[llvm] [AMDGPU] When allocating VGPRs, VGPR spills are not part of the prologue (PR #109439)

[Matt Arsenault via llvm-commits]

arsenm wrote:

> I don't know how to write a small test for this. The test case from #109294 is about 600K.

You can try llvm-reducing mir test using a strict -stress-regalloc value, it sometimes works 

https://github.com/llvm/llvm-project/pull/109439