[PATCH] D101836: [LoopVectorize] Enable strict reductions when allowReordering() returns false

[Kerry McLaughlin via Phabricator via llvm-commits]

kmclaughlin updated this revision to Diff 344065.
kmclaughlin marked 2 inline comments as done.
kmclaughlin added a reviewer: spatel.
kmclaughlin added a comment.

- Removed changes to allowReordering() from this patch
- Removed `Hints.getWidth().isScalar()` check from canVectorizeFPMath()
- Changed canVectorizeFPMath to also look at induction variables, as we should not vectorize if the loop has any exact floating-point induction operators and we do not allow reassociation.
- Added more tests to strict-fadd.ll which include floating-point induction variables to test the above changes.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D101836/new/

https://reviews.llvm.org/D101836

Files:
  llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
  llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
  llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D101836.344065.patch
Type: text/x-patch
Size: 58167 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210510/e0326294/attachment.bin>