[all-commits] [llvm/llvm-project] f229bf: [Legalize][X86] Improve nnan fmin/fmax vector redu...

[Nikita Popov via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: f229bf2e12461be55446e6b08ccb931308586031
      https://github.com/llvm/llvm-project/commit/f229bf2e12461be55446e6b08ccb931308586031
  Author: Nikita Popov <nikita.ppv at gmail.com>
  Date:   2020-09-27 (Sun, 27 Sep 2020)

  Changed paths:
    M llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
    M llvm/test/CodeGen/AArch64/vecreduce-fmax-legalization.ll
    M llvm/test/CodeGen/AArch64/vecreduce-fmin-legalization.ll
    M llvm/test/CodeGen/X86/vector-reduce-fmax-nnan.ll
    M llvm/test/CodeGen/X86/vector-reduce-fmin-nnan.ll

  Log Message:
  -----------
  [Legalize][X86] Improve nnan fmin/fmax vector reduction

Use +/-Inf or +/-Largest as neutral element for nnan fmin/fmax
reductions. This avoids dropping any FMF flags. Preserving the
nnan flag in particular is important to get a good lowering on X86.

Differential Revision: https://reviews.llvm.org/D87586