Invoker Struct Reference

Invoker Struct Reference#

Composable Kernel: ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Invoker Struct Reference
Public Member Functions | List of all members
ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Invoker Struct Reference

#include <device_reduce_threadwise.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Invoker:
ck::tensor_operation::device::BaseInvoker

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 InDataType, typename AccDataType, typename OutDataType, index_t Rank, index_t NumReduceDim, typename ReduceOperation, typename InElementwiseOperation, typename AccElementwiseOperation, bool PropagateNan, bool OutputIndex, bool TransformIndexKtoGlobal, bool HaveIndexInputIfOutputIndex, index_t BlockSize, index_t MThreadSliceSize, index_t KThreadSliceSize, index_t InSrcVectorDim, index_t InSrcVectorSize, index_t OutDstVectorSize>
float ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::Invoker::Run ( const Argument & arg,
const StreamConfig & stream_config = StreamConfig{} )
inline

◆ Run() [2/2]

template<typename InDataType, typename AccDataType, typename OutDataType, index_t Rank, index_t NumReduceDim, typename ReduceOperation, typename InElementwiseOperation, typename AccElementwiseOperation, bool PropagateNan, bool OutputIndex, bool TransformIndexKtoGlobal, bool HaveIndexInputIfOutputIndex, index_t BlockSize, index_t MThreadSliceSize, index_t KThreadSliceSize, index_t InSrcVectorDim, index_t InSrcVectorSize, index_t OutDstVectorSize>
float ck::tensor_operation::device::DeviceReduceThreadWise< InDataType, AccDataType, OutDataType, Rank, NumReduceDim, ReduceOperation, InElementwiseOperation, AccElementwiseOperation, PropagateNan, OutputIndex, TransformIndexKtoGlobal, HaveIndexInputIfOutputIndex, BlockSize, MThreadSliceSize, KThreadSliceSize, InSrcVectorDim, InSrcVectorSize, OutDstVectorSize >::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: