CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
|
Reference implementation for GEMM in host-side code. More...
Go to the source code of this file.
Classes | |
struct | cutlass::reference::detail::Cast< SrcType, DstType > |
struct | cutlass::reference::detail::Cast< float, int8_t > |
struct | cutlass::reference::detail::Cast< float, uint8_t > |
Namespaces | |
cutlass | |
cutlass::reference | |
cutlass::reference::detail | |
Functions | |
template<typename Atype , typename Btype , typename Ctype > | |
CUTLASS_HOST_DEVICE Ctype | cutlass::reference::detail::inner_product (Atype a, Btype b, Ctype c) |
Template function to compute an inner product. More... | |
template<> | |
CUTLASS_HOST_DEVICE int | cutlass::reference::detail::inner_product< Array< bin1_t, 32 >, Array< bin1_t, 32 >, int > (Array< bin1_t, 32 > a, Array< bin1_t, 32 > b, int c) |
Specialization for matrix multiplication with binary operands. More... | |