Composable Kernel: ck::tensor_operation::device::DeviceBatchNormBwdImpl< XDataType, DxDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize >::Invoker Struct Reference

Invoker Struct Reference

Invoker Struct Reference#

Composable Kernel: ck::tensor_operation::device::DeviceBatchNormBwdImpl< XDataType, DxDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize >::Invoker Struct Reference

Public Member Functions | List of all members

ck::tensor_operation::device::DeviceBatchNormBwdImpl< XDataType, DxDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize >::Invoker Struct Reference

#include <device_batchnorm_backward_impl.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceBatchNormBwdImpl< XDataType, DxDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize >::Invoker:

Public Member Functions
float	Run (const Argument &arg, const StreamConfig &stream_config=StreamConfig{})

float	Run (const BaseArgument *pArg, 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 DxDataType , typename DyDataType , typename AccDataType , typename ScaleDataType , typename DscaleDbiasDataType , typename MeanVarDataType , typename DyElementwiseOp , index_t Rank, index_t NumBatchNormReduceDim, bool UseMultiblockInK, index_t BlockSize, index_t MThreadClusterSize, index_t KThreadClusterSize, index_t MThreadSliceSize, index_t KThreadSliceSize, index_t XDyDxVectorDim, index_t XSrcVectorSize, index_t DySrcVectorSize, index_t DxDstVectorSize, index_t ScaleSrcVectorSize, index_t DscaleDbiasDstVectorSize, index_t MeanVarSrcVectorSize>

float ck::tensor_operation::device::DeviceBatchNormBwdImpl< XDataType, DxDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize >::Invoker::Run	(	const Argument &	arg,
		const StreamConfig &	stream_config = `StreamConfig{}`
	)

inline

◆ Run() [2/2]

template<typename XDataType , typename DxDataType , typename DyDataType , typename AccDataType , typename ScaleDataType , typename DscaleDbiasDataType , typename MeanVarDataType , typename DyElementwiseOp , index_t Rank, index_t NumBatchNormReduceDim, bool UseMultiblockInK, index_t BlockSize, index_t MThreadClusterSize, index_t KThreadClusterSize, index_t MThreadSliceSize, index_t KThreadSliceSize, index_t XDyDxVectorDim, index_t XSrcVectorSize, index_t DySrcVectorSize, index_t DxDstVectorSize, index_t ScaleSrcVectorSize, index_t DscaleDbiasDstVectorSize, index_t MeanVarSrcVectorSize>

float ck::tensor_operation::device::DeviceBatchNormBwdImpl< XDataType, DxDataType, DyDataType, AccDataType, ScaleDataType, DscaleDbiasDataType, MeanVarDataType, DyElementwiseOp, Rank, NumBatchNormReduceDim, UseMultiblockInK, BlockSize, MThreadClusterSize, KThreadClusterSize, MThreadSliceSize, KThreadSliceSize, XDyDxVectorDim, XSrcVectorSize, DySrcVectorSize, DxDstVectorSize, ScaleSrcVectorSize, DscaleDbiasDstVectorSize, MeanVarSrcVectorSize >::Invoker::Run	(	const BaseArgument *	pArg,
		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-7.1.0/include/ck/tensor_operation/gpu/device/impl/device_batchnorm_backward_impl.hpp