CUTLASS: fragment_iterator_simt.h File Reference

| | CUTLASS

CUDA Templates for Linear Algebra Subroutines and Solvers |

• Main Page

• Modules

• Namespaces

• Classes

• Files

• File List

• File Members

• include

• cutlass

• epilogue

• warp

Classes | Namespaces

fragment_iterator_simt.h File Reference

This defines a "fragment" iterator for visiting the fragments of an accumulator tile that participate in one warp-level store operation. More...

#include "cutlass/array.h"
#include "cutlass/layout/matrix.h"
#include "cutlass/epilogue/warp/simt_policy.h"

Include dependency graph for fragment_iterator_simt.h:

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

[Go to the source code of this file.](fragment iterator simt_8h_source.html)

|

Classes

| | class | cutlass::epilogue::warp::FragmentIteratorSimt< WarpShape, Operator, Layout, MmaSimtPolicy > | | | Fragment iterator for SIMT accumulator arrangements. More...
| | | | class | [cutlass::epilogue::warp::FragmentIteratorSimt< WarpShape_, Operator_, layout::RowMajor, MmaSimtPolicy_ >](classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorSimt_3_01WarpShape 00_01Operator 00_01la3f2abc523201c1b0228df99119ab88e1.html) | | | Partial specialization for row-major shared memory. [More...](classcutlass_1_1epilogue_1_1warp_1_1FragmentIteratorSimt_3_01WarpShape 00_01Operator 00_01la3f2abc523201c1b0228df99119ab88e1.html#details)
| | |

|

Namespaces

| | | cutlass | | | | | cutlass::epilogue | | | | | cutlass::epilogue::warp | | |

Detailed Description

Typically, the accumulator tile is the largest single block of register-backed storage within the kernel. Storing it to memory is best accomplished by partitioning it into smaller tiles and storing these sequentially.

Round trips through shared memory during the Epilogue phase require partitioning, as shared memory capacity is typically insufficient for a threadblock's total accumulator size.

---

Generated by 1.8.11