[llvm] [AMDGPU] Skip float and double atomicrmw fadd expansion on gfx12 (PR #100217)

[Matt Arsenault via llvm-commits]

https://github.com/arsenm requested changes to this pull request.

Please just close this and do not touch any atomic code. I have a large stack starting at #96759 that replaces all of this 

https://github.com/llvm/llvm-project/pull/100217