[all-commits] [llvm/llvm-project] ab9296: Revert "[LoopVectorize][AArch64] Enable ordered re...

[Florian Hahn via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ab9296f13be45cd190608f54a69bdd5c7c561b16
      https://github.com/llvm/llvm-project/commit/ab9296f13be45cd190608f54a69bdd5c7c561b16
  Author: Florian Hahn <flo at fhahn.com>
  Date:   2021-08-20 (Fri, 20 Aug 2021)

  Changed paths:
    M llvm/include/llvm/Analysis/TargetTransformInfo.h
    M llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
    M llvm/lib/Analysis/TargetTransformInfo.cpp
    M llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
    M llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    M llvm/test/Transforms/LoopVectorize/AArch64/scalable-strict-fadd.ll
    M llvm/test/Transforms/LoopVectorize/AArch64/strict-fadd.ll

  Log Message:
  -----------
  Revert "[LoopVectorize][AArch64] Enable ordered reductions by default for AArch64"

This reverts commit f4122398e7c195147cde120d070f9b72905d7c91 to
investigate a crash exposed by it.

The patch breaks building the code below with `clang -O2 --target=aarch64-linux`

     int a;
     double b, c;
     void d() {
       for (; a; a++) {
         b += c;
         c = a;
       }
     }