[clang] [llvm] [AMDGPU][GFX12.5] Reimplement monitor load as an atomic operation (PR #177343)

[Pierre van Houtryve via llvm-commits]

Pierre-vh wrote:

Added support for templated arguments, and added sema+codegen tests for those.
I also added test for the coop atomics because I factored out some code so now they support it too

https://github.com/llvm/llvm-project/pull/177343