[all-commits] [llvm/llvm-project] 393b55: [AArch64][GlobalISel] Add combine for G_EXTRACT_VE...

[AE via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 393b55380afcd8681db03dfbdea2f27ff3517d25
      https://github.com/llvm/llvm-project/commit/393b55380afcd8681db03dfbdea2f27ff3517d25
  Author: Amara Emerson <amara at apple.com>
  Date:   2020-11-03 (Tue, 03 Nov 2020)

  Changed paths:
    M llvm/lib/Target/AArch64/AArch64Combine.td
    M llvm/lib/Target/AArch64/AArch64InstrGISel.td
    M llvm/lib/Target/AArch64/GISel/AArch64PostLegalizerCombiner.cpp
    A llvm/test/CodeGen/AArch64/GlobalISel/postlegalizercombiner-extractvec-faddp.mir
    A llvm/test/CodeGen/AArch64/GlobalISel/select-faddp.mir

  Log Message:
  -----------
  [AArch64][GlobalISel] Add combine for G_EXTRACT_VECTOR_ELT to allow selection of pairwise FADD.

For the <2 x float> case, instead of adding another combine or legalization to
get it into a <4 x float> form, I'm just adding a GISel specific selection
pattern to cover it.

Differential Revision: https://reviews.llvm.org/D90699