alpaka
Abstraction Library for Parallel Kernel Acceleration
|
The GPU CUDA/HIP accelerator execution task. More...
#include <TaskKernelGpuUniformCudaHipRt.hpp>
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 |
The GPU CUDA/HIP accelerator execution task.
Definition at line 121 of file TaskKernelGpuUniformCudaHipRt.hpp.
|
inline |
Definition at line 125 of file TaskKernelGpuUniformCudaHipRt.hpp.
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.
TKernelFnObj alpaka::TaskKernelGpuUniformCudaHipRt< TApi, TAcc, TDim, TIdx, TKernelFnObj, TArgs >::m_kernelFnObj |
Definition at line 138 of file TaskKernelGpuUniformCudaHipRt.hpp.