One of the vector transformation patterns has been indiscriminately
converting layouts to affine maps. Leverage the strided form when
possible.
Details
Details
Diff Detail
Diff Detail
- Repository
- rG LLVM Github Monorepo
Paths
| Differential D134047
[mlir] use strided layouts in vector transfer on memrefs ClosedPublic Authored by ftynse on Sep 16 2022, 7:19 AM.
Details Summary One of the vector transformation patterns has been indiscriminately
Diff Detail
Event TimelineHerald added subscribers: bzcheeseman, ThomasRaoux, sdasgup3 and 21 others. · View Herald Transcript This revision is now accepted and ready to land.Sep 16 2022, 8:49 AM This revision was landed with ongoing or failed builds.Sep 16 2022, 11:11 PM Closed by commit rG83df43f3a204: [mlir] use strided layouts in vector transfer on memrefs (authored by ftynse). · Explain Why This revision was automatically updated to reflect the committed changes.
Revision Contents
Diff 460971 mlir/lib/Dialect/Vector/Transforms/VectorTransforms.cpp
mlir/test/Dialect/Vector/vector-transfer-collapse-inner-most-dims.mlir
|