CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
Public Attributes | Static Public Attributes | List of all members
cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ >::AccessType Struct Reference

#include <predicated_tile_iterator_2dthreadtile.h>

Public Attributes

Array< Element, ThreadMap::kElementsPerAccess > storage
 

Static Public Attributes

static int const kElements = ThreadMap::kElementsPerAccess
 

Detailed Description

template<typename Shape_, typename Element_, int AdvanceRank, typename ThreadMap_, bool Transpose_>
struct cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ >::AccessType

Type used for internal memory accesses extra set of parenthesis is needed for VS compiler

Member Data Documentation

template<typename Shape_ , typename Element_ , int AdvanceRank, typename ThreadMap_ , bool Transpose_>
int const cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ >::AccessType::kElements = ThreadMap::kElementsPerAccess
static
template<typename Shape_ , typename Element_ , int AdvanceRank, typename ThreadMap_ , bool Transpose_>
Array<Element, ThreadMap::kElementsPerAccess> cutlass::transform::threadblock::PredicatedTileIterator2dThreadTile< Shape_, Element_, layout::PitchLinear, AdvanceRank, ThreadMap_, Transpose_ >::AccessType::storage

The documentation for this struct was generated from the following file: