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

Threadblock swizzling function for batched GEMMs.

#include <threadblock_swizzle.h>

Public Member Functions

CUTLASS_HOST_DEVICE GemmCoord get_tiled_shape (GemmCoord problem_size, int batch_count, GemmCoord tile_size) 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...
CUTLASS_DEVICE int get_batch_idx () const
 Gets the batch index. More...

Member Function Documentation

CUTLASS_DEVICE int cutlass::gemm::threadblock::GemmBatchedIdentityThreadblockSwizzle::get_batch_idx ( ) const
CUTLASS_HOST_DEVICE dim3 cutlass::gemm::threadblock::GemmBatchedIdentityThreadblockSwizzle::get_grid_shape ( GemmCoord  tiled_shape) const
CUTLASS_DEVICE GemmCoord cutlass::gemm::threadblock::GemmBatchedIdentityThreadblockSwizzle::get_tile_offset ( ) const
CUTLASS_HOST_DEVICE GemmCoord cutlass::gemm::threadblock::GemmBatchedIdentityThreadblockSwizzle::get_tiled_shape ( GemmCoord  problem_size,
int  batch_count,
GemmCoord  tile_size 
) const

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