|
Cutlass
CUDA Templates for Linear Algebra Subroutines and Solvers
|
#include <threadblock_swizzle.h>
Public Member Functions | |
| CUTLASS_HOST_DEVICE | IdentityBlockSwizzle () |
| Ctor. aka ColumnMajorBlockSwizzle<1> More... | |
| CUTLASS_DEVICE dim3 | swizzle () |
| Swizzle the block index. More... | |
| CUTLASS_HOST_DEVICE dim3 | get_grid_layout (GemmCoord const &problem_size, Coord< 3 > const &OutputTile) |
| CUTLASS_DEVICE Coord< 3 > | get_threadblock_offset (Coord< 3 > const &OutputTile) |
| CUTLASS_DEVICE int | get_batch_id () |
|
inline |
|
inline |
|
inline |
|
inline |
|
inline |
1.8.14