Merge pull request #146 from AdaWorldAPI/claude/portable-simd-nightly

feat(simd_nightly): 30-type portable-simd backend (draft, nightly-simd feature)

Author: AdaWorldAPI

.claude/board/AGENT_LOG.md

@@ -147,6 +147,20 @@ serde = ["dep:serde"]
 std = ["num-traits/std", "matrixmultiply/std"]
 rayon = ["dep:rayon", "std"]
 
+# Portable-SIMD backend (NIGHTLY ONLY). Routes `crate::simd::*` types
+# through `core::simd::*` instead of the architecture-specific intrinsics
+# in `simd_avx512.rs` / `simd_avx2.rs` / `simd_neon.rs`. The point is
+# miri compatibility: miri can execute `core::simd` semantics but treats
+# `_mm*_*` intrinsics as opaque. With this feature on, miri-run tests
+# exercise the actual SIMD code paths in consumer code (`hpc/byte_scan`,
+# `hpc/framebuffer`, etc.) and catch UB that the intrinsics backend hides.
+#
+# Requires `cargo +nightly` because `src/simd_nightly.rs` is gated on
+# `#![feature(portable_simd)]` (Rust unstable issue #86656). The default
+# build (stable 1.95) does NOT touch this; the existing intrinsics
+# cfg-dispatch in `simd.rs` remains the production path.
+nightly-simd = ["std"]
+
 # HPC extras: blake3 hashing, p64 palette/NARS bridge, fractal manifold.
 # These pull in a non-trivial dependency tree; downstream crates such as
 # burn-ndarray that only need the core array layer can disable this with

Cargo.toml

@@ -6,6 +6,12 @@
 // option. This file may not be copied, modified, or distributed
 // except according to those terms.
 #![crate_name = "ndarray"]
+// Crate-level nightly feature gate for the optional `nightly-simd` backend
+// (`src/simd_nightly/`). When the `nightly-simd` cargo feature is OFF
+// (default), this attribute is absent and stable rustc compiles the crate
+// normally. When ON, the crate requires nightly rustc to access
+// `core::simd::*` types.
+#![cfg_attr(feature = "nightly-simd", feature(portable_simd))]
 #![doc(html_root_url = "https://docs.rs/ndarray/0.15/")]
 #![doc(html_logo_url = "https://rust-ndarray.github.io/images/rust-ndarray_logo.svg")]
 #![allow(
@@ -240,6 +246,14 @@ pub(crate) mod simd_avx512;
 #[allow(clippy::all, missing_docs, dead_code, unused_variables, unused_imports)]
 pub mod simd_avx2;
 
+// Portable-SIMD backend — nightly-only. Wraps `core::simd::*` so miri can
+// execute the polyfill paths (intrinsic-based backends are opaque to
+// miri). Gated behind `nightly-simd` feature; the file itself requires
+// `#![feature(portable_simd)]` so it only compiles on nightly rustc.
+#[cfg(feature = "nightly-simd")]
+#[allow(clippy::all, missing_docs)]
+pub mod simd_nightly;
+
 #[cfg(feature = "std")]
 #[allow(clippy::all, missing_docs, dead_code, unused_variables, unused_imports)]
 // AMX is an x86_64-only ISA (Intel Sapphire Rapids+); the module uses

src/lib.rs

@@ -203,6 +203,15 @@ pub const PREFERRED_I16_LANES: usize = 16;
 // at compile time → all types use native __m512/__m512d/__m512i.
 // The 256-bit types (F32x8, F64x4) also live in simd_avx512 (__m256).
 
+// Note on the `nightly-simd` feature: it adds the `crate::simd_nightly`
+// module (a portable-simd backend wrapping `core::simd`) but does NOT
+// replace the intrinsics dispatch below. Full type-parity coverage
+// would require the nightly module to define ~30 types; the current
+// draft covers 5 (F32x16, F64x8, U8x64, U32x16, F32Mask16). Consumers
+// who want miri-runnable SIMD code import from `simd_nightly`
+// explicitly (e.g. `use ndarray::simd_nightly::F32x16`). The main
+// polyfill via `crate::simd::F32x16` continues to use intrinsics.
+
 #[cfg(all(target_arch = "x86_64", target_feature = "avx512f"))]
 pub use crate::simd_avx512::{
     f32x16,