[Mlir-commits] [mlir] [mlir][GPU] Extend gpu.barrier with scope and named-barrier support (PR #195692)

[Fabian Mora]

================
@@ -1443,35 +1451,92 @@ def GPU_BarrierOp : GPU_Op<"barrier">,
     accessing the same memory can be avoided by synchronizing work items
     in-between these accesses.
 
-    If the `memfence` attribute is specified, the set of memory accesses that must
-    by completed after the barrier resolves is limited to only those accesses that
-    read from or write to the specified address spaces (though accesses to other
-    address spaces may be completed as well, especially if a particular combination
-    of address spaces is not supported on a given backend). In particular,
-    specifying `memfence []` creates a barrier that is not required to affect
-    the visibility of any memory operations and is purely used for synchronizing
-    work items.
+    The `scope` attribute controls the execution scope of the barrier:
 
     ```mlir
-    // Only workgroup address spaces accesses required to be visible.
+    // Synchronize within a subgroup (warp/wavefront).
+    gpu.barrier scope <subgroup>
+    // Synchronize across the entire device.
+    gpu.barrier scope <device>
+    ```
+
+    A `named` barrier allows synchronizing a specific subset of subgroups
+    that have been associated with a named barrier handle. Named barriers
+    require workgroup scope.
----------------
fabianmcg wrote:

In view of https://developer.nvidia.com/blog/cooperative-groups/ the requirement of workgroup seems arbitrary.

https://github.com/llvm/llvm-project/pull/195692