[all-commits] [llvm/llvm-project] 92be2c: [LoongArch] Use LSX for scalar FP rounding with ex...

[ZhaoQi via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 92be2cb08632ea38f6fbc41adfeb475ba27447dd
      https://github.com/llvm/llvm-project/commit/92be2cb08632ea38f6fbc41adfeb475ba27447dd
  Author: ZhaoQi <zhaoqi01 at loongson.cn>
  Date:   2024-11-06 (Wed, 06 Nov 2024)

  Changed paths:
    M llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
    M llvm/lib/Target/LoongArch/LoongArchLSXInstrInfo.td
    M llvm/test/CodeGen/LoongArch/fp-rounding.ll

  Log Message:
  -----------
  [LoongArch] Use LSX for scalar FP rounding with explicit rounding mode (#114766)

LoongArch FP base ISA only have frint.{s/d} instruction which reads the
global rounding mode. Utilize LSX for explicit rounding mode for scalar
ceil/floor/trunc/roundeven calls when -mlsx opend. It is faster than
calling the libm library functions.

Same as what gcc did:
https://gcc.gnu.org/pipermail/gcc-cvs/2023-November/394218.html



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