[all-commits] [llvm/llvm-project] 7593f9: [X86] combineConcatVectorOps - add handling for X8...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 7593f9b59a16d395c4bcfab8347037cefdf45f71
      https://github.com/llvm/llvm-project/commit/7593f9b59a16d395c4bcfab8347037cefdf45f71
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2023-08-08 (Tue, 08 Aug 2023)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/vector-interleaved-store-i8-stride-4.ll

  Log Message:
  -----------
  [X86] combineConcatVectorOps - add handling for X86ISD::SHUF128 nodes.

Prevents regression on some future work to improve codegen for concat_vectors(extract_subvector(),extract_subvector()) patterns.

X86ISD::SHUF128 optimization is still pretty poor (especially the zmm variant), not optimizing the shuffle demanded elts like we do for SHUFPS.