[all-commits] [llvm/llvm-project] 7bf299: [LV] Vectorize without versioning-for-unit-stride ...

[azaks via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 7bf299c8d8d59304fb821f8811618cdeb1d1f1fd
      https://github.com/llvm/llvm-project/commit/7bf299c8d8d59304fb821f8811618cdeb1d1f1fd
  Author: Ayal Zaks <ayal.zaks at intel.com>
  Date:   2020-07-07 (Tue, 07 Jul 2020)

  Changed paths:
    M llvm/lib/Analysis/LoopAccessAnalysis.cpp
    M llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    M llvm/test/Transforms/LoopVectorize/X86/optsize.ll
    M llvm/test/Transforms/LoopVectorize/X86/tail_loop_folding.ll
    M llvm/test/Transforms/LoopVectorize/optsize.ll
    M llvm/test/Transforms/LoopVectorize/pr39417-optsize-scevchecks.ll
    M llvm/test/Transforms/LoopVectorize/runtime-check.ll

  Log Message:
  -----------
  [LV] Vectorize without versioning-for-unit-stride under -Os/-Oz

If a loop is in a function marked OptSize, Loop Access Analysis should refrain
from generating runtime checks for unit strides that will version the loop.

If a loop is in a function marked OptSize and its vectorization is enabled, it
should be vectorized w/o any versioning.

Fixes PR46228.

Differential Revision: https://reviews.llvm.org/D81345