[all-commits] [llvm/llvm-project] 67d499: [InstCombine] add tests for icmp of casted vector; ...

[RotateRight via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 67d499445d47a5f2690954c8f15e1d22d696077e
      https://github.com/llvm/llvm-project/commit/67d499445d47a5f2690954c8f15e1d22d696077e
  Author: Sanjay Patel <spatel at rotateright.com>
  Date:   2021-08-06 (Fri, 06 Aug 2021)

  Changed paths:
    M llvm/test/Transforms/InstCombine/icmp-vec.ll

  Log Message:
  -----------
  [InstCombine] add tests for icmp of casted vector; NFC

https://llvm.org/PR51315


  Commit: 0369714b31682dc36e55f1a2b3a36c25fb1b6f98
      https://github.com/llvm/llvm-project/commit/0369714b31682dc36e55f1a2b3a36c25fb1b6f98
  Author: Sanjay Patel <spatel at rotateright.com>
  Date:   2021-08-06 (Fri, 06 Aug 2021)

  Changed paths:
    M llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
    M llvm/test/Transforms/InstCombine/icmp-vec.ll

  Log Message:
  -----------
  [InstCombine] reduce vector casting before icmp

There may be some generalizations (see test comments) of these patterns,
but this should handle the cases motivated by:
https://llvm.org/PR51315
https://llvm.org/PR51259

The backend may want to transform differently, but at least for
the x86 examples that I looked at, there does not appear to be
any significant perf diff either way.


Compare: https://github.com/llvm/llvm-project/compare/05783e1cfe40...0369714b3168