CUTLASS: cutlass::gemm::threadblock::GemvBatchedStridedThreadblockDefaultSwizzle Struct Reference

| | CUTLASS

CUDA Templates for Linear Algebra Subroutines and Solvers |

• Main Page

• Modules

• Namespaces

• Classes

• Files

• Class List

• Class Index

• Class Hierarchy

• Class Members

• cutlass

• gemm

• threadblock

• GemvBatchedStridedThreadblockDefaultSwizzle

Public Member Functions | List of all members

cutlass::gemm::threadblock::GemvBatchedStridedThreadblockDefaultSwizzle Struct Reference

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

---

Generated by 1.8.11