DeviceBatchedContractionMultipleD< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation > Struct Template Reference

DeviceBatchedContractionMultipleD&lt; NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation &gt; Struct Template Reference#

Composable Kernel: ck::tensor_operation::device::DeviceBatchedContractionMultipleD< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation > Struct Template Reference
Public Member Functions | Static Public Attributes | List of all members
ck::tensor_operation::device::DeviceBatchedContractionMultipleD< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation > Struct Template Referenceabstract

#include <device_batched_contraction_multiple_d.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceBatchedContractionMultipleD< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >:
ck::tensor_operation::device::BaseOperator ck::tensor_operation::device::DeviceBatchedContractionMultipleD_Wmma_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CDEShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer > ck::tensor_operation::device::DeviceBatchedContractionMultipleD_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >

Public Member Functions

virtual std::unique_ptr< BaseArgument > MakeArgumentPointer (const void *p_a, const void *p_b, std::array< const void *, NumDTensor > p_ds, void *p_e, const std::vector< index_t > &a_gs_ms_ns_lengths, const std::vector< index_t > &a_gs_ms_ks_strides, const std::vector< index_t > &b_gs_ns_ks_lengths, const std::vector< index_t > &b_gs_ns_ks_strides, const std::array< std::vector< index_t >, NumDTensor > &ds_gs_ms_ns_lengths, const std::array< std::vector< index_t >, NumDTensor > &ds_gs_ms_ns_strides, const std::vector< index_t > &e_gs_ms_ns_lengths, const std::vector< index_t > &e_gs_ms_ns_strides, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CDEElementwiseOperation cde_element_op)=0
virtual std::unique_ptr< BaseInvoker > MakeInvokerPointer ()=0
Public Member Functions inherited from ck::tensor_operation::device::BaseOperator
 BaseOperator ()=default
 BaseOperator (const BaseOperator &)=default
BaseOperator & operator= (const BaseOperator &)=default
virtual bool IsSupportedArgument (const BaseArgument *)
virtual std::string GetTypeString () const
virtual std::string GetInstanceString () const
virtual std::string GetTypeIdName () const
virtual std::optional< std::string > GetObjectName () const
virtual std::optional< std::string > GetTemplateInfo () const
virtual std::string GetTypeIdHashCode () const
virtual size_t GetWorkSpaceSize (const BaseArgument *) const
virtual void SetWorkSpacePointer (BaseArgument *p_arg, void *p_workspace, const StreamConfig &=StreamConfig{}) const
virtual ~BaseOperator ()

Static Public Attributes

static constexpr index_t NumDTensor = DsDataType::Size()

Member Function Documentation

◆ MakeArgumentPointer()

template<index_t NumDimG, index_t NumDimM, index_t NumDimN, index_t NumDimK, typename ADataType, typename BDataType, typename DsDataType, typename EDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation>
virtual std::unique_ptr< BaseArgument > ck::tensor_operation::device::DeviceBatchedContractionMultipleD< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >::MakeArgumentPointer ( const void * p_a,
const void * p_b,
std::array< const void *, NumDTensor > p_ds,
void * p_e,
const std::vector< index_t > & a_gs_ms_ns_lengths,
const std::vector< index_t > & a_gs_ms_ks_strides,
const std::vector< index_t > & b_gs_ns_ks_lengths,
const std::vector< index_t > & b_gs_ns_ks_strides,
const std::array< std::vector< index_t >, NumDTensor > & ds_gs_ms_ns_lengths,
const std::array< std::vector< index_t >, NumDTensor > & ds_gs_ms_ns_strides,
const std::vector< index_t > & e_gs_ms_ns_lengths,
const std::vector< index_t > & e_gs_ms_ns_strides,
AElementwiseOperation a_element_op,
BElementwiseOperation b_element_op,
CDEElementwiseOperation cde_element_op )
pure virtual

Implemented in ck::tensor_operation::device::DeviceBatchedContractionMultipleD_Wmma_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CDEShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer >, and ck::tensor_operation::device::DeviceBatchedContractionMultipleD_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >.

◆ MakeInvokerPointer()

template<index_t NumDimG, index_t NumDimM, index_t NumDimN, index_t NumDimK, typename ADataType, typename BDataType, typename DsDataType, typename EDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation>
virtual std::unique_ptr< BaseInvoker > ck::tensor_operation::device::DeviceBatchedContractionMultipleD< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >::MakeInvokerPointer ( )
pure virtual

Implemented in ck::tensor_operation::device::DeviceBatchedContractionMultipleD_Wmma_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, K1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CDEShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVector_NPerBlock, LoopSched, PipelineVer >, and ck::tensor_operation::device::DeviceBatchedContractionMultipleD_Xdl_CShuffle< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, ASpec, BSpec, DESpec, NumGemmKPrefetchStage, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >.

Member Data Documentation

◆ NumDTensor

template<index_t NumDimG, index_t NumDimM, index_t NumDimN, index_t NumDimK, typename ADataType, typename BDataType, typename DsDataType, typename EDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation>
index_t ck::tensor_operation::device::DeviceBatchedContractionMultipleD< NumDimG, NumDimM, NumDimN, NumDimK, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >::NumDTensor = DsDataType::Size()
staticconstexpr
The documentation for this struct was generated from the following file: