[llvm] [AMDGPU] Prevent cyclic behaviour in SIFoldOperands (PR #82099)

[Pierre van Houtryve via llvm-commits]

https://github.com/Pierre-vh requested changes to this pull request.

Thanks, needs a testcase as well. Please add a .mir testcase, there's already a few for `si-fold-operands` I think 

https://github.com/llvm/llvm-project/pull/82099