Back to Cutlass

CUTLASS: cutlass::layout::TensorCxRSKx< Interleave > Class Template Reference

docs/classcutlass_1_1layout_1_1TensorCxRSKx.html

4.4.29.4 KB
Original Source

| | CUTLASS

CUDA Templates for Linear Algebra Subroutines and Solvers |

Public Types | Public Member Functions | Static Public Member Functions | Static Public Attributes | List of all members

cutlass::layout::TensorCxRSKx< Interleave > Class Template Reference

Mapping function for 4-D CxRSKx tensors.

#include <tensor.h>

|

Public Types

| | using | Index = int32_t | | | Index type used for coordinates. More...
| | | | using | LongIndex = int64_t | | | Long index type used for offsets. More...
| | | | using | TensorCoord = Tensor4DCoord | | | Logical coordinate. More...
| | | | using | Stride = Coord< kStrideRank > | | | Stride vector. More...
| | |

|

Public Member Functions

| | CUTLASS_HOST_DEVICE | TensorCxRSKx (Stride const &stride=Stride(0)) | | | Constructor. More...
| | | | CUTLASS_HOST_DEVICE LongIndex | operator() (TensorCoord const &coord) const | | | Returns the offset of a coordinate in linear memory. More...
| | | | CUTLASS_HOST_DEVICE Stride | stride () const | | | Returns the stride of the layout. More...
| | | | CUTLASS_HOST_DEVICE Stride & | stride () | | | Returns the stride of the layout. More...
| | | | CUTLASS_HOST_DEVICE LongIndex | capacity (TensorCoord const &extent) const | | | Compute the number of contiguous elements needed to store a tensor with the given size. More...
| | |

|

Static Public Member Functions

| | static CUTLASS_HOST_DEVICE TensorCxRSKx | packed (TensorCoord const &extent) | | | Helper returns a layout to a tightly packed tensor. More...
| | |

|

Static Public Attributes

| | static int const | kInterleave = Interleave | | | Interleaving quantity. More...
| | | | static int const | kRank = 4 | | | Logical rank of tensor. More...
| | | | static int const | kStrideRank = 3 | | | Rank of stride vector. More...
| | |

Member Typedef Documentation

template<int Interleave>

| using cutlass::layout::TensorCxRSKx< Interleave >::Index = int32_t |

template<int Interleave>

| using cutlass::layout::TensorCxRSKx< Interleave >::LongIndex = int64_t |

template<int Interleave>

| using cutlass::layout::TensorCxRSKx< Interleave >::Stride = Coord<kStrideRank> |

template<int Interleave>

| using cutlass::layout::TensorCxRSKx< Interleave >::TensorCoord = Tensor4DCoord |

Constructor & Destructor Documentation

template<int Interleave>

|

| CUTLASS_HOST_DEVICE cutlass::layout::TensorCxRSKx< Interleave >::TensorCxRSKx | ( | Stride const & | stride = Stride(0) | ) | |

| inline |

Member Function Documentation

template<int Interleave>

|

| CUTLASS_HOST_DEVICE LongIndex cutlass::layout::TensorCxRSKx< Interleave >::capacity | ( | TensorCoord const & | extent | ) | const |

| inline |

template<int Interleave>

|

| CUTLASS_HOST_DEVICE LongIndex cutlass::layout::TensorCxRSKx< Interleave >::operator() | ( | TensorCoord const & | coord | ) | const |

| inline |

template<int Interleave>

|

| static CUTLASS_HOST_DEVICE TensorCxRSKx cutlass::layout::TensorCxRSKx< Interleave >::packed | ( | TensorCoord const & | extent | ) | |

| inlinestatic |

template<int Interleave>

|

| CUTLASS_HOST_DEVICE Stride cutlass::layout::TensorCxRSKx< Interleave >::stride | ( | | ) | const |

| inline |

template<int Interleave>

|

| CUTLASS_HOST_DEVICE Stride& cutlass::layout::TensorCxRSKx< Interleave >::stride | ( | | ) | |

| inline |

Member Data Documentation

template<int Interleave>

|

| int const cutlass::layout::TensorCxRSKx< Interleave >::kInterleave = Interleave |

| static |

template<int Interleave>

|

| int const cutlass::layout::TensorCxRSKx< Interleave >::kRank = 4 |

| static |

template<int Interleave>

|

| int const cutlass::layout::TensorCxRSKx< Interleave >::kStrideRank = 3 |

| static |


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


Generated by 1.8.11