Enum AccelX4 

pub enum AccelX4 {
    NeonI8mm,
    Avx2,
    Portable,
}

Which ×4 GEMM kernel this host runs, resolved once instead of once per call.

The gemm_*_group_x4 entry points are called once per (row-group × activation-quad) pair, which on a pp512 projection is 10^4 to 10^5 calls per GEMM. Each one used to re-run is_aarch64_feature_detected!, whose relaxed atomic load LLVM cannot hoist out of the caller’s loop. Callers now probe once per matmul and pass the answer down through the _on variants; [gemm_q4_kx8_group_x4] and its siblings stay as probe-per-call wrappers so existing callers and tests are unchanged.

This is a dispatch decision only. Every arm computes the same values, to within f32 rounding order; the portable arm is bit-identical to the per-activation GEMV, which is what the *_x4_portable_is_bit_exact_vs_scalar_gemv tests assert. Forcing AccelX4::Portable on an accelerated host is therefore a valid (slow) way to run, and the tests use it that way.

Variants

NeonI8mm

ARM i8mm SMMLA kernels in super::neon.

Avx2

x86_64 AVX2 + FMA kernels in super::avx2.

Portable

The portable scalar reference.

Implementations

impl AccelX4

pub fn detect() -> Self

The fastest kernel available on this host.

pub fn is_simd(self) -> bool

Whether this is a real SIMD kernel rather than the scalar reference.

Trait Implementations

impl Clone for AccelX4

fn clone(&self) -> AccelX4

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Copy for AccelX4

impl Debug for AccelX4

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Eq for AccelX4

impl PartialEq for AccelX4

fn eq(&self, other: &AccelX4) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for AccelX4