[all-commits] [llvm/llvm-project] d5b840: [LAA/LV] Simplify stride speculation logic [NFC]

[Philip Reames via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d5b840131223f2ffef4e48ca769ad1eb7bb1869a
      https://github.com/llvm/llvm-project/commit/d5b840131223f2ffef4e48ca769ad1eb7bb1869a
  Author: Philip Reames <preames at rivosinc.com>
  Date:   2023-05-11 (Thu, 11 May 2023)

  Changed paths:
    M llvm/include/llvm/Analysis/LoopAccessAnalysis.h
    M llvm/include/llvm/Analysis/VectorUtils.h
    M llvm/lib/Analysis/LoopAccessAnalysis.cpp
    M llvm/lib/Analysis/VectorUtils.cpp
    M llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    M llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp

  Log Message:
  -----------
  [LAA/LV] Simplify stride speculation logic [NFC]

The existing code makes it hard to tell that collectStridedAccess is really about identifying some loop invariant SCEV which is *profitable* to speculate is equal to one. The odd dual usage structure of Value and SCEV confuses this point.

We could choose to loosen the profitability analysis if desired. I'm not proposing doing so at this time as it exposes too many cases where the speculation is unprofitable.

Differential Revision: https://reviews.llvm.org/D147750