[clang] [llvm] [AMDGPU] Add OpenCL-specific fence address space masks (PR #78572)

[Pierre van Houtryve via llvm-commits]

Pierre-vh wrote:

I changed it so it's one or more string arguments:
```
__builtin_amdgcn_masked_fence(__ATOMIC_SEQ_CST, "workgroup", "local", "global")
```
I'm now wondering if adding a new builtin is needed at all, or if it should just be part of the original builtin? It's an additive change.

Should we also rename the MMRA to `amdgpu-fence-as` (remove OpenCL from the name) ?  

Then this feature would become fully generic.

https://github.com/llvm/llvm-project/pull/78572