[clang] [llvm] AMDGPU: Move enqueued block handling into clang (PR #128519)

[Sameer Sahasrabuddhe via cfe-commits]

https://github.com/ssahasra commented:

I don't have recent exposure to the OpenCL implementation, but generally eyeballed the code to make sure that the changes do what is described. Is there some confidence that the new scheme actually works? For example, maybe an existing CodeGen test where the final HSA metadata remains equivalent, and the runtime can successfully pick it up.

https://github.com/llvm/llvm-project/pull/128519