#include <mm_kernel_outer_A.h>
|
static void | exec (real const *const *const A, real const *const *const B, real *const C, int const i=1) |
| Executes the matrix-matrix multiply C += A B with the three matrices A, B, and C stored using the packing types of this class.
|
|
|
static int const | M_kernel |
| Number of rows of A and C kernels.
|
|
static int const | N_kernel |
| Number of columns of B and C kernels.
|
|
static int const | K_kernel |
| Number of columns of A kernels and rows of B kernels.
|
|
static int const | M_block |
| Number of rows of A and C (blocks).
|
|
static int const | N_block |
| Number of columns of B and C (blocks).
|
|
static int const | K_block |
| Number of columns of A and rows of B (blocks).
|
|
static int const | M |
| Number of rows of A and C.
|
|
static int const | N |
| Number of columns of B and C.
|
|
static int const | K |
| Number of columns of A and rows of B.
|
|
◆ Ordering_block_A
◆ Ordering_block_B
◆ Ordering_block_C
◆ Ordering_matrix
template<typename T_gemm_kernel, int T_M_block, int T_N_block>
template<int T_rows_block, int T_cols_block, typename T_ordering_block, typename T_pack_type_kernel>
template<typename T_ordering_matrix>
typedef T_ordering_matrix MM_kernel_outer_A< T_gemm_kernel, T_M_block, T_N_block >::Pack< T_rows_block, T_cols_block, T_ordering_block, T_pack_type_kernel >::Assign_to_packed< T_ordering_matrix >::Ordering_matrix |
◆ Pack_type_A
◆ Pack_type_B
◆ Pack_type_C
◆ real
Real number type (usually float or double)
◆ exec()
void MM_kernel_outer_A< T_gemm_kernel, T_M_block, T_N_block >::exec |
( |
real const *const *const | A, |
|
|
real const *const *const | B, |
|
|
real *const | C, |
|
|
int const | i = 1 ) |
|
static |
Executes the matrix-matrix multiply C += A B with the three matrices A, B, and C stored using the packing types of this class.
Number of columns of A and rows of B.
◆ K_block
Number of columns of A and rows of B (blocks).
◆ K_kernel
Number of columns of A kernels and rows of B kernels.
Number of rows of A and C.
◆ M_block
Number of rows of A and C (blocks).
◆ M_kernel
Number of rows of A and C kernels.
Number of columns of B and C.
◆ N_block
Number of columns of B and C (blocks).
◆ N_kernel
Number of columns of B and C kernels.
The documentation for this struct was generated from the following file: