[clang] clang/AMDGPU: Set amdgpu-max-num-workgroups to disable Y/Z by default (PR #119009)

[Shilei Tian via cfe-commits]

================
@@ -706,6 +706,10 @@ class LangOptions : public LangOptionsBase {
     return OpenCL || CUDA;
   }
 
+  /// Return true if the dispatch size for an offload language only uses one
+  /// dimension.
+  bool gridSizeIsOneDimension() const { return CUDA || HIP || OpenMP; }
----------------
shiltian wrote:

CUDA and HIP don't support 3d grid? Did I misunderstand?

https://github.com/llvm/llvm-project/pull/119009