uni20::kernel::cpu::GemmLoop< T, MR, NR, KR > Class Template Reference

Generic M×N×K contraction engine with full K-dimension recursion. More...

#include <contract.hpp>

Public Member Functions
	GemmLoop (static_vector< extent_strides< 2 >, MR > const &Mgrp, static_vector< extent_strides< 2 >, NR > const &Ngrp, static_vector< extent_strides< 2 >, KR > const &Kgrp, T alpha, T beta) noexcept
	Build the loop engine for a fused contraction.
void	run (T const *A0, T const *B0, T *C0) noexcept
	Perform C = β·C + α·(A ⋅ B) over all fused M, N, and K dimensions.

Detailed Description

template<typename T, std::size_t MR, std::size_t NR, std::size_t KR>
class uni20::kernel::cpu::GemmLoop< T, MR, NR, KR >

Generic M×N×K contraction engine with full K-dimension recursion.

Each dimension group stores extents and operand strides used to perform fused tensor contractions without materialising temporaries.

Template Parameters

T	Scalar type stored in the tensors.
MR	Number of fused M dimensions.
NR	Number of fused N dimensions.
KR	Number of fused K dimensions.

---

The documentation for this class was generated from the following file:

• kernel/cpu/contract.hpp