add documentation

Author: shiltian

clang/include/clang/Basic/Attr.td

@@ -1567,14 +1567,14 @@ def CUDAClusterDims : InheritableAttr {
   let Args = [ExprArgument<"X">, ExprArgument<"Y", 1>, ExprArgument<"Z", 1>];
   let Subjects = SubjectList<[Function], ErrorDiag, "kernel functions">;
   let LangOpts = [CUDA];
-  let Documentation = [Undocumented];
+  let Documentation = [CUDAClusterDimsAttrDoc];
 }
 
 def CUDANoCluster : InheritableAttr {
   let Spellings = [GNU<"no_cluster">, Declspec<"__no_cluster__">];
   let Subjects = SubjectList<[Function], ErrorDiag, "kernel functions">;
   let LangOpts = [CUDA];
-  let Documentation = [Undocumented];
+  let Documentation = [CUDANoClusterAttrDoc];
 }
 
 def : MutualExclusions<[CUDAClusterDims, CUDANoCluster]>;

clang/include/clang/Basic/AttrDocs.td

@@ -7532,6 +7532,25 @@ A managed variable can be accessed in both device and host code.
   }];
 }
 
+def CUDAClusterDimsAttrDoc : Documentation {
+  let Category = DocCatDecl;
+  let Content = [{
+In CUDA/HIP programming, the ``__cluster_dims__`` attribute can be applied to a kernel function
+to set the dimensions of a thread block cluster. This allows to group multiple thread blocks into
+a larger unit called a "cluster". `__cluster_dims__` defines the cluster size as ``(X, Y, Z)``,
+where each value is the number of thread blocks in that dimension.
+  }];
+}
+
+def CUDANoClusterAttrDoc : Documentation {
+  let Category = DocCatDecl;
+  let Content = [{
+In CUDA/HIP programming, the ``__no_cluster__`` attribute can be applied to a kernel function to
+indicate that the thread block cluster feature will not be enabled at both compile time and kernel
+launch time. Note: this is a LLVM/Clang only attribute.
+  }];
+}
+
 def LifetimeOwnerDocs : Documentation {
   let Category = DocCatDecl;
   let Content = [{