CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
|
#include <reduction_op.h>
Classes | |
struct | Params |
Host-constructable parameters structure. More... | |
Public Types | |
using | Element = Element_ |
using | Fragment = Array< Element, kCount > |
using | Operator = plus< Fragment > |
Public Member Functions | |
CUTLASS_HOST_DEVICE | ReductionOpPlus (Params const ¶ms) |
Constructs the function object, possibly loading from pointers in host memory. More... | |
CUTLASS_HOST_DEVICE Fragment | operator() (Fragment const &lhs, Fragment const &rhs) const |
Computes Compute => More... | |
Static Public Attributes | |
static int const | kCount = Count |
Applies a reduction sum to an array of elements.
using cutlass::epilogue::thread::ReductionOpPlus< Element_, Count >::Element = Element_ |
using cutlass::epilogue::thread::ReductionOpPlus< Element_, Count >::Fragment = Array<Element, kCount> |
using cutlass::epilogue::thread::ReductionOpPlus< Element_, Count >::Operator = plus<Fragment> |
|
inline |
|
inline |
|
static |