docs/structcutlass_1_1reduction_1_1BatchedReduction.html
| | CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers |
Public Types | Public Member Functions | Static Public Member Functions | Public Attributes | List of all members
cutlass::reduction::BatchedReduction< BatchedReductionTraits_ > Struct Template Reference
#include <batched_reduction.h>
|
|
| typedef BatchedReduction< BatchedReductionTraits_ > | This_ |
| | This class. More...
|
| |
| typedef BatchedReductionTraits_ | Traits |
| | The traits. More...
|
| |
| typedef Traits::Params | Params |
| | Params. More...
|
| |
| typedef Traits::Functor | Functor |
| | functor More...
|
| |
|
|
| 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) |
| |
|
|
| static __host__ cudaError_t | launch (Params const ¶ms, cudaStream_t stream=cudaStreamDefault) |
| | Launch the kernel. More...
|
| |
|
|
| Params const & | params |
| | The params. More...
|
| |
| Functor | functor |
| |
template<typename BatchedReductionTraits_ >
| typedef Traits::Functor cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::Functor |
template<typename BatchedReductionTraits_ >
| typedef Traits::Params cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::Params |
template<typename BatchedReductionTraits_ >
| typedef BatchedReduction<BatchedReductionTraits_> cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::This_ |
template<typename BatchedReductionTraits_ >
| typedef BatchedReductionTraits_ cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::Traits |
template<typename BatchedReductionTraits_ >
|
| CUTLASS_DEVICE cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::BatchedReduction | ( | Params const & | params_ | ) | |
| inline |
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_ >
|
| static __host__ cudaError_t cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::launch | ( | Params const & | params, |
| | | cudaStream_t | stream = cudaStreamDefault |
| | ) | | |
| inlinestatic |
template<typename BatchedReductionTraits_ >
|
| CUTLASS_DEVICE void cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::run | ( | | ) | |
| inline |
main operation method D = alpha * Reduction(A) + beta * C
template<typename BatchedReductionTraits_ >
| Functor cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::functor |
template<typename BatchedReductionTraits_ >
| Params const& cutlass::reduction::BatchedReduction< BatchedReductionTraits_ >::params |
The documentation for this struct was generated from the following file:
Generated by 1.8.11