[all-commits] [llvm/llvm-project] d07ff1: [X86] LowerABD - improve pre-SSE41 handling for v1...

[Simon Pilgrim via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d07ff1d1091ec06a79ccc16cf68bffa798ea79cf
      https://github.com/llvm/llvm-project/commit/d07ff1d1091ec06a79ccc16cf68bffa798ea79cf
  Author: Simon Pilgrim <llvm-dev at redking.me.uk>
  Date:   2023-06-27 (Tue, 27 Jun 2023)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/abds-vector-128.ll
    M llvm/test/CodeGen/X86/abdu-vector-128.ll
    M llvm/test/CodeGen/X86/midpoint-int-vec-128.ll

  Log Message:
  -----------
  [X86] LowerABD - improve pre-SSE41 handling for v16i8/v4i32 nodes

The generic expansion still causes a problem for SSE targets without BLENDV/select node, but we can create a custom lowering until that can be addressed.