[all-commits] [llvm/llvm-project] b2d58b: AMDGPU: Expand rsq testing to cover contract flag

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: b2d58b596c999ab897420715686c9b85f9fc2ed0
      https://github.com/llvm/llvm-project/commit/b2d58b596c999ab897420715686c9b85f9fc2ed0
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2023-07-20 (Thu, 20 Jul 2023)

  Changed paths:
    M llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-fdiv.ll
    M llvm/test/CodeGen/AMDGPU/rsq.f32.ll

  Log Message:
  -----------
  AMDGPU: Expand rsq testing to cover contract flag

The 1.0/sqrt(x) -> rsq(x) fold increases precision and probably needs
a contract flag.


  Commit: d33ab0546777127c93dbb719bafeabc06aec5d4f
      https://github.com/llvm/llvm-project/commit/d33ab0546777127c93dbb719bafeabc06aec5d4f
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2023-07-20 (Thu, 20 Jul 2023)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
    A llvm/test/CodeGen/AMDGPU/fdiv_flags.f32.ll

  Log Message:
  -----------
  AMDGPU: Add flag to disable fdiv processing in IR pass

We kind of have to have multiple implementations of fdiv split between
the two selectors with some pre-processing. Add yet another test to
check for consistency of interpretation of flag combinations. We have
quite a bit of test redundancy here already, but there are so many
possible interesting permutations it's unwieldy to cover every detail
in any one of them. We have a number of overlapping fdiv tests but
it's hard to follow everything going on as it is.


Compare: https://github.com/llvm/llvm-project/compare/3cca461f1f1f...d33ab0546777