[all-commits] [llvm/llvm-project] a738bd: AMDGPU: Permit more rsq formation in AMDGPUCodeGen...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: a738bdf35eaa3bb48b7d8022e2aaa352cff909ba
      https://github.com/llvm/llvm-project/commit/a738bdf35eaa3bb48b7d8022e2aaa352cff909ba
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2023-08-23 (Wed, 23 Aug 2023)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
    M llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-fdiv.ll
    M llvm/test/CodeGen/AMDGPU/fdiv_flags.f32.ll
    M llvm/test/CodeGen/AMDGPU/rsq.f32.ll

  Log Message:
  -----------
  AMDGPU: Permit more rsq formation in AMDGPUCodeGenPrepare

We were basing the defer the fast case to codegen based on the fdiv
itself, and not looking for a foldable sqrt input.

https://reviews.llvm.org/D158127