[llvm] AMDGPU: Add a subtarget feature for fine-grained remote memory support (PR #96442)

[Jay Foad via llvm-commits]

================
@@ -788,6 +788,16 @@ def FeatureFlatAtomicFaddF32Inst
   "Has flat_atomic_add_f32 instruction"
 >;
 
+def FeatureAgentScopeFineGrainedRemoteMemoryAtomics
----------------
jayfoad wrote:

I'd prefer using "Device" (hardware terminology) instead of "Agent" (terminology from some compute API??) in the hardware feature name. Although I see "agent" is already pervasive in AMDGPUUsage so perhaps that ship has sailed.

https://github.com/llvm/llvm-project/pull/96442