CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
|
Templates exposing SIMD operators. More...
Go to the source code of this file.
Namespaces | |
cutlass | |
cutlass::arch | |
Functions | |
template<typename T , int N> | |
CUTLASS_HOST_DEVICE Array< T, N > | cutlass::arch::operator* (Array< T, N > const &a, Array< T, N > const &b) |
template<typename T , int N> | |
CUTLASS_HOST_DEVICE Array< T, N > | cutlass::arch::operator+ (Array< T, N > const &a, Array< T, N > const &b) |
template<typename T , int N> | |
CUTLASS_HOST_DEVICE Array< T, N > | cutlass::arch::operator- (Array< T, N > const &a, Array< T, N > const &b) |
template<typename T , int N> | |
CUTLASS_HOST_DEVICE Array< T, N > | cutlass::arch::mac (Array< T, N > const &a, Array< T, N > const &b, Array< T, N > const &c) |
template<typename Element , typename Accumulator , int N> | |
CUTLASS_HOST_DEVICE Accumulator | cutlass::arch::dot (Array< T, N > const &a, Array< T, N > const &b, Accumulator accum) |