[all-commits] [llvm/llvm-project] 0fab74: [LLVM][CodeGen][AArch64] Don't scalarise v8{f16, bf...

[Paul Walker via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 0fab741a2687a6c42832fe8286591ebe626c40a8
      https://github.com/llvm/llvm-project/commit/0fab741a2687a6c42832fe8286591ebe626c40a8
  Author: Paul Walker <paul.walker at arm.com>
  Date:   2025-05-01 (Thu, 01 May 2025)

  Changed paths:
    M llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
    M llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    M llvm/test/Analysis/CostModel/AArch64/cmp.ll
    M llvm/test/Analysis/CostModel/AArch64/vector-select.ll
    M llvm/test/CodeGen/AArch64/bf16-v8-instructions.ll
    M llvm/test/CodeGen/AArch64/fcmp.ll
    M llvm/test/CodeGen/AArch64/fp16-v8-instructions.ll

  Log Message:
  -----------
  [LLVM][CodeGen][AArch64] Don't scalarise v8{f16,bf16} vsetcc operations. (#135398)

I have also removed custom promotion code for the v4{f16,bf16} cases
because the same common code can be used.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications