[clang] [Clang][HIP][CUDA] Add `__cluster_dims__` and `__no_cluster__` attribute (PR #156686)

Erich Keane via cfe-commits cfe-commits at lists.llvm.org
Wed Sep 10 08:45:32 PDT 2025


================
@@ -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
----------------
erichkeane wrote:

I'm not expecting to get ALL of the documentation right (though, patch would be welcome).  I'm asking you to do THIS one right since it is new.

https://github.com/llvm/llvm-project/pull/156686


More information about the cfe-commits mailing list