mma_sm70.h File Reference

Matrix multiply. More...

#include <assert.h>
#include "mma.h"
#include "cutlass/layout/matrix.h"
#include "cutlass/numeric_types.h"

Include dependency graph for mma_sm70.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
struct	cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::ColumnMajor, half_t, layout::ColumnMajor, half_t, layout::RowMajor, OpMultiplyAdd >
	Matrix multiply-add operation: F16 = F16 * F16 + F16. More...
struct	cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::ColumnMajor, half_t, layout::RowMajor, half_t, layout::RowMajor, OpMultiplyAdd >
	Matrix multiply-add operation: F16 = F16 * F16 + F16. More...
struct	cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::RowMajor, half_t, layout::ColumnMajor, half_t, layout::RowMajor, OpMultiplyAdd >
	Matrix multiply-add operation: F16 = F16 * F16 + F16. More...
struct	cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::RowMajor, half_t, layout::RowMajor, half_t, layout::RowMajor, OpMultiplyAdd >
	Matrix multiply-add operation: F16 = F16 * F16 + F16. More...
struct	cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::ColumnMajor, half_t, layout::ColumnMajor, float, layout::RowMajor, OpMultiplyAdd >
	Matrix multiply-add operation: F32 = F16 * F16 + F32. More...
struct	cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::ColumnMajor, half_t, layout::RowMajor, float, layout::RowMajor, OpMultiplyAdd >
	Matrix multiply-add operation: F32 = F16 * F16 + F32. More...
struct	cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::RowMajor, half_t, layout::ColumnMajor, float, layout::RowMajor, OpMultiplyAdd >
	Matrix multiply-add operation: F32 = F16 * F16 + F32. More...
struct	cutlass::arch::Mma< gemm::GemmShape< 8, 8, 4 >, 8, half_t, layout::RowMajor, half_t, layout::RowMajor, float, layout::RowMajor, OpMultiplyAdd >
	Matrix multiply-add operation: F32 = F16 * F16 + F32. More...
struct	cutlass::arch::Mma< gemm::GemmShape< 16, 16, 4 >, 32, half_t, LayoutA, half_t, LayoutB, ElementC, LayoutC, Operator >
	Matrix multiply-add operation specialized for the entire warp. More...

Namespaces
	cutlass
	cutlass::arch