[clang] [flang] [llvm] [mlir] [IR] Generalize !amdgpu.ignore.denormal.mode into !atomic.ignore.denormal.mode (PR #217585)

[Matt Arsenault via cfe-commits]

https://github.com/arsenm commented:

LGTM but I think the bitcode upgrade is unnecessary 

https://github.com/llvm/llvm-project/pull/217585