Skip to content

Struct TempLat::device_kokkos::KokkosNDLambdaWrapper

template <size_t NDim, typename FUN>

ClassList > TempLat > device_kokkos > KokkosNDLambdaWrapper

This is a functor which wraps a lambda. Basically, this is necessary when one wants to call a variadic lambda on an NVIDIA GPU. CUDA seems to be unable to expand the variadic arguments - in contrast, a direct approach does indeed work for openMP or serial compilation. To get around this limitation, the KokkosNDLambdaWrapper packs the indices into an array. If you wonder, whether there's a difference when using tie and tuples:https://godbolt.org/z/M3bG39rsM No. Therefore, we spare the ourselves the hassle and simply use an array.More...

  • #include <kokkos_internal.h>

Public Attributes

Type Name
FUN fun

Public Functions

Type Name
KokkosNDLambdaWrapper (const FUN & _fun)
DEVICE_INLINE_FUNCTION void operator() (const Args &... args) const

Detailed Description

Template parameters:

  • NDim Number of arguments taken
  • FUN The lambda to which we forward the indices

Public Attributes Documentation

variable fun

FUN TempLat::device_kokkos::KokkosNDLambdaWrapper< NDim, FUN >::fun;

Public Functions Documentation

function KokkosNDLambdaWrapper

inline TempLat::device_kokkos::KokkosNDLambdaWrapper::KokkosNDLambdaWrapper (
    const FUN & _fun
)

function operator()

template<typename... Args>
inline DEVICE_INLINE_FUNCTION void TempLat::device_kokkos::KokkosNDLambdaWrapper::operator() (
    const Args &... args
) const

The documentation for this class was generated from the following file cosmolatticeweb/tmp/code_source/templat/include/TempLat/parallel/devices/kokkos/kokkos_internal.h