[all-commits] [llvm/llvm-project] 8b6954: [X86][FP16] Promote FP16->[U]INT to FP16->FP32->[U...

Phoebe Wang via All-commits all-commits at lists.llvm.org
Sat Aug 13 18:37:49 PDT 2022

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 8b69549dc5c5fa0f5f8632cde1c740bb2c7d8957
  Author: Phoebe Wang <phoebe.wang at intel.com>
  Date:   2022-08-14 (Sun, 14 Aug 2022)

  Changed paths:
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/fpclamptosat_vec.ll
    M llvm/test/CodeGen/X86/half.ll
    M llvm/test/CodeGen/X86/vector-half-conversions.ll

  Log Message:
  [X86][FP16] Promote FP16->[U]INT to FP16->FP32->[U]INT

This is to avoid f16->i64 being lowered to `__fixhfdi/__fixunshfdi` on 32-bits since neither libgcc nor compiler-rt provide them. https://godbolt.org/z/cjWEsea5v

It also helps to improve the performance by promoting the vector type.

Reviewed By: LuoYuanke

Differential Revision: https://reviews.llvm.org/D131828

More information about the All-commits mailing list