[llvm] [AMDGPU] Make maximum hard clause size a subtarget feature (PR #81287)

[Jay Foad via llvm-commits]

================
@@ -168,6 +168,10 @@ class GCNSubtarget final : public AMDGPUGenSubtargetInfo,
   bool HasFlatAtomicFaddF32Inst = false;
   bool HasDefaultComponentZero = false;
   bool HasDefaultComponentBroadcast = false;
+  /// The maximum number of instructions that may be placed within an S_CLAUSE.
+  /// , which is one greater than the maximum argument to S_CLAUSE. A value
----------------
jayfoad wrote:

Weird comma placement

https://github.com/llvm/llvm-project/pull/81287