Composable Kernel: ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument Struct Reference

Argument Struct Reference

Argument Struct Reference#

Composable Kernel: ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument Struct Reference

Public Member Functions | Public Attributes | List of all members

ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument Struct Reference

#include <device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument:

Public Member Functions
	Argument (const void p_a_grid, const void p_b_grid, std::array< const void , NumDTensor > p_ds_grid, void p_e_grid, std::array< void *, NumRTensor > p_rs_grid, index_t MRaw, index_t NRaw, index_t KRaw, index_t StrideA, index_t StrideB, std::array< index_t, NumDTensor > StrideDs, index_t StrideE, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CDEElementwiseOperation cde_element_op, QsElementwiseOperation qs_element_op, RsElementwiseOperation rs_element_op)
Public Member Functions inherited from ck::tensor_operation::device::BaseArgument
	BaseArgument ()=default
	BaseArgument (const BaseArgument &)=default
BaseArgument &	operator= (const BaseArgument &)=default
virtual	~BaseArgument ()

Public Attributes
const ADataType *	p_a_grid_
const BDataType *	p_b_grid_
GridwiseGemm64::DsGridPointer	p_ds_grid_
EDataType *	p_e_grid_
GridwiseGemm64::RsGridPointer	p_rs_grid_
index_t	MRaw_
index_t	NRaw_
std::array< index_t, NumDTensor >	stride_ds_
AGridDesc_M_K	a_grid_desc_m_k_
BGridDesc_N_K	b_grid_desc_n_k_
EGridDesc_M_N	e_grid_desc_m_n_
RGridDesc_M	r_grid_desc_m_
AGridDesc_AK0_M_AK1	a_grid_desc_ak0_m_ak1_
BGridDesc_BK0_N_BK1	b_grid_desc_bk0_n_bk1_
Block2ETileMap	block_2_etile_map_
AElementwiseOperation	a_element_op_
BElementwiseOperation	b_element_op_
CDEElementwiseOperation	cde_element_op_
QsElementwiseOperation	qs_element_op_
RsElementwiseOperation	rs_element_op_
Public Attributes inherited from ck::tensor_operation::device::BaseArgument
void *	p_workspace_ = nullptr

Constructor & Destructor Documentation

◆ Argument()

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::Argument	(	const void *	p_a_grid,
		const void *	p_b_grid,
		std::array< const void *, NumDTensor >	p_ds_grid,
		void *	p_e_grid,
		std::array< void *, NumRTensor >	p_rs_grid,
		index_t	MRaw,
		index_t	NRaw,
		index_t	KRaw,
		index_t	StrideA,
		index_t	StrideB,
		std::array< index_t, NumDTensor >	StrideDs,
		index_t	StrideE,
		AElementwiseOperation	a_element_op,
		BElementwiseOperation	b_element_op,
		CDEElementwiseOperation	cde_element_op,
		QsElementwiseOperation	qs_element_op,
		RsElementwiseOperation	rs_element_op )

inline

Member Data Documentation

◆ a_element_op_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

AElementwiseOperation ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::a_element_op_

◆ a_grid_desc_ak0_m_ak1_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

AGridDesc_AK0_M_AK1 ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::a_grid_desc_ak0_m_ak1_

◆ a_grid_desc_m_k_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

AGridDesc_M_K ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::a_grid_desc_m_k_

◆ b_element_op_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

BElementwiseOperation ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::b_element_op_

◆ b_grid_desc_bk0_n_bk1_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

BGridDesc_BK0_N_BK1 ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::b_grid_desc_bk0_n_bk1_

◆ b_grid_desc_n_k_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

BGridDesc_N_K ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::b_grid_desc_n_k_

◆ block_2_etile_map_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

Block2ETileMap ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::block_2_etile_map_

◆ cde_element_op_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

CDEElementwiseOperation ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::cde_element_op_

◆ e_grid_desc_m_n_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

EGridDesc_M_N ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::e_grid_desc_m_n_

◆ MRaw_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

index_t ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::MRaw_

◆ NRaw_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

index_t ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::NRaw_

◆ p_a_grid_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

const ADataType* ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::p_a_grid_

◆ p_b_grid_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

const BDataType* ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::p_b_grid_

◆ p_ds_grid_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

GridwiseGemm64::DsGridPointer ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::p_ds_grid_

◆ p_e_grid_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

EDataType* ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::p_e_grid_

◆ p_rs_grid_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

GridwiseGemm64::RsGridPointer ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::p_rs_grid_

◆ qs_element_op_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

QsElementwiseOperation ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::qs_element_op_

◆ r_grid_desc_m_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

RGridDesc_M ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::r_grid_desc_m_

◆ rs_element_op_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

RsElementwiseOperation ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::rs_element_op_

◆ stride_ds_

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename GemmAccDataType, typename CShuffleDataType, typename DsDataType, typename EDataType, typename ReduceAccDataType, typename RsDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation, typename QsElementwiseOperation, typename RsElementwiseOperation, typename ThreadReduceOperations, typename RsGlobalMemoryDataOperation, GemmSpecialization GemmSpec, index_t NumGemmKPrefetchStage, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t KPerBlock, index_t AK1, index_t BK1, index_t MPerXDL, index_t NPerXDL, index_t MXdlPerWave, index_t NXdlPerWave, typename ABlockTransferThreadClusterLengths_AK0_M_AK1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_AK1, bool ABlockLdsExtraM, typename BBlockTransferThreadClusterLengths_BK0_N_BK1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_BK1, bool BBlockLdsExtraN, index_t CShuffleMXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle, typename CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, index_t CDEReduceThreadTransferScalarPerVector_NPerBlock, index_t RThreadTransferDstScalarPerVector_MPerBlock, LoopScheduler LoopSched = make_default_loop_scheduler()>

std::array<index_t, NumDTensor> ck::tensor_operation::device::DeviceGemmMultipleDMultipleR_Xdl_CShuffle< ALayout, BLayout, DELayout, ADataType, BDataType, GemmAccDataType, CShuffleDataType, DsDataType, EDataType, ReduceAccDataType, RsDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, QsElementwiseOperation, RsElementwiseOperation, ThreadReduceOperations, RsGlobalMemoryDataOperation, GemmSpec, 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, CDRThreadTransferClusterLengths_MPerBlock_NPerBlock, CDEReduceThreadTransferScalarPerVector_NPerBlock, RThreadTransferDstScalarPerVector_MPerBlock, LoopSched >::Argument::stride_ds_

The documentation for this struct was generated from the following file:

device_gemm_multiple_d_multiple_r_xdl_cshuffle.hpp