quantum_fabric_tensor_engine (opt-in): the gate's sixteen products per pair as exact limb convolutions in one bf16 matrix multiply per tile of 512 pairs, accumulated in fp32, on a tensor processor's matrix engine. Each 32-bit value is four 8-bit limbs (bf16 holds each exactly), every limb product is at most 2^16 and every coefficient a sum of at most four, so fp32 holds every partial sum exactly in any order: the argument holds for any engine that multiplies bf16 and accumulates in fp32. The host checks every coefficient is an integer below 2^24, assembles the products in 64 bits and applies the fixed-point arithmetic, as the neural-processor member's host does. The probe uses its own weight layout, sixteen independent pairs a multiply. The kernel (tensor_engine_helper.py) runs as a long-lived helper under the Python WAI_QUANTUM_TENSOR_ENGINE_PYTHON names; today its target is the kernel toolchain's simulator (Apache-2.0), so every certificate's provenance is simulator:<versions>. Four mutants: the three host constants, and Radix9, nine-bit limbs the engine's bf16 inputs cannot hold, which the engine gets wrong. Measured on the simulator: tensor_engine_member 9/9 in 340 s (66020 probe pairs, all four pinned certificates, circuits to 20 qubits, 4 of 4 mutants killed). Workflow: the simulator on the container runner, and the absent case on linux-arm64, where the HIP and npu-cores absent legs move too. Co-Authored-By: Claude Opus 5.5 <[email protected]>
153 lines
7.9 KiB
YAML
153 lines
7.9 KiB
YAML
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; 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.
|
|
# - 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.ref }}
|
|
cancel-in-progress: true
|
|
|
|
on:
|
|
push:
|
|
branches: [main]
|
|
paths:
|
|
- 'wai/wai-quantum/**'
|
|
- 'rust-toolchain.toml'
|
|
- '.github/workflows/wai-quantum-hip.yml'
|
|
pull_request:
|
|
paths:
|
|
- 'wai/wai-quantum/**'
|
|
- 'rust-toolchain.toml'
|
|
- '.github/workflows/wai-quantum-hip.yml'
|
|
|
|
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-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 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 "$RUNNER_TEMP/sv.log"
|
|
grep -qE '^test result: ok\. 3 passed; 0 failed' "$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 -qx "hip sv mutants: key=$key killed 4 of 4" "$report" || { echo "::error::a state-vector mutant survived"; 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 1.98.0
|
|
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 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; }
|
|
cargo test --locked --features quantum_fabric_hip,quantum_sv --test hip_sv -- --test-threads=1 2>&1 | tee "$RUNNER_TEMP/sv.log"
|
|
grep -qE '^test result: ok\. 3 passed; 0 failed' "$RUNNER_TEMP/sv.log" || { echo "::error::the state-vector tests did not run over no device"; exit 1; }
|