[Mlir-commits] [mlir] [mlir][gpu] Add `subgroup_broadcast` op (PR #152808)

[Krzysztof Drewniak]

================
@@ -3212,4 +3212,51 @@ def GPU_WarpExecuteOnLane0Op : GPU_Op<"warp_execute_on_lane_0",
   }];
 }
 
+def GPU_BroadcastType : I32EnumAttr<"BroadcastType",
+    "a lane to broadcast from",
+    [
+      I32EnumAttrCase<"first_lane", 0>,
+      I32EnumAttrCase<"any_lane", 1>,
+      I32EnumAttrCase<"lane", 2>
+    ]>{
+  let genSpecializedAttr = 0;
+  let cppNamespace = "::mlir::gpu";
+}
+def GPU_BroadcastTypeAttr : EnumAttr<GPU_Dialect, GPU_BroadcastType, "broadcast">;
+
+def GPU_BroadcastLaneOp : GPU_Op<"broadcast_lane",
----------------
krzysz00 wrote:

I do kinda like `subgroup_broadcast`

https://github.com/llvm/llvm-project/pull/152808