hip" nice -n 10 \
            cargo test --locked --release --features quantum_engine,quantum_fabric,quantum_fabric_hip,quantum_fabric_opencl --test fabric_placement -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/fabric.log"
          grep -qE '^test result: ok\. 7 passed; 0 failed' "$RUNNER_TEMP/fabric.log" || { echo "::error::not every placement test ran and passed"; exit 1; }
          cat "$report"
          grep -qx "fabric members: as declared ($keys)" "$report" || { echo "::error::the members placement found are not the declared ones"; exit 1; }
          for key in ${keys//,/ }; do
            grep -q "^fabric placed: key=$key .* give the CPU's answers byte for byte$" "$report" || { echo "::error::$key: a placed job's answers are not the CPU's"; exit 1; }
            grep -q "^fabric refused: key=$key " "$report" || { echo "::error::$key: a state past what it holds was not refused"; exit 1; }
            grep -qx "fabric wide: key=$key placed at fusion 5, the CPU's answers byte for byte" "$report" || { echo "::error::$key: a job of wider gates did not run with the CPU's answers"; exit 1; }
          done
          grep -qx "fabric split: ${keys//,/+} over 14 and 19 qubits gives the CPU's answers byte for byte" "$report" || { echo "::error::the state split over the members is not the CPU's"; exit 1; }
          # The measurements show the integrated GPU faster here from 18 qubits at
          # fusion 2 and 3 (engine::fabric_measured): auto places the measured job
          # on it, and keeps a shallower one on the CPU.
          # (A runner whose processor is not the one measured, by its model or its
          # thread count, matches no row, and auto keeps every state on its CPU.)
          if [ "$(grep -c '^fabric auto host: .* measured=true$' "$report")" = 1 ]; then
            grep -qE "^fabric auto: by measurement, 18 qubits at fusion 2 on (gpu-hip-gfx1151|opencl-gpu-1002), the CPU's answers byte for byte; a shallower job on the CPU$" "$report" || { echo "::error::auto did not follow the measurements"; exit 1; }
          else
            grep -qx "fabric auto: no member here measured faster; every state on the CPU, its result unnamed" "$report" || { echo "::error::auto placed a state on a host not measured"; exit 1; }
          fi
          grep -q "^fabric accelerator: .* the CPU's answers byte for byte" "$report" || { echo "::error::an accelerator request placed no state"; exit 1; }
          # The pauli method's members are CUDA's alone: none here, and it says so.
          grep -qx "fabric pauli: no member here certified for it; accelerator refused" "$report" || { echo "::error::a pauli job was placed with no member for it"; exit 1; }

  hip-absent:
    name: member · HIP absent (linux-arm64)
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    runs-on: linux-arm64
    timeout-minutes: 60
    env:
      WAI_QUANTUM_HIP_EXPECT: none
    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: No HIP here, and the member says so
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          report="$RUNNER_TEMP/hip-report.txt"; : > "$report"
          WAI_QUANTUM_HIP_REPORT="$report" cargo test --locked --features quantum_fabric_hip --test hip_member -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/device.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/device.log" || { echo "::error::not every device test ran and passed"; exit 1; }
          grep -qx 'hip devices: as declared (none)' "$report" || { echo "::error::the absent case was not established"; exit 1; }
          WAI_QUANTUM_HIP_REPORT="$report" cargo test --locked --features quantum_fabric_hip --test hip_wmma -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/wmma.log"
          grep -qE '^test result: ok\. 9 passed; 0 failed' "$RUNNER_TEMP/wmma.log" || { echo "::error::the matrix-instruction tests did not run over no device"; exit 1; }
          grep -qx 'hip wmma devices: as declared (none)' "$report" || { echo "::error::the matrix-instruction absent case was not established"; exit 1; }
          cargo test --locked --features quantum_fabric_hip,quantum_sv --test hip_sv -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/sv.log"
          grep -qE '^test result: ok\. 4 passed; 0 failed' "$RUNNER_TEMP/sv.log" || { echo "::error::the state-vector tests did not run over no device"; exit 1; }
          WAI_QUANTUM_FABRIC_EXPECT=none WAI_QUANTUM_FABRIC_REPORT="$report" cargo test --locked --features quantum_engine,quantum_fabric,quantum_fabric_hip --test fabric_placement -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/fabric.log"
          grep -qE '^test result: ok\. 7 passed; 0 failed' "$RUNNER_TEMP/fabric.log" || { echo "::error::the placement tests did not run over no member"; exit 1; }
          grep -qx 'fabric members: as declared (none)' "$report" || { echo "::error::the placement's absent case was not established"; exit 1; }