dcharlot
bbc5e531ce
Some checks failed
repository checks / lockfiles, advisories, tests in CI, workflow hygiene, spec and section references, public text (push) Has been cancelled
182 lines
10 KiB
YAML
182 lines
10 KiB
YAML
name: wai-quantum matrix-extension member
|
|
|
|
# The fabric's matrix-extension member: the gate's fixed-point arithmetic in the
|
|
# processor's streaming vector mode (SME), 64-bit lanes, certified bit-exact
|
|
# against the CPU reference's pinned corpus digests.
|
|
#
|
|
# - sme-emulated (the container runner): the member's device tests for aarch64
|
|
# Linux, run under a user-mode emulator the job fetches and runs itself
|
|
# (Debian's static QEMU, pinned, which emulates SME), never the host's binfmt
|
|
# handler; the job declares the emulator, and every certificate says it was
|
|
# earned there, never on silicon.
|
|
# - sme-absent (the macOS runner, whose processor has no SME): the same build
|
|
# finds no member and says why.
|
|
#
|
|
# Silicon: a processor with SME runs the same tests with the declaration
|
|
# `cpu-matrix-sme` and no emulator.
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
on:
|
|
pull_request:
|
|
paths:
|
|
- 'wai/wai-quantum/**'
|
|
- 'rust-toolchain.toml'
|
|
- '.github/workflows/wai-quantum-sme.yml'
|
|
schedule:
|
|
- cron: '14 8 * * *'
|
|
|
|
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-sme.yml \
|
|
"${{ github.event.pull_request.base.sha }}" \
|
|
"${{ github.event.pull_request.head.sha }}")
|
|
echo "this change touches wai-quantum-sme: $r"
|
|
echo "run=$r" >> "$GITHUB_OUTPUT"
|
|
|
|
sme-emulated:
|
|
name: member · matrix extension, emulated (aarch64 Linux)
|
|
needs: relevant
|
|
if: needs.relevant.outputs.run == 'true'
|
|
runs-on: linux
|
|
timeout-minutes: 90
|
|
container:
|
|
image: ghcr.io/cross-rs/aarch64-unknown-linux-gnu@sha256:7f8308a8734d9fcd2ebbe9a3e4bdea74af293f0799d80c3cc341e340cda49a4c
|
|
options: --memory=6g --memory-swap=6g
|
|
env:
|
|
WAI_QUANTUM_SME_EXPECT: cpu-matrix-sme
|
|
# The emulator every aarch64 test binary runs under, which the certificates
|
|
# name: Debian's static QEMU, SHA-256 pinned, fetched by the job and named as
|
|
# cargo's runner. Not the image's own (5.1), and not the host's binfmt
|
|
# handler, which some `linux` runners lack and others run at another
|
|
# version. (Not QEMU_*: qemu-user reads every QEMU_<option> variable as that
|
|
# option.)
|
|
WAI_QUANTUM_SME_EMULATOR: qemu-user 10.0.13 (Debian's static build, run by the job)
|
|
USER_EMULATOR_VERSION: 10.0.13
|
|
USER_EMULATOR_DEB: qemu-user_10.0.13+ds-0+deb13u1_amd64.deb
|
|
USER_EMULATOR_SHA256: ca6ede739327a20ae5a3498230c8a3a9a072c586e131bc6bcc1201eb1725e336
|
|
USER_EMULATOR_SHA1: dec1373851d29f91642c197f4a339d0d2ad25ed0
|
|
steps:
|
|
# The image has no Node for a checkout action: the forge's archive of the
|
|
# exact commit, its embedded commit id checked.
|
|
- name: Fetch the source
|
|
shell: bash
|
|
run: |
|
|
set -euo pipefail
|
|
want="${{ github.event.pull_request.head.sha || github.sha }}"
|
|
rm -rf src src.tar.gz src.tar && mkdir src
|
|
curl -sSf -o src.tar.gz "http://100.64.224.0:3400/Transaction-Science/open-standards/archive/$want.tar.gz"
|
|
gzip -dc src.tar.gz > src.tar
|
|
got="$(git get-tar-commit-id < src.tar)"
|
|
[ "$got" = "$want" ] || { echo "::error::the archive is of $got, not $want"; exit 1; }
|
|
# -m: every file gets the time it was extracted, not its commit's. The build
|
|
# reuses a target directory kept between runs, and cargo takes a crate as
|
|
# built when no source file is newer than its last build: with the commit's
|
|
# times, an older commit ran the binary another commit had built there.
|
|
tar -xmf src.tar -C src --strip-components=1
|
|
rm src.tar.gz src.tar
|
|
- name: The member's device tests under the emulator
|
|
shell: bash
|
|
working-directory: src/wai/wai-quantum
|
|
run: |
|
|
set -euo pipefail
|
|
cache=/ci-cache/wai-quantum-sme
|
|
mkdir -p "$cache"
|
|
exec 9>"$cache/.lock"
|
|
flock 9
|
|
# Every source file newer than every build in the cache, now that the lock is
|
|
# held: another run may have built here while this one waited for it, after
|
|
# this one's extraction. (../.. is the extracted tree.)
|
|
find ../.. -type f -exec touch {} +
|
|
export RUSTUP_HOME="$cache/rustup" CARGO_HOME="$cache/cargo" CARGO_TARGET_DIR="$cache/target"
|
|
export PATH="$CARGO_HOME/bin:$PATH"
|
|
if ! command -v rustup >/dev/null; then
|
|
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --no-modify-path --profile minimal --default-toolchain none
