[PATCH] D126778: [LoopVectorize] Add FastMathFlags to the select used for reductions with tail-folding

David Sherwood via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Jun 1 07:23:40 PDT 2022


david-arm created this revision.
david-arm added reviewers: sdesmalen, spatel, kmclaughlin, CarolineConcatto, peterwaller-arm.
Herald added subscribers: dmgreen, hiraditya.
Herald added a project: All.
david-arm requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

Based on reviewer comments on https://reviews.llvm.org/D126692 I've
added FastMathFlags to the select instruction used when tail-folding
with reductions. These flags can then be used by InstCombine to
decide upon the most optimal floating point identity value for
fadd/fsub. Doing so unlocks further optimisations, such as folding


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D126778

Files:
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/test/Transforms/LoopVectorize/ARM/mve-reduction-predselect.ll
  llvm/test/Transforms/LoopVectorize/ARM/mve-reduction-types.ll
  llvm/test/Transforms/LoopVectorize/reduction-predselect.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D126778.433390.patch
Type: text/x-patch
Size: 7763 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220601/f2f3f491/attachment.bin>


More information about the llvm-commits mailing list