diff --git a/mlir/include/mlir/Dialect/GPU/IR/GPUOps.td b/mlir/include/mlir/Dialect/GPU/IR/GPUOps.td
--- a/mlir/include/mlir/Dialect/GPU/IR/GPUOps.td
+++ b/mlir/include/mlir/Dialect/GPU/IR/GPUOps.td
@@ -1245,8 +1245,7 @@
                                   "mma_element_wise">;
 
 def GPU_SubgroupMmaElementwiseOp : GPU_Op<"subgroup_mma_elementwise",
-    [NoSideEffect,
-     AllTypesMatch<["args"]>]>{
+    [NoSideEffect]>{
 
   let summary = "GPU warp elementwise operation on a matrix";
 
diff --git a/mlir/include/mlir/IR/OpBase.td b/mlir/include/mlir/IR/OpBase.td
--- a/mlir/include/mlir/IR/OpBase.td
+++ b/mlir/include/mlir/IR/OpBase.td
@@ -2311,7 +2311,8 @@
     AllMatchSameOperatorTrait<names, Shape<"_self">.result, "shape">;
 
 class AllTypesMatch<list<string> names> :
-    AllMatchSameOperatorTrait<names, "$_self.getType()", "type">;
+    AllMatchSameOperatorTrait<names, "$_self.getType().cast<::mlir::Type>()",
+                             "type">;
 
 // A type constraint that denotes `transform(lhs.getType()) == rhs.getType()`.
 // An optional comparator function may be provided that changes the above form