Back to Cutlass

CUTLASS: shared_load_iterator.h File Reference

docs/shared__load__iterator_8h.html

4.4.21.8 KB
Original Source

| | CUTLASS

CUDA Templates for Linear Algebra Subroutines and Solvers |

Classes | Namespaces

shared_load_iterator.h File Reference

Epilogue for threadblock scoped GEMMs using Tensor Ops. More...

#include "cutlass/cutlass.h"
#include "cutlass/numeric_types.h"
#include "cutlass/array.h"
#include "cutlass/layout/matrix.h"
#include "cutlass/matrix_shape.h"
#include "cutlass/tensor_ref.h"
#include "cutlass/epilogue/threadblock/output_tile_thread_map.h"

Include dependency graph for shared_load_iterator.h:

This graph shows which files directly or indirectly include this file:

[Go to the source code of this file.](shared load iterator_8h_source.html)

|

Classes

| | class | cutlass::epilogue::threadblock::SharedLoadIterator< ThreadMap_, Element_, MaxAlignment > | | |

|

Namespaces

| | | cutlass | | | | | cutlass::epilogue | | | | | cutlass::epilogue::threadblock | | |

Detailed Description

The epilogue rearranges the result of a matrix product through shared memory to match canonical tensor layouts in global memory. Epilogues support conversion and reduction operations.


Generated by 1.8.11