Enum OpClass 

pub enum OpClass {
    MatMul,
    Convolution,
    Attention,
    Reduction,
    Elementwise,
    Memory,
}

Routable operation classes used by BackendRegistry::route.

This is a coarse routing key, not the full op set: it lets a consumer ask “which backend should run my GEMMs?” so that, for example, dense linear algebra can be pinned to a Tensor-Core backend while element-wise work goes to whatever is cheapest.

Variants

MatMul

Dense matrix multiply (gemm / batched_gemm).

Convolution

Convolution (conv2d_forward).

Attention

Scaled dot-product attention.

Reduction

Axis reductions.

Elementwise

Element-wise unary / binary / softmax.

Memory

Host/device memory transfers.

Implementations

impl OpClass

pub const ALL: [OpClass; 6]

Every routable op class.

pub const fn prefers_tensor_cores(self) -> bool

true if this op class benefits from Tensor-Core units, so the router prefers a matrix-capable backend when one is available.

Trait Implementations

impl Clone for OpClass

fn clone(&self) -> OpClass

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for OpClass

impl Debug for OpClass

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

Formats the value using the given formatter.

impl Eq for OpClass

impl Hash for OpClass

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for OpClass

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for OpClass