[all-commits] [llvm/llvm-project] 7ec8fc: [X86] combineAnd() - per-element simplification - ...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 7ec8fc29321c698af665072424bc02a87369c8ad
      https://github.com/llvm/llvm-project/commit/7ec8fc29321c698af665072424bc02a87369c8ad
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2022-01-31 (Mon, 31 Jan 2022)

  Changed paths:
    M llvm/include/llvm/CodeGen/TargetLowering.h
    M llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/vector_splat-const-shift-of-constmasked.ll

  Log Message:
  -----------
  [X86] combineAnd() - per-element simplification - call SimplifyDemandedBits using mask demanded bits if SimplifyDemandedVectorElts fails

We already call SimplifyDemandedVectorElts using whether each vector mask element is zero/nonzero, this just extends this to also try SimplifyDemandedBits using the demanded bits mask generated from the nonzero elements.

This also requires an additional TargetLowering::SimplifyDemandedBits DemandedBits/DemandedElts wrapper.