CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
|
Templates exposing architecture support for multiply-add operations. More...
#include "cutlass/cutlass.h"
#include "cutlass/tensor_ref.h"
#include "cutlass/layout/matrix.h"
#include "cutlass/arch/mma.h"
#include "cutlass/gemm/gemm.h"
#include "cutlass/gemm/thread/mma.h"
Go to the source code of this file.
Classes | |
struct | cutlass::gemm::thread::MmaGeneric< Shape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, Operator_ > |
Gemplate that handles all packed matrix layouts. More... | |
struct | cutlass::gemm::thread::Mma< Shape_, ElementA_, LayoutA_, ElementB_, LayoutB_, ElementC_, LayoutC_, arch::OpMultiplyAdd, bool > |
Gemplate that handles conventional layouts for FFMA and DFMA GEMM. More... | |
Namespaces | |
cutlass | |
cutlass::gemm | |
cutlass::gemm::thread | |