Threadblock swizzling function for batched GEMVs.

#include <threadblock_swizzle.h>

Public Member Functions
CUTLASS_HOST_DEVICE BatchedGemmCoord	get_tiled_shape (BatchedGemmCoord problem_size, BatchedGemmCoord tile_size) const
	Returns the shape of the problem in units of logical tiles. More...

CUTLASS_HOST_DEVICE dim3	get_grid_shape (BatchedGemmCoord tiled_shape) const
	Computes CUDA grid dimensions given a size in units of logical tiles. More...

CUTLASS_DEVICE BatchedGemmCoord	get_tile_offset () const
	Obtains the threadblock offset (in units of threadblock-scoped tiles) More...

CUTLASS_DEVICE int	get_batch_tile_idx () const
	Gets the batch tile index. More...

CUTLASS_DEVICE int	get_batch_idx () const
	Gets the absolute batch index. More...

Member Function Documentation

CUTLASS_DEVICE int cutlass::gemm::threadblock::GemvBatchedStridedThreadblockDefaultSwizzle::get_batch_idx ( ) const

inline

CUTLASS_DEVICE int cutlass::gemm::threadblock::GemvBatchedStridedThreadblockDefaultSwizzle::get_batch_tile_idx ( ) const

inline

CUTLASS_HOST_DEVICE dim3 cutlass::gemm::threadblock::GemvBatchedStridedThreadblockDefaultSwizzle::get_grid_shape ( BatchedGemmCoord tiled_shape ) const

inline

CUTLASS_DEVICE BatchedGemmCoord cutlass::gemm::threadblock::GemvBatchedStridedThreadblockDefaultSwizzle::get_tile_offset ( ) const

inline

CUTLASS_HOST_DEVICE BatchedGemmCoord cutlass::gemm::threadblock::GemvBatchedStridedThreadblockDefaultSwizzle::get_tiled_shape	(	BatchedGemmCoord	problem_size,
		BatchedGemmCoord	tile_size
	)		const

inline

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

gemm/threadblock/threadblock_swizzle.h

Public Member Functions

Member Function Documentation