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

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, on each host with a CUDA GPU (jetson-hub's laptop GPU, compute
#   capability 8.9, on x86-64; thor's integrated GPU, compute capability 11.0,
#   on aarch64 through CUDA 13.2): 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, 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 (or say it did not), at 16
#   and 20 qubits and on random circuits from |0...0> and from a given state,
#   every state-vector mutant caught; and sparse Pauli dynamics with its sum of
#   terms on the GPU must give the CPU's results and final tables bit for bit
#   on its pinned corpus and on large sums, every mutant caught; and jobs placed on the fabric's members found there (the GPU
#   by CUDA and by OpenCL, the CPU by OpenCL; on thor OpenCL is PoCL's) must give the CPU's answers byte
#   for byte, asked for by key and by `accelerator`, alone and with one state
#   split four ways over them and the CPU reference, a state past a member
#   refused, a job of wider gates placed only where the wider kernels
#   certified, a pauli job on the GPU, and auto keeping every state on the
#   CPU, as the committed measurements say for this host.
# - 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`; and placement with no device, the
#   state split over CPU partitions bit for bit the CPU's, every test by name.

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-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: 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-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 (${{ matrix.host }})
    needs: relevant
    if: needs.relevant.outputs.run == 'true'
    runs-on: ${{ matrix.runner }}
    timeout-minutes: 90
    strategy:
      fail-fast: false
      matrix:
        include:
          # Each host's devices, declared here: its CUDA GPU, and the fabric's
          # members there (sorted), with one state split over them and the CPU
          # reference.
          - host: jetson-hub
            runner: linux-hw
            cuda: gpu-cuda-sm89
            fabric: gpu-cuda-sm89,opencl-cpu-8086,opencl-gpu-10de
            split: gpu-cuda-sm89,opencl-gpu-10de,opencl-cpu-8086,cpu
            pocl_arch: ''
          # PoCL's CUDA device compiles to PTX for sm_90 (its LLVM 18 has no
          # sm_110), which the driver compiles for the GPU.
          - host: thor
            runner: linux-arm64-hw
            cuda: gpu-cuda-sm110
            fabric: gpu-cuda-sm110,opencl-cpu-13b5,opencl-gpu-10de
            split: gpu-cuda-sm110,opencl-gpu-10de,opencl-cpu-13b5,cpu
            pocl_arch: sm_90
    env:
      WAI_QUANTUM_CUDA_EXPECT: ${{ matrix.cuda }}
      WAI_QUANTUM_HW_FABRIC_KEYS: ${{ matrix.fabric }}
      WAI_QUANTUM_HW_FABRIC_SPLIT: ${{ matrix.split }}
      POCL_CUDA_GPU_ARCH: ${{ matrix.pocl_arch }}
      CARGO_PROFILE_DEV_DEBUG: '0'
      CARGO_BUILD_JOBS: '8'
    steps:
      - name: Fetch the source
        shell: bash
        run: |
          set -euo pipefail
          want="${{ 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 "$RUNNER_TEMP/sv.log"
          grep -qE '^test result: ok\. 4 passed; 0 failed' "$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=$key .* parity=bit-exact cases=48 digest=b7d129d0593adf70dc164477664970c5c0b8c09f79f1a0573036bd60888dbcd1$" "$report" || { echo "::error::the state vector is not the CPU's bit for bit"; exit 1; }
          grep -q "^cuda sv wide certified: key=$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 "cuda sv mutants: key=$key killed 4 of 4" "$report" || { echo "::error::a state-vector mutant survived"; exit 1; }
          grep -qx "cuda 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: Sparse Pauli dynamics on the GPU, bit for bit, its table included
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          report="$RUNNER_TEMP/cuda-spd-report.txt"; : > "$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_spd --test cuda_spd -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/spd.log"
          grep -qE '^test result: ok\. 3 passed; 0 failed' "$RUNNER_TEMP/spd.log" || { echo "::error::not every propagation test ran and passed"; exit 1; }
          cat "$report"
          key="$WAI_QUANTUM_CUDA_EXPECT"
          grep -q "^cuda spd certified: key=$key .* kernel=wai.quantum.spd/propagate implementation=cuda-spd/[0-9a-f]\{16\} parity=bit-exact cases=40 digest=25737ef1c61f056c0830404c64dcb06d5355ea784bd15bebbc201500ae85bb8b$" "$report" || { echo "::error::the propagation is not the CPU's bit for bit"; exit 1; }
          grep -q "^cuda spd large: key=$key .* match the CPU bit for bit$" "$report" || { echo "::error::a large sum is not the CPU's"; exit 1; }
          grep -qx "cuda spd mutants: key=$key killed 6 of 6" "$report" || { echo "::error::a propagation mutant survived"; exit 1; }
      - name: Jobs placed on the fabric's members, and a state split over several devices
        shell: bash
        working-directory: src/wai/wai-quantum
        run: |
          set -euo pipefail
          export PATH="$HOME/.cargo/bin:$PATH"
