DeviceBatchedGemmV2MultiD< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation > Struct Template Reference

• ck
• tensor_operation
• device
• DeviceBatchedGemmV2MultiD

Public Member Functions | Static Public Attributes | List of all members

ck::tensor_operation::device::DeviceBatchedGemmV2MultiD< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation > Struct Template Referenceabstract

#include <device_batched_gemm_multi_d.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceBatchedGemmV2MultiD< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >:

Public Member Functions
virtual std::unique_ptr< BaseArgument >	MakeArgumentPointer (const void *p_a, const void *p_b, const std::array< const void *, NumDTensor > &p_ds, void *p_e, index_t M, index_t N, index_t K, index_t Batch, index_t StrideA, index_t StrideB, const std::array< ck::index_t, NumDTensor > &StrideDs, index_t StrideE, index_t BatchStrideA, index_t BatchStrideB, const std::array< ck::index_t, NumDTensor > &BatchStrideDs, index_t BatchStrideE, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CDEElementwiseOperation cde_element_op, index_t KBatch)=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<typename ALayout, typename BLayout, typename DsLayout, typename ELayout, typename ADataType, typename BDataType, typename DsDataType, typename EDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation>

virtual std::unique_ptr< BaseArgument > ck::tensor_operation::device::DeviceBatchedGemmV2MultiD< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >::MakeArgumentPointer ( const void * p_a, const void * p_b, const std::array< const void *, NumDTensor > & p_ds, void * p_e, index_t M, index_t N, index_t K, index_t Batch, index_t StrideA, index_t StrideB, const std::array< ck::index_t, NumDTensor > & StrideDs, index_t StrideE, index_t BatchStrideA, index_t BatchStrideB, const std::array< ck::index_t, NumDTensor > & BatchStrideDs, index_t BatchStrideE, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CDEElementwiseOperation cde_element_op, index_t KBatch )

pure virtual

Implemented in ck::tensor_operation::device::DeviceBatchedGemmMultiD_Xdl_CShuffle_V3< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >.

◆ MakeInvokerPointer()

template<typename ALayout, typename BLayout, typename DsLayout, typename ELayout, typename ADataType, typename BDataType, typename DsDataType, typename EDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation>

virtual std::unique_ptr< BaseInvoker > ck::tensor_operation::device::DeviceBatchedGemmV2MultiD< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >::MakeInvokerPointer ( )

pure virtual

Implemented in ck::tensor_operation::device::DeviceBatchedGemmMultiD_Xdl_CShuffle_V3< ALayout, BLayout, DsLayout, CLayout, ADataType, BDataType, DsDataType, CDataType, GemmAccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEShuffleBlockTransferScalarPerVectors, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, LDSTypeA, LDSTypeB >.

Member Data Documentation

◆ NumDTensor

template<typename ALayout, typename BLayout, typename DsLayout, typename ELayout, typename ADataType, typename BDataType, typename DsDataType, typename EDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CDEElementwiseOperation>

index_t ck::tensor_operation::device::DeviceBatchedGemmV2MultiD< ALayout, BLayout, DsLayout, ELayout, ADataType, BDataType, DsDataType, EDataType, AElementwiseOperation, BElementwiseOperation, CDEElementwiseOperation >::NumDTensor = DsDataType::Size()

staticconstexpr

---

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

• device_batched_gemm_multi_d.hpp