CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
Public Types | Public Member Functions | List of all members
cutlass::arch::Mma< gemm::GemmShape< 2, 1, 1 >, 1, half_t, LayoutA, half_t, LayoutB, half_t, LayoutC, OpMultiplyAdd > Struct Template Reference

Matrix multiply-add operation.

#include <mma_sm60.h>

Public Types

using Shape = gemm::GemmShape< 2, 1, 1 >
 

Public Member Functions

CUTLASS_HOST_DEVICE void operator() (Array< half_t, 2 > &d, Array< half_t, 2 > const &a, Array< half_t, 1 > const &b, Array< half_t, 2 > const &c)
 

Member Typedef Documentation

template<typename LayoutA , typename LayoutB , typename LayoutC >
using cutlass::arch::Mma< gemm::GemmShape< 2, 1, 1 >, 1, half_t, LayoutA, half_t, LayoutB, half_t, LayoutC, OpMultiplyAdd >::Shape = gemm::GemmShape<2, 1, 1>

Member Function Documentation

template<typename LayoutA , typename LayoutB , typename LayoutC >
CUTLASS_HOST_DEVICE void cutlass::arch::Mma< gemm::GemmShape< 2, 1, 1 >, 1, half_t, LayoutA, half_t, LayoutB, half_t, LayoutC, OpMultiplyAdd >::operator() ( Array< half_t, 2 > &  d,
Array< half_t, 2 > const &  a,
Array< half_t, 1 > const &  b,
Array< half_t, 2 > const &  c 
)
inline

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