          # The CPU platform's runtime loads its threading and memory libraries
          # from the toolkit's own directories (as in wai-quantum-opencl.yml).
          oneapi=/opt/intel/oneapi
          export LD_LIBRARY_PATH="$oneapi/compiler/latest/lib:$oneapi/tbb/latest/lib/intel64/gcc4.8:$oneapi/tbb/latest/lib:$oneapi/umf/latest/lib:$oneapi/tcm/latest/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
          # The members placement finds here, sorted: the GPU by CUDA and by OpenCL,
          # and the CPU by OpenCL (the integrated GPU has no binary64, and is not
          # placed). One state is split four ways: the GPU by both, the CPU by
          # OpenCL, and the CPU reference.
          keys="${WAI_QUANTUM_HW_FABRIC_KEYS:-gpu-cuda-sm89,opencl-cpu-8086,opencl-gpu-10de}"
          split="${WAI_QUANTUM_HW_FABRIC_SPLIT:-gpu-cuda-sm89,opencl-gpu-10de,opencl-cpu-8086,cpu}"
          report="$RUNNER_TEMP/fabric-report.txt"; : > "$report"
          WAI_QUANTUM_FABRIC_EXPECT="$keys" WAI_QUANTUM_FABRIC_SPLIT="$split" WAI_QUANTUM_FABRIC_PAULI_EXPECT="$WAI_QUANTUM_CUDA_EXPECT" WAI_QUANTUM_FABRIC_REPORT="$report" CARGO_TARGET_DIR="$HOME/hw-target/wai-quantum-cuda" nice -n 10 \
            cargo test --locked --release --features quantum_engine,quantum_fabric,quantum_fabric_cuda,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 -qE "^fabric wide: key=$key (placed at fusion 5, the CPU's answers byte for byte|refused at fusion 5: its wider kernels did not certify bit-exact here)$" "$report" || { echo "::error::$key: a job of wider gates was neither placed with the CPU's answers nor refused"; exit 1; }
          done
          grep -qx "fabric wide: key=$WAI_QUANTUM_CUDA_EXPECT placed at fusion 5, the CPU's answers byte for byte" "$report" || { echo "::error::the GPU's wider kernels did not run a job of wider gates"; exit 1; }
          grep -qx "fabric split: ${split//,/+} over 14 and 19 qubits gives the CPU's answers byte for byte" "$report" || { echo "::error::the state split over the devices is not the CPU's"; exit 1; }
          # The measurements show no member here faster (engine::fabric_measured).
          grep -qx "fabric auto: no member here measured faster; every state on the CPU, its result unnamed" "$report" || { echo "::error::auto did not follow the measurements"; exit 1; }
          grep -q "^fabric accelerator: .* the CPU's answers byte for byte" "$report" || { echo "::error::an accelerator request placed no state"; exit 1; }
          grep -qE "^fabric pauli: key=$WAI_QUANTUM_CUDA_EXPECT 60 qubits, up to [0-9]+ terms, the CPU's answers byte for byte$" "$report" || { echo "::error::a pauli job on the GPU did not give the CPU's answers"; 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 1.99.1
        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 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 "$RUNNER_TEMP/sv.log"
          grep -qE '^test result: ok\. 4 passed; 0 failed' "$RUNNER_TEMP/sv.log" || { echo "::error::the state-vector tests did not run over no device"; exit 1; }
          cargo test --locked --features quantum_fabric_cuda,quantum_spd --test cuda_spd -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/spd.log"
          grep -qE '^test result: ok\. 3 passed; 0 failed' "$RUNNER_TEMP/spd.log" || { echo "::error::the propagation tests did not run over no device"; exit 1; }
          WAI_QUANTUM_FABRIC_EXPECT=none WAI_QUANTUM_FABRIC_PAULI_EXPECT=none WAI_QUANTUM_FABRIC_REPORT="$report" cargo test --locked --features quantum_engine,quantum_fabric,quantum_fabric_cuda --test fabric_placement -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/fabric.log"
          grep -qE '^test result: ok\. 7 passed; 0 failed' "$RUNNER_TEMP/fabric.log" || { echo "::error::the placement tests did not run over no member"; exit 1; }
          grep -qx 'fabric pauli: no member here certified for it; accelerator refused' "$report" || { echo "::error::a pauli job was placed with no member"; exit 1; }
          grep -qx 'fabric members: as declared (none)' "$report" || { echo "::error::the placement's absent case was not established"; exit 1; }
      # The placement and the split with no device: CPU partitions bit for bit the
      # CPU's state vector, exchanges included, and every refusal a host gives;
      # the rule auto places by; the propagation's protocol, run on the host,
      # the CPU's bit for bit; each test required by name.
      - name: Placement and the split, on CPU partitions
        shell: bash
        working-directory: wai/wai-quantum
        run: |
          set -euo pipefail
          cargo test --locked --features full --lib -- engine::fabric:: engine::fabric_measured:: quantum_fabric::sv64:: quantum_fabric::spd:: quantum_spd::device:: 2>&1 | tee "$RUNNER_TEMP/split.log"
          for t in quantum_fabric::sv64::tests::a_partitioned_run_is_the_cpu_run_bit_for_bit \
                   quantum_fabric::sv64::tests::a_launch_table_holds_every_launch_as_it_was_planned \
                   quantum_fabric::sv64::tests::each_corpus_certifies_the_kernels_it_names \
                   quantum_fabric::sv64::tests::the_cpu_reproduces_the_pinned_digest \
                   quantum_fabric::sv64::tests::exchanges_and_remaps_move_amplitudes_and_compute_nothing \
                   quantum_fabric::sv64::tests::a_split_refuses_what_it_cannot_hold \
                   engine::fabric::tests::a_job_s_fabric_reads_or_is_refused_with_its_code \
                   engine::fabric::tests::a_placement_changes_where_the_state_runs_and_not_a_byte_of_the_answers \
                   engine::fabric::tests::a_placement_this_host_cannot_honour_is_refused_never_made_elsewhere \
                   engine::fabric::tests::a_placed_result_and_its_provenance_follow_their_schemas \
                   engine::fabric_measured::tests::every_row_names_a_measured_host_and_its_spread_is_ordered \
                   engine::fabric_measured::tests::the_rules_are_the_rows_faster_tails \
                   engine::fabric_measured::tests::a_faster_tail_is_found_on_rows_of_any_shape \
                   engine::fabric_measured::tests::the_measured_circuit_reads_and_its_job_plans \
                   engine::fabric::tests::a_pauli_job_is_placed_as_asked_and_refused_what_the_host_cannot_honour \
                   quantum_fabric::spd::tests::the_implementation_id_follows_the_kernel_and_every_mutant_edits_once \
                   quantum_spd::device::tests::the_protocol_on_the_host_is_the_cpu_bit_for_bit \
                   quantum_spd::device::tests::the_corpus_reaches_every_decision_of_the_term_set \
                   quantum_spd::device::tests::the_cpu_reproduces_the_pinned_digest \
                   quantum_spd::device::tests::the_encoded_gates_and_the_table_are_the_cpus_conjugations \
                   quantum_spd::device::tests::a_device_s_refusals_are_the_cpus; do
            grep -qx "test $t ... ok" "$RUNNER_TEMP/split.log" || { echo "::error::$t did not run and pass"; exit 1; }
          done
          grep -qE '^test result: ok\. [1-9][0-9]* passed; 0 failed' "$RUNNER_TEMP/split.log" || { echo "::error::a test failed"; exit 1; }