Cutlass
CUDA Templates for Linear Algebra Subroutines and Solvers
Classes | Namespaces
igemm_multiply_add.h File Reference

Implements matrix multiply accumulate operation of 8-bit integer data using DP4A instruction. More...

#include <cutlass/fragment.h>
#include <cutlass/gemm/thread_multiply_add.h>

Go to the source code of this file.

Classes

struct  cutlass::gemm::ThreadMultiplyAdd< AccumulatorsPerThread_, ThreadsPerWarp_, int8_t, int8_t, int >
 Template performing matrix multiply-add operation within a thread. More...
 

Namespaces

 cutlass
 
 cutlass::gemm