Enum CutlassEpilogue 

pub enum CutlassEpilogue {
    LinearCombination,
    Relu,
}

A fused pointwise epilogue our compiler folds INTO the GEMM — the thing cuBLAS cannot do in-kernel. cuBLAS must write the GEMM result to global memory and run a SECOND kernel for the activation (an extra full-output read+write); fusing it here removes that round-trip and BEATS a cuBLAS+elementwise baseline.

Variants

LinearCombination

alphaacc + betaC — a plain GEMM (parity with cuBLAS).

Relu

relu(alphaacc + betaC) — GEMM + activation fused in one kernel (the KernelBench Level-2 win).

Trait Implementations

impl Clone for CutlassEpilogue

fn clone(&self) -> CutlassEpilogue

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CutlassEpilogue

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

Formats the value using the given formatter.

impl PartialEq for CutlassEpilogue

fn eq(&self, other: &CutlassEpilogue) -> 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 Copy for CutlassEpilogue

impl Eq for CutlassEpilogue

impl StructuralPartialEq for CutlassEpilogue