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

Specialization implementing multiply-add operation on half-precision floating point fragments. 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_, half, half, half >
 Template performing matrix multiply-add operation within a thread. More...
 

Namespaces

 cutlass
 
 cutlass::gemm