CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
Classes | Namespaces | Functions
device/kernel/tensor_foreach.h File Reference
#include "cutlass/cutlass.h"
#include "cutlass/coord.h"
Include dependency graph for device/kernel/tensor_foreach.h:
This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes

struct  cutlass::reference::device::kernel::detail::TensorForEachHelper< Func, Rank, RankRemaining >
 Helper to perform for-each operation. More...
 
struct  cutlass::reference::device::kernel::detail::TensorForEachHelper< Func, Rank, 0 >
 Helper to perform for-each operation. More...
 

Namespaces

 cutlass
 
 cutlass::reference
 
 cutlass::reference::device
 
 cutlass::reference::device::kernel
 
 cutlass::reference::device::kernel::detail
 Defines several helpers.
 

Functions

template<typename Func , int Rank, typename Params >
__global__ void cutlass::reference::device::kernel::TensorForEach (Coord< Rank > size, Params params=Params())
 Kernel calls a functor for each element in a tensor's index space. More...
 
template<typename Func , int Rank, typename Params >
__global__ void cutlass::reference::device::kernel::TensorDiagonalForEach (Coord< Rank > size, Params params, int start, int end)
 Kernel calls a functor for each element along a tensor's diagonal. More...
 
template<typename Element , typename Func >
__global__ void cutlass::reference::device::kernel::BlockForEach (Element *ptr, size_t capacity, typename Func::Params params)