[all-commits] [llvm/llvm-project] c23688: [X86] Optimize fdiv with reciprocal instructions f...

[Phoebe Wang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c236883b6ba791881256b31cfdb8a8520a821a67
      https://github.com/llvm/llvm-project/commit/c236883b6ba791881256b31cfdb8a8520a821a67
  Author: Wang, Pengfei <pengfei.wang at intel.com>
  Date:   2021-10-08 (Fri, 08 Oct 2021)

  Changed paths:
    M llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
    M llvm/lib/Target/X86/X86ISelLowering.cpp
    M llvm/test/CodeGen/X86/avx512fp16-arith-vl-intrinsics.ll
    M llvm/test/CodeGen/X86/avx512fp16-arith.ll
    M llvm/test/CodeGen/X86/avx512fp16-intrinsics.ll
    M llvm/test/CodeGen/X86/avx512fp16vl-intrinsics.ll

  Log Message:
  -----------
  [X86] Optimize fdiv with reciprocal instructions for half type

Reviewed By: craig.topper

Differential Revision: https://reviews.llvm.org/D110557