[clang] [llvm] [AMDGPU] Emit a waitcnt instruction after each memory instruction (PR #79236)

[Pierre van Houtryve via llvm-commits]

================
@@ -167,6 +167,10 @@ def FeatureCuMode : SubtargetFeature<"cumode",
   "Enable CU wavefront execution mode"
 >;
 
+def FeaturePreciseMemory
----------------
Pierre-vh wrote:

The extra overhead is just 3 lines in `clang/lib/Driver/ToolChains/AMDGPU.cpp`, it's negligible.
We don't have any target feature that starts with `amdgpu` so it's out of place IMO, it should really drop the `amdgpu-` prefix.

https://github.com/llvm/llvm-project/pull/79236