Templates for efficient gemm kernels. More...

#include "common.h"
#include "vector_intrin.h"

Classes
class	MM_kernel_inner_sse2_A< T_real, T_reg, T_M, T_N, T_K >
	Matrix multiplication template for architectures with SSE2 or higher and compilers that support C++ intrinsics for access to SSE instructions. More...
struct	MM_kernel_inner_sse2_A< T_real, T_reg, T_M, T_N, T_K >::Loop< T_loop_index, T_end >
struct	MM_kernel_inner_sse2_A< T_real, T_reg, T_M, T_N, T_K >::Loop< T_end, T_end >
class	MM_kernel_inner_sse2_A< T_real, T_reg, T_M, T_N, T_K >::Pack< T_rows, T_cols, T_ordering_kernel, T_repetitions >
	Template for packing of matrix elements. More...
struct	MM_kernel_inner_sse2_A< T_real, T_reg, T_M, T_N, T_K >::Pack< T_rows, T_cols, T_ordering_kernel, T_repetitions >::Assign_to_packed< T_ordering_matrix >
struct	MM_kernel_inner_sse2_A< T_real, T_reg, T_M, T_N, T_K >::Pack< T_rows, T_cols, T_ordering_kernel, T_repetitions >::Extract_from_packed< T_ordering_matrix >

Detailed Description

Templates for efficient gemm kernels.

For architectures with SSE2 or higher.

Classes