[PATCH] D109368: [LV] Don't vectorize if we can prove RT + vector cost >= scalar cost.

Florian Hahn via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Apr 5 09:45:41 PDT 2022


fhahn updated this revision to Diff 420560.
fhahn added a comment.

Rebased

In D109368#3429586 <https://reviews.llvm.org/D109368#3429586>, @xbolva00 wrote:

> Good to go now?

Basically yes from my prespective, although we should wait for D122126 <https://reviews.llvm.org/D122126> and maybe D119078 <https://reviews.llvm.org/D119078> to land. We should definitely make sure that there's a substantial  gap between this patch and D119078 <https://reviews.llvm.org/D119078>, because both have the potential to shake things up quite a bit.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D109368/new/

https://reviews.llvm.org/D109368

Files:
  llvm/include/llvm/Transforms/Vectorize/LoopVectorizationLegality.h
  llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
  llvm/lib/Transforms/Vectorize/LoopVectorizationPlanner.h
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/test/Transforms/LoopVectorize/AArch64/runtime-check-size-based-threshold.ll
  llvm/test/Transforms/LoopVectorize/X86/gather_scatter.ll
  llvm/test/Transforms/LoopVectorize/X86/pointer-runtime-checks-unprofitable.ll
  llvm/test/Transforms/LoopVectorize/X86/pr23997.ll
  llvm/test/Transforms/LoopVectorize/X86/pr35432.ll
  llvm/test/Transforms/LoopVectorize/X86/runtime-limit.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D109368.420560.patch
Type: text/x-patch
Size: 25037 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220405/34f502d5/attachment.bin>


More information about the llvm-commits mailing list