|
|
fi
|
|
rustup toolchain install
|
|
rustup target add aarch64-unknown-linux-gnu
|
|
# The emulator, fetched once per host into the cache (under the lock above)
|
|
# and checked against its pin, then named as cargo's runner, so this leg
|
|
# passes or fails the same on every `linux` runner.
|
|
q="$cache/qemu-user-$USER_EMULATOR_VERSION"
|
|
if [ ! -x "$q/qemu-aarch64" ]; then
|
|
d="$cache/qemu-user-fetch"; rm -rf "$d" && mkdir "$d"
|
|
curl -sSfL -o "$d/$USER_EMULATOR_DEB" "https://deb.debian.org/debian/pool/main/q/qemu/$USER_EMULATOR_DEB" \
|
|
|| curl -sSfL -o "$d/$USER_EMULATOR_DEB" "https://snapshot.debian.org/file/$USER_EMULATOR_SHA1"
|
|
echo "$USER_EMULATOR_SHA256 $d/$USER_EMULATOR_DEB" | sha256sum -c -
|
|
dpkg-deb --fsys-tarfile "$d/$USER_EMULATOR_DEB" | tar -x -C "$d" ./usr/bin/qemu-aarch64
|
|
rm -rf "$q.tmp" && mkdir "$q.tmp" && mv "$d/usr/bin/qemu-aarch64" "$q.tmp/"
|
|
rm -rf "$q" && mv "$q.tmp" "$q" && rm -rf "$d"
|
|
fi
|
|
runner="$q/qemu-aarch64 -L /usr/aarch64-linux-gnu"
|
|
export CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_RUNNER="$runner"
|
|
# Preflight: a trivial program, built for the target and run as cargo will run
|
|
# the tests. An emulator that cannot run it fails the leg here, saying so,
|
|
# rather than as a test that never ran.
|
|
cat > "$RUNNER_TEMP/probe.c" <<'EOF'
|
|
#include <stdio.h>
|
|
#include <sys/utsname.h>
|
|
int main(void) { struct utsname u; if (uname(&u) != 0) return 1; printf("%s\n", u.machine); return 0; }
|
|
EOF
|
|
aarch64-linux-gnu-gcc -o "$RUNNER_TEMP/probe" "$RUNNER_TEMP/probe.c"
|
|
got="$($runner "$RUNNER_TEMP/probe")" || { echo "::error::the emulator cannot run an aarch64 program: $runner"; exit 1; }
|
|
[ "$got" = aarch64 ] || { echo "::error::the preflight program ran as $got, not aarch64"; exit 1; }
|
|
echo "emulator: $("$q/qemu-aarch64" --version | head -1); an aarch64 program runs under it"
|
|
report="$(mktemp)"
|
|
WAI_QUANTUM_SME_REPORT="$report" cargo test --locked --release -j 6 --target aarch64-unknown-linux-gnu --features quantum_fabric_sme --test sme_member -- --test-threads=1 2>&1 | tee "$cache/device.log"
|
|
# The first build after the refresh compiles wai-quantum; one that compiled
|
|
# none ran a binary another commit left in the cache.
|
|
grep -qE '^ *Compiling wai-quantum v[0-9]' "$cache/device.log" || { echo "::error::the build compiled no wai-quantum: its tests ran a binary already in the cache"; exit 1; }
|
|
grep -qE '^test result: ok\. 9 passed; 0 failed' "$cache/device.log" || { echo "::error::not every device test ran and passed"; exit 1; }
|
|
cat "$report"
|
|
key="$WAI_QUANTUM_SME_EXPECT"
|
|
grep -qx "sme devices: as declared ($key)" "$report" || { echo "::error::the member found is not the declared one"; exit 1; }
|
|
grep -q "^sme member: key=$key .*emulator:qemu-user" "$report" || { echo "::error::the member does not say it ran under the emulator"; exit 1; }
|
|
n="$(grep -c "^sme certified: key=$key .* parity=bit-exact " "$report")"
|
|
[ "$n" = 4 ] || { echo "::error::$n of 4 certificates were earned"; exit 1; }
|
|
grep -qx "sme mutants: key=$key killed 3 of 3" "$report" || { echo "::error::a kernel mutant survived"; exit 1; }
|
|
|
|
sme-absent:
|
|
name: member · matrix extension absent (macos)
|
|
needs: relevant
|
|
if: needs.relevant.outputs.run == 'true'
|
|
# The Mac Studio's M3 Ultra has no matrix extension; the fleet's M4 Max and M5 Max
|
|
# do, and this member refuses a host that has one. It runs on the Studio by its label.
|
|
runs-on: macos-m3-ultra
|
|
timeout-minutes: 60
|
|
env:
|
|
WAI_QUANTUM_SME_EXPECT: none
|
|
steps:
|
|
- uses: actions/checkout@v5
|
|
# launchd's PATH omits cargo on the macOS host runner.
|
|
- name: Put cargo on PATH
|
|
shell: bash
|
|
run: echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
|
|
- name: No matrix extension here, and the member says so
|
|
shell: bash
|
|
working-directory: wai/wai-quantum
|
|
run: |
|
|
set -euo pipefail
|
|
[ "$(sysctl -n hw.optional.arm.FEAT_SME 2>/dev/null || echo 0)" = 0 ] || { echo "::error::this runner has SME; declare it and run the silicon tests"; exit 1; }
|
|
report="$RUNNER_TEMP/sme-report.txt"; : > "$report"
|
|
WAI_QUANTUM_SME_REPORT="$report" nice -n 10 cargo test --locked --features quantum_fabric_sme --test sme_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 'sme devices: as declared (none)' "$report" || { echo "::error::the absent case was not established"; exit 1; }
|