#include <batched_reduction.h>
|
CUTLASS_DEVICE | BatchedReduction (Params const ¶ms_) |
| ctor More...
|
|
CUTLASS_DEVICE void | run () |
|
template<bool ThreadShapeMultiple2> |
CUTLASS_DEVICE void | functor_caller (typename Traits::ScalarAccum const *accum, typename Traits::ScalarAccum const *old, typename Traits::ScalarAccum *output) |
|
template<typename BatchedReductionTraits_ >
template<typename BatchedReductionTraits_ >
template<typename BatchedReductionTraits_ >
template<typename BatchedReductionTraits_ >
template<typename BatchedReductionTraits_ >
template<typename BatchedReductionTraits_ >
template<bool ThreadShapeMultiple2>
CUTLASS_DEVICE void cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::functor_caller |
( |
typename Traits::ScalarAccum const * |
accum, |
|
|
typename Traits::ScalarAccum const * |
old, |
|
|
typename Traits::ScalarAccum * |
output |
|
) |
| |
|
inline |
template<typename BatchedReductionTraits_ >
template<typename BatchedReductionTraits_ >
main operation method D = alpha * Reduction(A) + beta * C
template<typename BatchedReductionTraits_ >
template<typename BatchedReductionTraits_ >
The documentation for this struct was generated from the following file: