Composable Kernel: ck::tensor_operation::device::DeviceNormalizationFwdSplitKImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize >::Invoker Struct Reference

Invoker Struct Reference

Invoker Struct Reference#

Composable Kernel: ck::tensor_operation::device::DeviceNormalizationFwdSplitKImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize >::Invoker Struct Reference

Public Member Functions | List of all members

ck::tensor_operation::device::DeviceNormalizationFwdSplitKImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize >::Invoker Struct Reference

#include <device_normalization_fwd_splitk_impl.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceNormalizationFwdSplitKImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize >::Invoker:

Public Member Functions
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

◆ Run() [1/2]

template<typename XDataType , typename GammaDataType , typename BetaDataType , typename ComputeDataType , typename YDataType , typename SaveMeanInvStdDataType , typename YElementwiseOperation , index_t Rank, index_t NumReduceDim, index_t BlockSize, index_t MThreadClusterSize, index_t KThreadClusterSize, index_t MThreadSliceSize, index_t KThreadSliceSize, index_t XYVectorDim, index_t XSrcVectorSize, index_t GammaSrcVectorDim, index_t GammaSrcVectorSize, index_t BetaSrcVectorDim, index_t BetaSrcVectorSize, index_t YDstVectorSize, index_t SaveMeanInvStdDstVectorSize>

float ck::tensor_operation::device::DeviceNormalizationFwdSplitKImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize >::Invoker::Run	(	const Argument &	arg,
		const StreamConfig &	stream_config = `StreamConfig{}`
	)

inline

◆ Run() [2/2]

template<typename XDataType , typename GammaDataType , typename BetaDataType , typename ComputeDataType , typename YDataType , typename SaveMeanInvStdDataType , typename YElementwiseOperation , index_t Rank, index_t NumReduceDim, index_t BlockSize, index_t MThreadClusterSize, index_t KThreadClusterSize, index_t MThreadSliceSize, index_t KThreadSliceSize, index_t XYVectorDim, index_t XSrcVectorSize, index_t GammaSrcVectorDim, index_t GammaSrcVectorSize, index_t BetaSrcVectorDim, index_t BetaSrcVectorSize, index_t YDstVectorSize, index_t SaveMeanInvStdDstVectorSize>

float ck::tensor_operation::device::DeviceNormalizationFwdSplitKImpl< XDataType, GammaDataType, BetaDataType, ComputeDataType, YDataType, SaveMeanInvStdDataType, YElementwiseOperation, Rank, NumReduceDim, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XYVectorDim, XSrcVectorSize, GammaSrcVectorDim, GammaSrcVectorSize, BetaSrcVectorDim, BetaSrcVectorSize, YDstVectorSize, SaveMeanInvStdDstVectorSize >::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:

/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-composable-kernel/checkouts/docs-7.0.0/include/ck/tensor_operation/gpu/device/impl/device_normalization_fwd_splitk_impl.hpp