feat(simd_avx2): add U8x32 — native AVX2 byte vector (round-3 keystone) #276
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| on: | |
| pull_request: | |
| paths-ignore: | |
| - '.github/workflows/latest-deps.yaml' | |
| merge_group: | |
| push: | |
| branches: | |
| - master | |
| - main | |
| name: Continuous integration | |
| env: | |
| CARGO_TERM_COLOR: always | |
| HOST: x86_64-unknown-linux-gnu | |
| FEATURES: "approx,serde,rayon" | |
| # `-C target-cpu=x86-64-v3` was removed from the global env. It conflicts | |
| # with the cross_test matrix (`i686-unknown-linux-gnu` is 32-bit, `s390x` | |
| # isn't even x86) and contradicts the design intent recorded in | |
| # `.cargo/config.toml`: per-function `#[target_feature]` + runtime | |
| # `LazyLock<Tier>` detection means one binary, all ISAs. Jobs that | |
| # specifically need a higher target-cpu can opt in via per-job env. | |
| RUSTFLAGS: "-D warnings" | |
| MSRV: 1.94.0 | |
| BLAS_MSRV: 1.94.0 | |
| jobs: | |
| pass-msrv: | |
| runs-on: ubuntu-latest | |
| name: Pass MSRV values to other jobs | |
| outputs: | |
| MSRV: ${{ env.MSRV }} | |
| BLAS_MSRV: ${{ env.BLAS_MSRV }} | |
| steps: | |
| - name: Pass MSRV | |
| run: | | |
| echo "MSRV=${{ env.MSRV }}" >> $GITHUB_OUTPUT | |
| echo "BLAS_MSRV=${{ env.BLAS_MSRV }}" >> $GITHUB_OUTPUT | |
| clippy: | |
| runs-on: ubuntu-latest | |
| strategy: | |
| matrix: | |
| # Pinned to 1.94.1 to match `rust-toolchain.toml`. Auto-tracking | |
| # `stable` would silently bump to 1.95 and start rejecting code | |
| # on lints like `clippy::unnecessary_sort_by` that 1.94 accepted. | |
| rust: | |
| - "1.94.1" | |
| name: clippy/${{ matrix.rust }} | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@1.94.1 | |
| with: | |
| components: clippy | |
| - uses: Swatinem/rust-cache@v2 | |
| - run: cargo clippy --features approx,serde,rayon -- -D warnings | |
| - run: cargo clippy --features native -- -D warnings | |
| format: | |
| runs-on: ubuntu-latest | |
| name: format/nightly | |
| # Marked non-blocking until a separate fmt-sweep PR aligns the | |
| # codebase with `rustfmt.toml`. Local audit (2026-04-30) under | |
| # `cargo +nightly fmt --all -- --check` reports 5,679 drift sites — | |
| # too large to bundle into a CI-fix PR. The format job remains in | |
| # the pipeline as a continuous signal so the sweep author can verify | |
| # zero drift after running `cargo +nightly fmt --all`, but it does | |
| # not gate merge until that sweep lands. | |
| continue-on-error: true | |
| steps: | |
| - uses: actions/checkout@v4 | |
| # `rustfmt.toml` declares 13 nightly-only options | |
| # (`brace_style = AlwaysNextLine`, `imports_granularity = Preserve`, | |
| # `unstable_features = true`, etc.). Stable rustfmt warns and | |
| # ignores them, then produces drift on every nightly-formatted | |
| # file because its defaults differ from the unstable settings. | |
| # The format job MUST use nightly rustfmt for the project's chosen | |
| # style to be enforceable. | |
| # | |
| # The compile + clippy jobs stay on 1.94.1 (pinned in | |
| # `rust-toolchain.toml`) — only this fmt job needs nightly. | |
| - uses: dtolnay/rust-toolchain@nightly | |
| with: | |
| components: rustfmt | |
| - run: cargo fmt --all --check | |
| nostd: | |
| runs-on: ubuntu-latest | |
| continue-on-error: ${{ matrix.experimental }} | |
| strategy: | |
| matrix: | |
| include: | |
| - rust: stable | |
| experimental: false | |
| target: thumbv6m-none-eabi | |
| name: nostd/${{ matrix.target }}/${{ matrix.rust }} | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@stable | |
| with: | |
| toolchain: ${{ matrix.rust }} | |
| targets: ${{ matrix.target }} | |
| # rust-toolchain.toml pins 1.94.1 — install the cross-compile target | |
| # for that toolchain too, since dtolnay/rust-toolchain only installs | |
| # for the matrix value which may differ from the pinned version. | |
| - run: rustup target add ${{ matrix.target }} | |
| - name: Tests | |
| run: | | |
| # Scope to `-p ndarray` so workspace dev-deps (criterion → serde_core | |
| # → getrandom) don't get evaluated against the no_std target. The | |
| # library itself builds cleanly under no_std + portable-atomic- | |
| # critical-section; only its dev-dependency tree pulls std-requiring | |
| # crates that have no business existing in the nostd build. | |
| cargo rustc -p ndarray "--target=${{ matrix.target }}" --no-default-features --features portable-atomic-critical-section | |
| tests: | |
| runs-on: ubuntu-latest | |
| needs: pass-msrv | |
| strategy: | |
| matrix: | |
| rust: | |
| - stable | |
| - beta | |
| - ${{ needs.pass-msrv.outputs.MSRV }} | |
| name: tests/${{ matrix.rust }} | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@master | |
| with: | |
| toolchain: ${{ matrix.rust }} | |
| - uses: rui314/setup-mold@v1 | |
| - uses: Swatinem/rust-cache@v2 | |
| - uses: taiki-e/install-action@nextest | |
| - name: Install openblas | |
| run: sudo apt-get install libopenblas-dev gfortran | |
| - run: ./scripts/all-tests.sh "$FEATURES" ${{ matrix.rust }} | |
| native-backend: | |
| runs-on: ubuntu-latest | |
| name: native-backend/stable | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@stable | |
| - uses: Swatinem/rust-cache@v2 | |
| - uses: taiki-e/install-action@nextest | |
| - name: Build native backend | |
| run: cargo build --features native | |
| - name: Test native backend | |
| run: cargo nextest run -p ndarray --features native | |
| - name: Test native + approx | |
| run: cargo nextest run -p ndarray --features native,approx | |
| blas-msrv: | |
| runs-on: ubuntu-latest | |
| name: blas-msrv | |
| needs: pass-msrv | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@master | |
| with: | |
| toolchain: ${{ needs.pass-msrv.outputs.BLAS_MSRV }} | |
| - uses: rui314/setup-mold@v1 | |
| - uses: Swatinem/rust-cache@v2 | |
| - uses: taiki-e/install-action@nextest | |
| - name: Install openblas | |
| run: sudo apt-get install libopenblas-dev gfortran | |
| - run: ./scripts/blas-integ-tests.sh $BLAS_MSRV | |
| miri: | |
| # Nightly-only. Cannot run SIMD intrinsics or FFI. | |
| # Only runs on merge queue / push to main — never blocks PR checks. | |
| if: github.event_name == 'merge_group' || github.event_name == 'push' | |
| runs-on: ubuntu-latest | |
| name: miri | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@nightly | |
| with: | |
| components: miri | |
| - uses: Swatinem/rust-cache@v2 | |
| - uses: taiki-e/install-action@nextest | |
| - run: ./scripts/miri-tests.sh | |
| cross_test: | |
| # Gated on merge_group only — cross-compile via docker (cross-rs) for | |
| # s390x / i686 is slow, flaky on the s390x docker image's toolchain | |
| # resolution (rust-toolchain.toml's 1.94.1 pin doesn't resolve cleanly | |
| # inside the s390x cross container), and reliably caught by the | |
| # `tests/{stable,beta,1.94.0}` jobs on every PR push. Reserve cross | |
| # validation for the merge queue where it can fail loudly without | |
| # gating individual PRs on infra flakiness. The commented `if:` was | |
| # the original intent (per the pre-existing comment) — uncommenting | |
| # per the PR #143 codex thread that surfaced this consistently. | |
| if: ${{ github.event_name == 'merge_group' }} | |
| runs-on: ubuntu-latest | |
| strategy: | |
| matrix: | |
| include: | |
| - rust: stable | |
| target: s390x-unknown-linux-gnu | |
| - rust: stable | |
| target: i686-unknown-linux-gnu | |
| name: cross_test/${{ matrix.target }}/${{ matrix.rust }} | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@master | |
| with: | |
| toolchain: ${{ matrix.rust }} | |
| targets: ${{ matrix.target }} | |
| - uses: rui314/setup-mold@v1 | |
| - uses: Swatinem/rust-cache@v2 | |
| - name: Install cross | |
| run: cargo install cross | |
| - run: ./scripts/cross-tests.sh "approx,serde,rayon" ${{ matrix.rust }} ${{ matrix.target }} | |
| cargo-careful: | |
| # Nightly-only. Only runs on merge queue / push — never blocks PR checks. | |
| if: github.event_name == 'merge_group' || github.event_name == 'push' | |
| runs-on: ubuntu-latest | |
| name: cargo-careful | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@nightly | |
| - uses: Swatinem/rust-cache@v2 | |
| - uses: taiki-e/install-action@nextest | |
| - name: Install cargo-careful | |
| run: cargo install cargo-careful | |
| - run: cargo careful nextest run -Zcareful-sanitizer --features="$FEATURES" | |
| docs: | |
| # Nightly needed for --cfg docsrs. Only on merge queue / push. | |
| if: github.event_name == 'merge_group' || github.event_name == 'push' | |
| runs-on: ubuntu-latest | |
| name: docs/nightly | |
| env: | |
| RUSTDOCFLAGS: "-Dwarnings --cfg docsrs" | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: dtolnay/rust-toolchain@nightly | |
| - run: cargo doc --no-deps --all-features | |
| conclusion: | |
| needs: | |
| - clippy | |
| - format | |
| - nostd | |
| - tests | |
| - native-backend | |
| - miri | |
| - cross_test | |
| - cargo-careful | |
| - docs | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Result | |
| run: | | |
| jq -C <<< "${needs}" | |
| # Check if all needs were successful or skipped. | |
| "$(jq -r 'all(.result as $result | (["success", "skipped"] | contains([$result])))' <<< "${needs}")" | |
| env: | |
| needs: ${{ toJson(needs) }} |