Composable Kernel: ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker Struct Reference

Invoker Struct Reference

Invoker Struct Reference#

Composable Kernel: ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker Struct Reference

Public Types | Public Member Functions | List of all members

ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker Struct Reference

#include <device_grouped_conv_bwd_weight_wmma_cshuffle.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker:

Public Types
using	Argument = DeviceOp::Argument

Public Member Functions
void	Print (const Argument &arg)
float	Run (const Argument &arg, const StreamConfig &stream_config=StreamConfig{})
float	Run (const BaseArgument *p_arg, const StreamConfig &stream_config=StreamConfig{}) override
Public Member Functions inherited from ck::tensor_operation::device::BaseInvoker
	BaseInvoker ()=default
	BaseInvoker (const BaseInvoker &)=default
BaseInvoker &	operator= (const BaseInvoker &)=default
virtual	~BaseInvoker ()

Member Typedef Documentation

◆ Argument

template<index_t NDimSpatial, typename InLayout, typename WeiLayout, typename OutLayout, typename InDataType, typename WeiDataType, typename OutDataType, typename AccDataType, typename InElementwiseOperation, typename WeiElementwiseOperation, typename OutElementwiseOperation, ConvolutionBackwardWeightSpecialization ConvBackwardWeightSpecialization, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t K0PerBlock, index_t K1, index_t MPerWMMA, index_t NPerWMMA, index_t MRepeat, index_t NRepeat, typename ABlockTransferThreadClusterLengths_K0_M_K1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_K1, bool ABlockLdsAddExtraM, typename BBlockTransferThreadClusterLengths_K0_N_K1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_K1, bool BBlockLdsAddExtraN, index_t CShuffleMRepeatPerShuffle, index_t CShuffleNRepeatPerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, index_t CShuffleBlockTransferScalarPerVector_NPerBlock, index_t NumGemmKPrefetchStage = 1, LoopScheduler LoopSched = make_default_loop_scheduler(), ck::PipelineVersion PipelineVer = ck::PipelineVersion::v1, typename ck::enable_if< NDimSpatial==3, bool >::type = false>

using ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker::Argument = DeviceOp::Argument

Member Function Documentation

◆ Print()

template<index_t NDimSpatial, typename InLayout, typename WeiLayout, typename OutLayout, typename InDataType, typename WeiDataType, typename OutDataType, typename AccDataType, typename InElementwiseOperation, typename WeiElementwiseOperation, typename OutElementwiseOperation, ConvolutionBackwardWeightSpecialization ConvBackwardWeightSpecialization, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t K0PerBlock, index_t K1, index_t MPerWMMA, index_t NPerWMMA, index_t MRepeat, index_t NRepeat, typename ABlockTransferThreadClusterLengths_K0_M_K1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_K1, bool ABlockLdsAddExtraM, typename BBlockTransferThreadClusterLengths_K0_N_K1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_K1, bool BBlockLdsAddExtraN, index_t CShuffleMRepeatPerShuffle, index_t CShuffleNRepeatPerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, index_t CShuffleBlockTransferScalarPerVector_NPerBlock, index_t NumGemmKPrefetchStage = 1, LoopScheduler LoopSched = make_default_loop_scheduler(), ck::PipelineVersion PipelineVer = ck::PipelineVersion::v1, typename ck::enable_if< NDimSpatial==3, bool >::type = false>

void ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker::Print ( const Argument & arg )

inline

◆ Run() [1/2]

template<index_t NDimSpatial, typename InLayout, typename WeiLayout, typename OutLayout, typename InDataType, typename WeiDataType, typename OutDataType, typename AccDataType, typename InElementwiseOperation, typename WeiElementwiseOperation, typename OutElementwiseOperation, ConvolutionBackwardWeightSpecialization ConvBackwardWeightSpecialization, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t K0PerBlock, index_t K1, index_t MPerWMMA, index_t NPerWMMA, index_t MRepeat, index_t NRepeat, typename ABlockTransferThreadClusterLengths_K0_M_K1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_K1, bool ABlockLdsAddExtraM, typename BBlockTransferThreadClusterLengths_K0_N_K1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_K1, bool BBlockLdsAddExtraN, index_t CShuffleMRepeatPerShuffle, index_t CShuffleNRepeatPerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, index_t CShuffleBlockTransferScalarPerVector_NPerBlock, index_t NumGemmKPrefetchStage = 1, LoopScheduler LoopSched = make_default_loop_scheduler(), ck::PipelineVersion PipelineVer = ck::PipelineVersion::v1, typename ck::enable_if< NDimSpatial==3, bool >::type = false>

float ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker::Run	(	const Argument &	arg,
		const StreamConfig &	stream_config = StreamConfig{} )

inline

◆ Run() [2/2]

template<index_t NDimSpatial, typename InLayout, typename WeiLayout, typename OutLayout, typename InDataType, typename WeiDataType, typename OutDataType, typename AccDataType, typename InElementwiseOperation, typename WeiElementwiseOperation, typename OutElementwiseOperation, ConvolutionBackwardWeightSpecialization ConvBackwardWeightSpecialization, index_t BlockSize, index_t MPerBlock, index_t NPerBlock, index_t K0PerBlock, index_t K1, index_t MPerWMMA, index_t NPerWMMA, index_t MRepeat, index_t NRepeat, typename ABlockTransferThreadClusterLengths_K0_M_K1, typename ABlockTransferThreadClusterArrangeOrder, typename ABlockTransferSrcAccessOrder, index_t ABlockTransferSrcVectorDim, index_t ABlockTransferSrcScalarPerVector, index_t ABlockTransferDstScalarPerVector_K1, bool ABlockLdsAddExtraM, typename BBlockTransferThreadClusterLengths_K0_N_K1, typename BBlockTransferThreadClusterArrangeOrder, typename BBlockTransferSrcAccessOrder, index_t BBlockTransferSrcVectorDim, index_t BBlockTransferSrcScalarPerVector, index_t BBlockTransferDstScalarPerVector_K1, bool BBlockLdsAddExtraN, index_t CShuffleMRepeatPerShuffle, index_t CShuffleNRepeatPerShuffle, typename CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, index_t CShuffleBlockTransferScalarPerVector_NPerBlock, index_t NumGemmKPrefetchStage = 1, LoopScheduler LoopSched = make_default_loop_scheduler(), ck::PipelineVersion PipelineVer = ck::PipelineVersion::v1, typename ck::enable_if< NDimSpatial==3, bool >::type = false>

float ck::tensor_operation::device::DeviceGroupedConvBwdWeight_Wmma_CShuffle< NDimSpatial, InLayout, WeiLayout, OutLayout, InDataType, WeiDataType, OutDataType, AccDataType, InElementwiseOperation, WeiElementwiseOperation, OutElementwiseOperation, ConvBackwardWeightSpecialization, BlockSize, MPerBlock, NPerBlock, K0PerBlock, 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, CShuffleBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CShuffleBlockTransferScalarPerVector_NPerBlock, NumGemmKPrefetchStage, LoopSched, PipelineVer, type >::Invoker::Run	(	const BaseArgument *	p_arg,
		const StreamConfig &	stream_config = StreamConfig{} )

inlineoverridevirtual

Reimplemented from ck::tensor_operation::device::BaseInvoker.

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

device_grouped_conv_bwd_weight_wmma_cshuffle.hpp