func.return
    // CHECK-LABEL: @init_all_tables
  }

  func.func @serving_default(%arg0: tensor<i64> {tf_saved_model.index_path = ["x"]}) -> (tensor<*x!tf_type.string> {tf_saved_model.index_path = ["r"]})
  attributes {tf.entry_function = {control_outputs = "", inputs = "input:0", outputs = "hash_table_Lookup/LookupTableFindV2:0"}, tf_saved_model.exported_names = ["serving_default"]} {

  # CHECK:      func {{@[a-zA-Z_0-9]+}}(
  # CHECK-SAME:   %arg0: tensor<f32> {tf._user_specified_name = "x", tf_saved_model.index_path = [0]},
  # CHECK-SAME:   %arg1: tensor<!tf_type.resource<{{.*}}>>
  # CHECK-SAME: ) -> (
  # CHECK-SAME:   tensor<f32> {tf_saved_model.index_path = [0]},
  # CHECK-SAME:   tensor<f32> {tf_saved_model.index_path = [1]})
  # CHECK-SAME: attributes{{.*}}tf_saved_model.exported_names = ["callee"]

module attributes {tf.versions = {bad_consumers = [], min_consumer = 12 : i32, producer = 554 : i32}, tf_saved_model.semantics} {
  func.func @add(%arg0: tensor<?xf32> {tf_saved_model.index_path = ["input1"]}, %arg1: tensor<?xf32> {tf_saved_model.index_path = ["input2"]}) -> (tensor<?xf32> {tf_saved_model.index_path = ["result"]}) attributes {tf.entry_function = {control_outputs = "", inputs = "input1:0,input2:0", outputs = "result:0"}, tf_saved_model.exported_names = ["add"]} {

  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},
      %arg2: tensor<!tf_type.string> {tf_saved_model.bound_input = @z}
    ) -> (tensor<1x1xi32> {tf_saved_model.index_path = ["r"]})
      attributes {

module attributes {tf_saved_model.semantics, tf_saved_model.under_construction} {

  func.func @serving_default(%arg0: tensor<!tf_type.resource<tensor<100x50xf32>>> {tf.resource_name = "dense/kernel"}) -> (tensor<100x50xf32> {tf_saved_model.index_path = ["dense_2"]})
  attributes {tf.entry_function = {control_outputs = "", inputs = "", outputs = "dense_2/Add:0"}, tf_saved_model.exported_names = ["serving_default"]} {

  EXPECT_THAT(arg_node_itr->name(), StrEq("input_tensor"));
  ASSERT_TRUE(arg_node_itr->attr().contains("tf_saved_model.index_path"));
  ASSERT_THAT(arg_node_itr->attr().at("tf_saved_model.index_path").list().s(),
              SizeIs(1));
  EXPECT_THAT(
      arg_node_itr->attr().at("tf_saved_model.index_path").list().s()[0],
      StrEq("input_tensor:0"));

  // Match the `_Retval` node that corresponds to the return value of @main.

  func.func @read(%arg0: tensor<!tf_type.resource<tensor<10xf32>>> {tf_saved_model.bound_input = @v})
  -> (tensor<10xf32> {tf_saved_model.index_path = []})
  attributes {tf_saved_model.exported_names = ["read"]} {
    // CHECK: %[[v:.*]] = ml_program.global_load @vars.v : tensor<10xf32>
    // CHECK: %[[bar:.*]] = ml_program.global_load @vars.bar : tensor<1xf32>

  func.func @conv_with_multiple_uses(%arg0: tensor<1x3x4x3xf32> {tf_saved_model.index_path = ["input"]}) -> (tensor<1x3x2x2xf32> {tf_saved_model.index_path = ["output"]}, tensor<1x3x2x1xf32> {tf_saved_model.index_path = ["output2"]}) attributes {tf.entry_function = {control_outputs = "", inputs = "serving_default_input:0", outputs = "PartitionedCall:0, Sum:0"}, tf_saved_model.exported_names = ["serving_default"]}...

  func.func @main(%arg0: tensor<2x4x2x2xf32> {tf_saved_model.index_path = ["x"]}) -> (tensor<2x2x1x2xi32> {tf_saved_model.index_path = ["output_1"]}, tensor<2x2x1x2xf32> {tf_saved_model.index_path = ["output_0"]}) attributes {tf.entry_function = {inputs = "serving_default_x:0", outputs = "PartitionedCall:1,PartitionedCall:0"}, tf_saved_model.exported_names = ["serving_default"]}...

  func.func @main(%arg0: tensor<?x3xf32> {tf_saved_model.index_path = ["input2"]}, %arg1: tensor<?x3xf32> {tf_saved_model.index_path = ["input1"]}) -> (tensor<?x5xf32> {tf_saved_model.index_path = ["start_logits"]}, tensor<?x5xf32> {tf_saved_model.index_path = ["end_logits"]}) attributes {tf.entry_function = {control_outputs = "", inputs = "serving_default_input2:0,serving_default_input1:0", outputs = "St...