"tf_saved_model.global_tensor"() {is_mutable, sym_name = "y", type = tensor<3x1xi32>, value = dense<[[1], [2], [3]]> : tensor<3x1xi32>} : () -> ()
  "tf_saved_model.asset"() {sym_name = "z", filename = "file"} : () -> ()
  func.func @serving_default(
      %arg0: tensor<1x3xi32> {tf_saved_model.index_path = ["x"]},
      %arg1: tensor<!tf_type.resource<tensor<3x1xi32>>> {tf_saved_model.bound_input = @y},

func.func @main() -> tensor<2x3xi32> {
  %graph = tf_executor.graph {
    %0:2 = tf_executor.island wraps "tf.Const"() {value = dense<5> : tensor<2x3xi32>} : () -> tensor<2x3xi32> loc("Const0")
    %1:2 = tf_executor.island wraps "tf.Const"() {value = dense<4.2> : tensor<4x5xf32>} : () -> tensor<4x5xf32> loc("Const1")

      %outputs_9, %control_10 = tf_executor.island(%control_4) wraps "tf.Identity"(%outputs_7) {device = ""} : (tensor<2x3xi32>) -> tensor<2x3xi32>
      tf_executor.fetch %outputs_9 : tensor<2x3xi32>
    }
    return %0 : tensor<2x3xi32>
  }
}

// CHECK: module attributes
// CHECK-SAME:  tfl.metadata = {{{.*}}keep_stablehlo_constant = "true"{{.*}}}

  %3 = "tfl.pack"(%1, %2) {axis = 0 : i32, values_count = 2 : i32} : (tensor<1xf32>, tensor<1xf32>) -> tensor<2x1xf32>
  func.return %3 : tensor<2x1xf32>
}

// CHECK: %[[CST:.*]] = arith.constant dense<1> : tensor<4xi32>

  func.return %0#0 : tensor<*xi32>
}

// compute_3 has different argument types from compute_1, thus error is reported.
// CHECK: error: func_ops for BatchFunctionOp with the same shared name are different
func.func private @compute_3(%arg0: tensor<?x1xi32> {tf._user_specified_name = "0"}, %arg1: tensor<?x1xi32>) -> (tensor<?x1xi32>, tensor<?x1xi32>) {

// CHECK-LABEL: hardcode_all
func.func @hardcode_all(%arg0: tensor<2x2xf32>, %arg1: tensor<2x1xf32>) -> tensor<2x2xf32> {
  %0 = "tfl.add"(%arg0, %arg1) {fused_activation_function="NONE"}: (tensor<2x2xf32>, tensor<2x1xf32>) -> tensor<2x2xf32>
  func.return %0 : tensor<2x2xf32>

// CHECK: %[[q0:.*]] = "tfl.quantize"(%arg1) <{qtype = tensor<2x1x!quant.uniform<u8:f32, 0.0078431372549019607:128>>}>

  %ch0 = tfrt.new.chain

  %a1 = tfrt_fallback_async.const_dense_tensor dense<[[2, 2], [2, 2]]> : tensor<2x2xi32>
  %a2 = tfrt_fallback_async.const_dense_tensor dense<[[3, 3], [3, 3]]> : tensor<2x2xi32>
  %b = tfrt_fallback_async.const_dense_tensor dense<[[1, 1], [1, 1]]> : tensor<2x2xi32>

  // Two batch_size=2 batches get concatenated.

    %0 = "tf.VarHandleOp"() {container = "c", shared_name = "v"} : () -> tensor<*x!tf_type.resource<tensor<2x8xi32>>>
    %1 = "tf.VarHandleOp"() {container = "c", shared_name = "w"} : () -> tensor<*x!tf_type.resource<tensor<2xi32>>>
    %2 = "tf.Const"() {value = dense<1> : tensor<i32>} : () -> tensor<i32>
    %3 = "tf.Const"() {value = dense<1> : tensor<i32>} : () -> tensor<i32>

  %3 = "tfl.batch_matmul"(%arg0, %2) {adj_x = false, adj_y = false, asymmetric_quantize_inputs = false} : (tensor<4x128x2xf32>, tensor<2x1xf32>) -> tensor<4x128x1xf32>
  func.return %3 : tensor<4x128x1xf32>
  // CHECK: %[[TRANSPOSED_X:.*]] = "tfl.transpose"
  // CHECK-SAME: (tensor<2x1xf32>, tensor<2xi32>) -> tensor<1x2xf32>
  // CHECK: %[[FC_RES:.*]] = "tfl.fully_connected"(%arg0, %[[TRANSPOSED_X]]

  }

  // CHECK-LABEL: pack
  func.func @pack(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<2x1xf32> {
    %0 = "tfl.pack"(%arg0, %arg1) {axis = 0 : i32, values_count = 2 : i32} : (tensor<1xf32>, tensor<1xf32>) -> tensor<2x1xf32>
    func.return %0 : tensor<2x1xf32>
    // CHECK: %[[VAL_0:.*]] = arith.constant dense<[2, 1]> : tensor<2xi32>