DeviceBatchedGemm< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation > Struct Template Reference

• ck
• tensor_operation
• device
• DeviceBatchedGemm

Public Member Functions | List of all members

ck::tensor_operation::device::DeviceBatchedGemm< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation > Struct Template Referenceabstract

#include <device_batched_gemm.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceBatchedGemm< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation >:

Public Member Functions
virtual std::unique_ptr< BaseArgument >	MakeArgumentPointer (const void *p_a, const void *p_b, void *p_c, ck::index_t M, ck::index_t N, ck::index_t K, ck::index_t StrideA, ck::index_t StrideB, ck::index_t StrideC, ck::index_t BatchStrideA, ck::index_t BatchStrideB, ck::index_t BatchStrideC, ck::index_t Batch, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CElementwiseOperation c_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 CLayout, typename ADataType, typename BDataType, typename CDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation>

virtual std::unique_ptr< BaseArgument > ck::tensor_operation::device::DeviceBatchedGemm< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation >::MakeArgumentPointer ( const void * p_a, const void * p_b, void * p_c, ck::index_t M, ck::index_t N, ck::index_t K, ck::index_t StrideA, ck::index_t StrideB, ck::index_t StrideC, ck::index_t BatchStrideA, ck::index_t BatchStrideB, ck::index_t BatchStrideC, ck::index_t Batch, AElementwiseOperation a_element_op, BElementwiseOperation b_element_op, CElementwiseOperation c_element_op )

pure virtual

Implemented in ck::tensor_operation::device::DeviceBatchedGemm_Wmma_CShuffleV3< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, PermuteA, PermuteB >, and ck::tensor_operation::device::DeviceBatchedGemmXdl< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, NumGemmKPrefetchStage, LoopSched, PipelineVer >.

◆ MakeInvokerPointer()

template<typename ALayout, typename BLayout, typename CLayout, typename ADataType, typename BDataType, typename CDataType, typename AElementwiseOperation, typename BElementwiseOperation, typename CElementwiseOperation>

virtual std::unique_ptr< BaseInvoker > ck::tensor_operation::device::DeviceBatchedGemm< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation >::MakeInvokerPointer ( )

pure virtual

Implemented in ck::tensor_operation::device::DeviceBatchedGemm_Wmma_CShuffleV3< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, CShuffleDataType, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, GemmSpec, BlockSize, MPerBlock, NPerBlock, KPerBlock, AK1, BK1, MPerWmma, NPerWmma, MRepeat, NRepeat, ABlockTransferThreadClusterLengths_AK0_M_AK1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_AK1, ABlockLdsExtraM, BBlockTransferThreadClusterLengths_BK0_N_BK1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_BK1, BBlockLdsExtraN, CShuffleMRepeatPerShuffle, CShuffleNRepeatPerShuffle, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, BlkGemmPipeSched, BlkGemmPipelineVer, ComputeTypeA, ComputeTypeB, PermuteA, PermuteB >, and ck::tensor_operation::device::DeviceBatchedGemmXdl< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementwiseOperation, BElementwiseOperation, CElementwiseOperation, BlockSize, MPerBlock, NPerBlock, K0PerBlock, K1, MPerXDL, NPerXDL, MXdlPerWave, NXdlPerWave, ABlockTransferThreadClusterLengths_K0_M_K1, ABlockTransferThreadClusterArrangeOrder, ABlockTransferSrcAccessOrder, ABlockTransferSrcVectorDim, ABlockTransferSrcScalarPerVector, ABlockTransferDstScalarPerVector_K1, ABlockLdsAddExtraM, BBlockTransferThreadClusterLengths_K0_N_K1, BBlockTransferThreadClusterArrangeOrder, BBlockTransferSrcAccessOrder, BBlockTransferSrcVectorDim, BBlockTransferSrcScalarPerVector, BBlockTransferDstScalarPerVector_K1, BBlockLdsAddExtraN, CThreadTransferSrcDstVectorDim, CThreadTransferDstScalarPerVector, NumGemmKPrefetchStage, LoopSched, PipelineVer >.

---

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

• device_batched_gemm.hpp