// CHECK-NEXT:     %[[GROUP:.*]] = "tf.Const"()
  // CHECK-SAME:       [0, 1, 2, 3]
  // CHECK-NEXT:     %[[REDUCED:.*]] = "tf.XlaAllReduce"(%[[ID]], %[[GROUP]]) <{mode = "CrossReplica", reduce_op = "Add"}> : (tensor<f32>, tensor<1x4xi32>) -> tensor<f32>
  // CHECK-NEXT:     "tf.OpA"(%[[REDUCED]]) : (tensor<f32>) -> ()
  tf_device.replicate {n = 4 : i32} {
    "tf_device.cluster"() ({
      "tf.OpA"(%arg0) : (tensor<f32>) -> ()
      tf_device.return

  %size_shape = "tf.Const"() {value = dense<[10, 8, 4]> : tensor<3xi32>} : () -> tensor<3xi32>
  %tl = "tf.BroadcastTo"(%emptyf, %size_shape) : (tensor<f32>, tensor<3xi32>) -> tensor<10x8x4xf32>
  // TensorListPushBack lowering
  %index_in_list = "tf.Const"() {value = dense<0> : tensor<1xi32>} : () -> tensor<1xi32>
  %arg0_shape = "tf.Const"() {value = dense<[1, 8, 4]> : tensor<3xi32>} : () -> tensor<3xi32>