alpaka
Abstraction Library for Parallel Kernel Acceleration
alpaka::TaskKernelGpuUniformCudaHipRt< TApi, TAcc, TDim, TIdx, TKernelFnObj, TArgs > Class Template Reference

The GPU CUDA/HIP accelerator execution task. More...

#include <TaskKernelGpuUniformCudaHipRt.hpp>

+ Inheritance diagram for alpaka::TaskKernelGpuUniformCudaHipRt< TApi, TAcc, TDim, TIdx, TKernelFnObj, TArgs >:

Public Member Functions

template<typename TWorkDiv >
ALPAKA_FN_HOST TaskKernelGpuUniformCudaHipRt (TWorkDiv &&workDiv, TKernelFnObj const &kernelFnObj, TArgs &&... args)
 
- Public Member Functions inherited from alpaka::WorkDivMembers< TDim, TIdx >
ALPAKA_FN_HOST_ACC WorkDivMembers ()=delete
 
ALPAKA_NO_HOST_ACC_WARNING ALPAKA_FN_HOST_ACC WorkDivMembers (alpaka::Vec< TDim, TIdx > const &gridBlockExtent, alpaka::Vec< TDim, TIdx > const &blockThreadExtent, alpaka::Vec< TDim, TIdx > const &elemExtent)
 Accepts single specific type and is called without explicit template parameters. More...
 
template<typename TGridBlockExtent , typename TBlockThreadExtent , typename TThreadElemExtent >
ALPAKA_NO_HOST_ACC_WARNING ALPAKA_FN_HOST_ACC WorkDivMembers (TGridBlockExtent const &gridBlockExtent=TGridBlockExtent(), TBlockThreadExtent const &blockThreadExtent=TBlockThreadExtent(), TThreadElemExtent const &threadElemExtent=TThreadElemExtent())
 Accepts different alpaka vector types and takes the last TDim number of items. More...
 
template<typename TWorkDiv >
ALPAKA_NO_HOST_ACC_WARNING ALPAKA_FN_HOST_ACC WorkDivMembers (TWorkDiv const &other)
 
 WorkDivMembers (WorkDivMembers &&)=default
 
ALPAKA_NO_HOST_ACC_WARNING ALPAKA_FN_HOST_ACC WorkDivMembers (WorkDivMembers const &other)
 
template<typename TWorkDiv >
ALPAKA_NO_HOST_ACC_WARNING ALPAKA_FN_HOST_ACC auto operator= (TWorkDiv const &other) -> WorkDivMembers< TDim, TIdx > &
 
auto operator= (WorkDivMembers &&) -> WorkDivMembers &=default
 
auto operator= (WorkDivMembers const &) -> WorkDivMembers &=default
 

Public Attributes

std::tuple< remove_restrict_t< std::decay_t< TArgs > >... > m_args
 
TKernelFnObj m_kernelFnObj
 
- Public Attributes inherited from alpaka::WorkDivMembers< TDim, TIdx >
Vec< TDim, TIdx > m_blockThreadExtent
 
Vec< TDim, TIdx > m_gridBlockExtent
 
Vec< TDim, TIdx > m_threadElemExtent
 

Detailed Description

template<typename TApi, typename TAcc, typename TDim, typename TIdx, typename TKernelFnObj, typename... TArgs>
class alpaka::TaskKernelGpuUniformCudaHipRt< TApi, TAcc, TDim, TIdx, TKernelFnObj, TArgs >

The GPU CUDA/HIP accelerator execution task.

Definition at line 121 of file TaskKernelGpuUniformCudaHipRt.hpp.

Constructor & Destructor Documentation

◆ TaskKernelGpuUniformCudaHipRt()

template<typename TApi , typename TAcc , typename TDim , typename TIdx , typename TKernelFnObj , typename... TArgs>
template<typename TWorkDiv >
ALPAKA_FN_HOST alpaka::TaskKernelGpuUniformCudaHipRt< TApi, TAcc, TDim, TIdx, TKernelFnObj, TArgs >::TaskKernelGpuUniformCudaHipRt ( TWorkDiv &&  workDiv,
TKernelFnObj const &  kernelFnObj,
TArgs &&...  args 
)
inline

Definition at line 125 of file TaskKernelGpuUniformCudaHipRt.hpp.

Member Data Documentation

◆ m_args

template<typename TApi , typename TAcc , typename TDim , typename TIdx , typename TKernelFnObj , typename... TArgs>
std::tuple<remove_restrict_t<std::decay_t<TArgs> >...> alpaka::TaskKernelGpuUniformCudaHipRt< TApi, TAcc, TDim, TIdx, TKernelFnObj, TArgs >::m_args

Definition at line 139 of file TaskKernelGpuUniformCudaHipRt.hpp.

◆ m_kernelFnObj

template<typename TApi , typename TAcc , typename TDim , typename TIdx , typename TKernelFnObj , typename... TArgs>
TKernelFnObj alpaka::TaskKernelGpuUniformCudaHipRt< TApi, TAcc, TDim, TIdx, TKernelFnObj, TArgs >::m_kernelFnObj

Definition at line 138 of file TaskKernelGpuUniformCudaHipRt.hpp.


The documentation for this class was generated from the following files: