Invoker Struct Reference

Invoker Struct Reference#

Composable Kernel: ck::tensor_operation::device::DeviceElementwiseImpl< InDataTypeTuple, OutDataTypeTuple, ElementwiseOperation, NumDim, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq >::Invoker Struct Reference
Public Member Functions | List of all members
ck::tensor_operation::device::DeviceElementwiseImpl< InDataTypeTuple, OutDataTypeTuple, ElementwiseOperation, NumDim, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq >::Invoker Struct Reference

#include <device_elementwise_dynamic_vector_dims_impl.hpp>

Inheritance diagram for ck::tensor_operation::device::DeviceElementwiseImpl< InDataTypeTuple, OutDataTypeTuple, ElementwiseOperation, NumDim, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq >::Invoker:
ck::tensor_operation::device::BaseInvoker 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
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() [1/4]

template<typename InDataTypeTuple, typename OutDataTypeTuple, typename ElementwiseOperation, index_t NumDim, index_t BlockSize, index_t M0PerBlock, index_t M1PerBlock, index_t M0PerThread, index_t M1PerThread, typename ThreadClusterArrangeOrder, typename InScalarPerVectorSeq, typename OutScalarPerVectorSeq>
float ck::tensor_operation::device::DeviceElementwiseImpl< InDataTypeTuple, OutDataTypeTuple, ElementwiseOperation, NumDim, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq >::Invoker::Run ( const Argument & arg,
const StreamConfig & stream_config = StreamConfig{} )
inline

◆ Run() [2/4]

template<typename InDataTypeTuple, typename OutDataTypeTuple, typename ElementwiseOperation, index_t NumDim, index_t BlockSize, index_t M0PerBlock, index_t M1PerBlock, index_t M0PerThread, index_t M1PerThread, typename ThreadClusterArrangeOrder, typename InScalarPerVectorSeq, typename OutScalarPerVectorSeq>
float ck::tensor_operation::device::DeviceElementwiseImpl< InDataTypeTuple, OutDataTypeTuple, ElementwiseOperation, NumDim, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq >::Invoker::Run ( const Argument & arg,
const StreamConfig & stream_config = StreamConfig{} )
inline

◆ Run() [3/4]

template<typename InDataTypeTuple, typename OutDataTypeTuple, typename ElementwiseOperation, index_t NumDim, index_t BlockSize, index_t M0PerBlock, index_t M1PerBlock, index_t M0PerThread, index_t M1PerThread, typename ThreadClusterArrangeOrder, typename InScalarPerVectorSeq, typename OutScalarPerVectorSeq>
float ck::tensor_operation::device::DeviceElementwiseImpl< InDataTypeTuple, OutDataTypeTuple, ElementwiseOperation, NumDim, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq >::Invoker::Run ( const BaseArgument * p_arg,
const StreamConfig & stream_config = StreamConfig{} )
inlineoverridevirtual

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

◆ Run() [4/4]

template<typename InDataTypeTuple, typename OutDataTypeTuple, typename ElementwiseOperation, index_t NumDim, index_t BlockSize, index_t M0PerBlock, index_t M1PerBlock, index_t M0PerThread, index_t M1PerThread, typename ThreadClusterArrangeOrder, typename InScalarPerVectorSeq, typename OutScalarPerVectorSeq>
float ck::tensor_operation::device::DeviceElementwiseImpl< InDataTypeTuple, OutDataTypeTuple, ElementwiseOperation, NumDim, BlockSize, M0PerBlock, M1PerBlock, M0PerThread, M1PerThread, ThreadClusterArrangeOrder, InScalarPerVectorSeq, OutScalarPerVectorSeq >::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 files: