Composable Kernel: ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize >::Invoker Struct Reference

Invoker Struct Reference

Invoker Struct Reference#

Composable Kernel: ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize >::Invoker Struct Reference

Public Member Functions | List of all members

ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize >::Invoker Struct Reference

#include <device_normalization_bwd_data_impl.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize >::Invoker:

Public Member Functions
auto	KernelSelector (bool isSweepOnce)
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 Function Documentation

◆ KernelSelector()

template<typename DYDataType, typename XDataType, typename GammaDataType, typename MeanInvStdDataType, typename ComputeDataType, typename DXDataType, index_t Rank, index_t NumReduceDim, index_t BlockSize, index_t MThreadClusterSize, index_t KThreadClusterSize, index_t MThreadSliceSize, index_t KThreadSliceSize, bool IsDYFastestDimReduced, index_t DYSrcVectorSize, bool IsXFastestDimReduced, index_t XSrcVectorSize, bool IsGammaFastestDimReduced, index_t GammaSrcVectorSize, bool IsMeanInvStdFastestDimReduced, index_t MeanInvStdSrcVectorSize, bool IsDxFastestDimReduced, index_t DXDstVectorSize>

auto ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize >::Invoker::KernelSelector ( bool isSweepOnce )

inline

◆ Run() [1/2]

template<typename DYDataType, typename XDataType, typename GammaDataType, typename MeanInvStdDataType, typename ComputeDataType, typename DXDataType, index_t Rank, index_t NumReduceDim, index_t BlockSize, index_t MThreadClusterSize, index_t KThreadClusterSize, index_t MThreadSliceSize, index_t KThreadSliceSize, bool IsDYFastestDimReduced, index_t DYSrcVectorSize, bool IsXFastestDimReduced, index_t XSrcVectorSize, bool IsGammaFastestDimReduced, index_t GammaSrcVectorSize, bool IsMeanInvStdFastestDimReduced, index_t MeanInvStdSrcVectorSize, bool IsDxFastestDimReduced, index_t DXDstVectorSize>

float ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize >::Invoker::Run	(	const Argument &	arg,
		const StreamConfig &	stream_config = StreamConfig{} )

inline

◆ Run() [2/2]

template<typename DYDataType, typename XDataType, typename GammaDataType, typename MeanInvStdDataType, typename ComputeDataType, typename DXDataType, index_t Rank, index_t NumReduceDim, index_t BlockSize, index_t MThreadClusterSize, index_t KThreadClusterSize, index_t MThreadSliceSize, index_t KThreadSliceSize, bool IsDYFastestDimReduced, index_t DYSrcVectorSize, bool IsXFastestDimReduced, index_t XSrcVectorSize, bool IsGammaFastestDimReduced, index_t GammaSrcVectorSize, bool IsMeanInvStdFastestDimReduced, index_t MeanInvStdSrcVectorSize, bool IsDxFastestDimReduced, index_t DXDstVectorSize>

float ck::tensor_operation::device::DeviceNormalizationBwdDataImpl< DYDataType, XDataType, GammaDataType, MeanInvStdDataType, ComputeDataType, DXDataType, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, IsDYFastestDimReduced, DYSrcVectorSize, IsXFastestDimReduced, XSrcVectorSize, IsGammaFastestDimReduced, GammaSrcVectorSize, IsMeanInvStdFastestDimReduced, MeanInvStdSrcVectorSize, IsDxFastestDimReduced, DXDstVectorSize >::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_normalization_bwd_data_impl.hpp