ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock > Struct Template Reference#
ck::ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock > Struct Template Reference
#include <epilogue_cshuffle_v3_reduce_wmma.hpp>
Public Types | |
| using | ReduceAccDataType_ = ReduceAccDataType |
| using | ReducePtrsGlobal_ = ReducePtrsGlobal |
| using | ReduceOperations_ = ReduceOperations |
| using | ReduceInElementwiseOperations_ = ReduceInElementwiseOperations |
| using | ReduceAccElementwiseOperations_ = ReduceAccElementwiseOperations |
| using | ReduceGlobalMemoryDataOperation_ = ReduceGlobalMemoryDataOperation |
| using | CReduceThreadClusterLengths_MPerBlock_NPerBlock_ = CReduceThreadClusterLengths_MPerBlock_NPerBlock |
Static Public Attributes | |
| static constexpr index_t | CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock_ |
| static constexpr index_t | CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock_ |
Member Typedef Documentation
◆ CReduceThreadClusterLengths_MPerBlock_NPerBlock_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
| using ck::ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock >::CReduceThreadClusterLengths_MPerBlock_NPerBlock_ = CReduceThreadClusterLengths_MPerBlock_NPerBlock |
◆ ReduceAccDataType_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
| using ck::ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock >::ReduceAccDataType_ = ReduceAccDataType |
◆ ReduceAccElementwiseOperations_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
| using ck::ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock >::ReduceAccElementwiseOperations_ = ReduceAccElementwiseOperations |
◆ ReduceGlobalMemoryDataOperation_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
| using ck::ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock >::ReduceGlobalMemoryDataOperation_ = ReduceGlobalMemoryDataOperation |
◆ ReduceInElementwiseOperations_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
| using ck::ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock >::ReduceInElementwiseOperations_ = ReduceInElementwiseOperations |
◆ ReduceOperations_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
| using ck::ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock >::ReduceOperations_ = ReduceOperations |
◆ ReducePtrsGlobal_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
| using ck::ReduceTrait_< ReduceAccDataType, ReducePtrsGlobal, ReduceOperations, ReduceInElementwiseOperations, ReduceAccElementwiseOperations, ReduceGlobalMemoryDataOperation, CReduceThreadClusterLengths_MPerBlock_NPerBlock, CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock >::ReducePtrsGlobal_ = ReducePtrsGlobal |
Member Data Documentation
◆ CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
|
staticconstexpr |
Initial value:
=
CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock
◆ CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock_
template<typename ReduceAccDataType , typename ReducePtrsGlobal , typename ReduceOperations , typename ReduceInElementwiseOperations , typename ReduceAccElementwiseOperations , typename ReduceGlobalMemoryDataOperation , typename CReduceThreadClusterLengths_MPerBlock_NPerBlock , index_t CReduceThreadLds2VGprCopySrcDstScalarPerVector_NPerBlock, index_t CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock>
|
staticconstexpr |
Initial value:
=
CReduceThreadVgpr2GlobalCopySrcDstScalarPerVector_MPerBlock
The documentation for this struct was generated from the following file:
- /home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/develop/include/ck/tensor_operation/gpu/grid/epilogue_cshuffle_v3_reduce_wmma.hpp