CUTLASS
CUDA Templates for Linear Algebra Subroutines and Solvers
Public Member Functions | Public Attributes | List of all members
cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle Struct Reference

Threadblock swizzling function for GEMMs.

#include <threadblock_swizzle.h>

Public Member Functions

CUTLASS_HOST_DEVICE GemmIdentityThreadblockSwizzle ()
 
CUTLASS_HOST_DEVICE GemmCoord get_tiled_shape (GemmCoord problem_size, GemmCoord tile_size, int split_k_slices) const
 Returns the shape of the problem in units of logical tiles. More...
 
CUTLASS_HOST_DEVICE dim3 get_grid_shape (GemmCoord tiled_shape) const
 Computes CUDA grid dimensions given a size in units of logical tiles. More...
 
CUTLASS_DEVICE GemmCoord get_tile_offset () const
 Obtains the threadblock offset (in units of threadblock-scoped tiles) More...
 

Public Attributes

int const kTile = 1
 

Constructor & Destructor Documentation

CUTLASS_HOST_DEVICE cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle::GemmIdentityThreadblockSwizzle ( )
inline

Member Function Documentation

CUTLASS_HOST_DEVICE dim3 cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle::get_grid_shape ( GemmCoord  tiled_shape) const
inline
CUTLASS_DEVICE GemmCoord cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle::get_tile_offset ( ) const
inline
CUTLASS_HOST_DEVICE GemmCoord cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle::get_tiled_shape ( GemmCoord  problem_size,
GemmCoord  tile_size,
int  split_k_slices 
) const
inline

Member Data Documentation

int const cutlass::gemm::threadblock::GemmIdentityThreadblockSwizzle::kTile = 1

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