[PATCH] D143465: [LoopVectorize] Vectorize the reduction pattern of integer min/max with index. (WIP)

[Mel Chen via Phabricator via llvm-commits]

Mel-Chen updated this revision to Diff 496879.
Mel-Chen added a comment.

Changes:

- Fix interleave code generation for `SelectIVICmp` and `SelectIVFCmp`.
- Fix the internal compiler error for `MinMaxFirstIdx` and `MinMaxLastIdx` when -force-vector-width=1.
- Update test cases. Add more run command lines.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D143465/new/

https://reviews.llvm.org/D143465

Files:
  llvm/include/llvm/Analysis/IVDescriptors.h
  llvm/include/llvm/Transforms/Utils/LoopUtils.h
  llvm/lib/Analysis/IVDescriptors.cpp
  llvm/lib/Transforms/Utils/LoopUtils.cpp
  llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
  llvm/test/Transforms/LoopVectorize/select-min-index.ll
  llvm/test/Transforms/LoopVectorize/smax-idx.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D143465.496879.patch
Type: text/x-patch
Size: 199342 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230213/ff1ed4d8/attachment-0001.bin>