[llvm] [AMDGPU] Introduce Next-Use Analysis for SSA-based Register Allocation (PR #156079)

[via llvm-commits]

alex-t wrote:

@arsenm , @ruiling , @ronlieb, @shiltian 

Please let me know if there are any additional objections, comments, or suggestions.
If there’s no further feedback over the next week, I’ll proceed with landing.

https://github.com/llvm/llvm-project/pull/156079