[all-commits] [llvm/llvm-project] 59af65: [X86][BF16] Try to use `f16` for lowering (#76901)

[Phoebe Wang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 59af659ee3c790d06cb5e2bf580e042547c24323
      https://github.com/llvm/llvm-project/commit/59af659ee3c790d06cb5e2bf580e042547c24323
  Author: Phoebe Wang <phoebe.wang at intel.com>
  Date:   2024-01-05 (Fri, 05 Jan 2024)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/lib/Target/X86/X86ISelLowering.h
    M llvm/lib/Target/X86/X86ISelLoweringCall.cpp
    M llvm/test/CodeGen/X86/bfloat.ll

  Log Message:
  -----------
  [X86][BF16] Try to use `f16` for lowering (#76901)

This patch fixes BF16 32-bit ABI problem:
https://godbolt.org/z/6dMnh8jGG