DeviceBatchedGemmEPermute< ALayout, BLayout, DELayout, ADataType, BDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation > Struct Template Reference

• ck
• tensor_operation
• device
• DeviceBatchedGemmEPermute

Public Member Functions | List of all members

ck::tensor_operation::device::DeviceBatchedGemmEPermute< ALayout, BLayout, DELayout, ADataType, BDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation > Struct Template Referenceabstract

#include <device_batched_gemm_e_permute.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceBatchedGemmEPermute< ALayout, BLayout, DELayout, ADataType, BDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >:

Public Member Functions
virtual std::unique_ptr< BaseArgument >	MakeArgumentPointer (const void *p_a, const void *p_b, void *p_e, index_t M, index_t N, index_t K, index_t stride_A, index_t stride_B, index_t batch_stride_A, index_t batch_stride_B, BatchedGemmEPermuteDesc batched_gemm_e_permute_desc, index_t BatchCount, 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 ()

Member Function Documentation

◆ MakeArgumentPointer()

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename EDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation>

virtual std::unique_ptr< BaseArgument > ck::tensor_operation::device::DeviceBatchedGemmEPermute< ALayout, BLayout, DELayout, ADataType, BDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >::MakeArgumentPointer ( const void * p_a, const void * p_b, void * p_e, index_t M, index_t N, index_t K, index_t stride_A, index_t stride_B, index_t batch_stride_A, index_t batch_stride_B, BatchedGemmEPermuteDesc batched_gemm_e_permute_desc, index_t BatchCount, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CDEElementwiseOperation cde_element_op )

pure virtual

Implemented in ck::tensor_operation::device::DeviceBatchedGemmEPermuteXdl< ALayout, BLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >.

◆ MakeInvokerPointer()

template<typename ALayout, typename BLayout, typename DELayout, typename ADataType, typename BDataType, typename EDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation>

virtual std::unique_ptr< BaseInvoker > ck::tensor_operation::device::DeviceBatchedGemmEPermute< ALayout, BLayout, DELayout, ADataType, BDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >::MakeInvokerPointer ( )

pure virtual

Implemented in ck::tensor_operation::device::DeviceBatchedGemmEPermuteXdl< ALayout, BLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation, GemmSpec, NumPrefetch, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsExtraN, CShuffleMXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock, LoopSched >.

---

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

• device_batched_gemm_e_permute.hpp