[llvm] [AMDGPU][SIMemoryLegalizer][GFX12] Correctly insert sample/bvhcnt (PR #161637)

[Jay Foad via llvm-commits]

jayfoad wrote:

> Before it was inserting those SAMPLE/BVHcnt and they were eliminated by InsertWaitCnt

So a more interesting test case would be when those waits were not eliminated, because they were preceded by some SAMPLE/BVH instructions.

https://github.com/llvm/llvm-project/pull/161637