[all-commits] [llvm/llvm-project] becbc3: AMDGPU: Improve fsqrt f64 expansion with ninf

[Matt Arsenault via All-commits]

  Branch: refs/heads/users/arsenm/amdgpu/todo-no-infs-f64-sqrt
  Home:   https://github.com/llvm/llvm-project
  Commit: becbc33e1f52c07fe711c90ae61fc03b63620312
      https://github.com/llvm/llvm-project/commit/becbc33e1f52c07fe711c90ae61fc03b63620312
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2026-02-27 (Fri, 27 Feb 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-fsqrt.mir
    M llvm/test/CodeGen/AMDGPU/fsqrt.f64.ll

  Log Message:
  -----------
  AMDGPU: Improve fsqrt f64 expansion with ninf

Address todo to reduce the is_fpclass check to an fcmp with 0.



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