auto reduce =
      internal::BroadcastGradientArgs(scope, x_batch_shape, y_batch_shape);
  (*grad_outputs)[0] =
      Reshape(scope, ReduceSum(scope, (*grad_outputs)[0], reduce.r0), sx);
  (*grad_outputs)[1] =
      Reshape(scope, ReduceSum(scope, (*grad_outputs)[1], reduce.r1), sy);
  return scope.status();
}
REGISTER_GRADIENT_OP("BatchMatMulV2", BatchMatMulV2Grad);