[llvm-branch-commits] [llvm] AMDGPU: Stop using the wavemask register class for SCC cross class copies (PR #161801)

[Stanislav Mekhanoshin via llvm-branch-commits]

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

That's a scalar condition, so really does not depend on wave size. LGTM.

https://github.com/llvm/llvm-project/pull/161801