[all-commits] [llvm/llvm-project] 587747: [AMDGPU] G_IS_FPCLASS lower() support for IEEE fp ...

[Janek van Oirschot via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 587747d8d142828be31a6835d29e75e7cb657a51
      https://github.com/llvm/llvm-project/commit/587747d8d142828be31a6835d29e75e7cb657a51
  Author: Janek van Oirschot <janek.vanoirschot at amd.com>
  Date:   2022-12-07 (Wed, 07 Dec 2022)

  Changed paths:
    M llvm/include/llvm/CodeGen/GlobalISel/LegalizerHelper.h
    M llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/test/CodeGen/AMDGPU/llvm.is.fpclass.f16.ll

  Log Message:
  -----------
  [AMDGPU] G_IS_FPCLASS lower() support for IEEE fp types

Simplified globalisel version of sdag's expandIS_FPCLASS.

Reviewed By: arsenm, #amdgpu

Differential Revision: https://reviews.llvm.org/D139128