[llvm-branch-commits] [llvm] [AMDGPU] Apply occupancy-aware register allocation anti-hints (PR #218074)

[Syadus Sefat via llvm-branch-commits]

mssefat wrote:

> I didn't look at the details of the anti hints heuristic, but the core approach is reasonable. I have a suggestion for avoid code duplication between generic and target specific code.
> 
> Let's have another round of review based on that

I have updated it. Please check.

https://github.com/llvm/llvm-project/pull/218074