[all-commits] [llvm/llvm-project] d21bf5: [CostModel][X86] Adjust pre-SSE41 fp scalar select...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d21bf514940fd3b6368796e3ad22e1910c8598c6
      https://github.com/llvm/llvm-project/commit/d21bf514940fd3b6368796e3ad22e1910c8598c6
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2022-05-06 (Fri, 06 May 2022)

  Changed paths:
    M llvm/lib/Target/X86/X86TargetTransformInfo.cpp
    M llvm/test/Analysis/CostModel/X86/vselect-cost.ll
    M llvm/test/Transforms/SLPVectorizer/X86/crash_cmpop.ll

  Log Message:
  -----------
  [CostModel][X86] Adjust pre-SSE41 fp scalar select costs to account for vector ops

Based off the script from D103695, we now mainly use BLENDV or OR(AND,ANDN) to select scalar float/double ops