[llvm-branch-commits] [llvm] AMDGPU: Handle f32 minimum3/maximum3 pattern for gfx950 (PR #117737)

[Shilei Tian via llvm-branch-commits]

https://github.com/shiltian approved this pull request.

wonder why it is called `v_maximum3`.

https://github.com/llvm/llvm-project/pull/117737