Struct AmxInt8 

pub struct AmxInt8;

x86/x86_64 AMX INT8 matrix multiply backend.

Trait Implementations

impl AmxGemm<I8, I8, I32> for AmxInt8

unsafe fn amx_gemm( m: usize, n: usize, k: usize, a: *const I8, a_stride: usize, b: *const I8, b_stride: usize, c: *mut I32, c_stride: usize, )

Perform matrix multiplication c += a * b using Intel AMX block execution.

impl AmxGemm<i8, i8, i32> for AmxInt8

unsafe fn amx_gemm( m: usize, n: usize, k: usize, a: *const i8, a_stride: usize, b: *const i8, b_stride: usize, c: *mut i32, c_stride: usize, )

Perform matrix multiplication c += a * b using Intel AMX block execution.

impl Clone for AmxInt8

fn clone(&self) -> AmxInt8

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for AmxInt8

impl Debug for AmxInt8

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

Formats the value using the given formatter.

impl Eq for AmxInt8

impl PartialEq for AmxInt8

fn eq(&self, other: &AmxInt8) -> bool

Equality operator ==.

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

Inequality operator !=.

impl SimdArch for AmxInt8

const NAME: &'static str = "amx_int8"

Human-readable ISA name ("avx2", "avx512", "neon", "scalar").

const REGISTER_WIDTH_BITS: u32 = 8192

Width of vector registers in bits.

const ISA_FAMILY: IsaFamily = IsaFamily::X86

ISA family for this architecture.

const FMA_THROUGHPUT_HINT: u32 = 16

Suggested TILE_M value for tiled_dot to saturate FMA throughput.

fn is_runtime_supported() -> bool

Returns true when the current host may execute this architecture’s native instructions from safe wrappers.

impl StructuralPartialEq for AmxInt8

impl TileMatrixMultiply<I8, I8, I32, AmxInt8, AmxInt8, 16, 16, 64> for AmxInt8

unsafe fn tile_matmul( c: *mut I32, c_stride: usize, a: *const I8, a_stride: usize, b: *const I8, b_stride: usize, )

Performs tile matrix multiplication: C += A * B

impl TileMatrixMultiply<i8, i8, i32, AmxInt8, AmxInt8, 16, 16, 64> for AmxInt8

unsafe fn tile_matmul( c: *mut i32, c_stride: usize, a: *const i8, a_stride: usize, b: *const i8, b_stride: usize, )

Performs tile matrix multiplication: C += A * B