%1 = "tf.Const"() {value = dense<1.0> : tensor<2xf32>} : () -> tensor<2xf32>
      %2 = "tf.Const"() {value = dense<2> : tensor<2xi32>} : () -> tensor<2xi32>
      %3 = "tf.Const"() {value = dense<1.0> : tensor<2xf32>} : () -> tensor<2xf32>
      %4 = "tf.Const"() {value = dense<0> : tensor<2xi32>} : () -> tensor<2xi32>

  module attributes {tf.versions = {bad_consumers = [], min_consumer = 0 : i32, producer = 268 : i32}} {
    func.func @main() -> tensor<1xi32> {
      %0 = "tf.Const"() {value = dense<1000> : tensor<1xi32>} : () -> tensor<1xi32>
      return %0 : tensor<1xi32>
    }
  })";
  CreateModule(kMlirModuleStr);

  auto result = Run();

  EXPECT_TRUE(result.succeeded());
}

func.func @noinline0() -> (tensor<0xf32>) {
  %cst = "tf.Const"() {value = dense<1.0> : tensor<0xf32>} : () -> tensor<0xf32>
  return %cst : tensor<0xf32>
}

// -----

// Tests that the function not listed in the option `noinline-functions`
// is not marked tf._noinline = true.

// CHECK-LABEL: @inline
// CHECK-NOT: tf._noinline
func.func @inline() -> (tensor<0xf32>) {

// CHECK-LABEL: fuseMulIntoPerTensorConv2dWithQDQs
func.func @fuseMulIntoPerTensorConv2dWithQDQs(%arg0: tensor<256x32x32x3xf32>) -> tensor<256x8x7x3xf32> {
  %cst = arith.constant dense<1.5> : tensor<3xf32>
  %cst_0 = arith.constant dense<[1.0, 2.0, 3.0]> : tensor<3xf32>
  %w = arith.constant dense<2.0> : tensor<3x3x3x3xf32>

// RUN: flatbuffer_translate -mlir-to-tflite-flatbuffer %s -o - | flatbuffer_translate -tflite-flatbuffer-to-mlir - -o - | FileCheck --check-prefix=IMPORT %s

func.func @main(tensor<4xf32>) -> tensor<4xf32> {
^bb0(%arg0: tensor<4xf32>):
// CHECK: {
// CHECK-NEXT:   version: 3,
// CHECK-NEXT:     operator_codes: [ {
// CHECK-NEXT:       deprecated_builtin_code: 80,
// CHECK-NEXT:       version: 1,

func.func @func_0_CPU(%arg0: tensor<10x10x10xf32>, %arg1: tensor<10xf32>) -> tensor<10x10x10xf32> attributes {tac.device = "CPU", tac.interface_name = "func_0"} {
  %0 = "tfl.add"(%arg0, %arg1) {fused_activation_function = "RELU", tac.device = "CPU"} : (tensor<10x10x10xf32>, tensor<10xf32>) -> tensor<10x10x10xf32>
  %1 = "tfl.mul"(%0, %arg1) {fused_activation_function = "RELU", tac.device = "CPU"} : (tensor<10x10x10xf32>, tensor<10xf32>) -> tensor<10x10x10xf32>

    module {
      func.func @test_fold_constant(%arg0: tensor<*xf32>) -> (tensor<?x?x?x3xf32>) {
        %cst = "tf.Const"() {value = dense<2.000000e+00> : tensor<2x3x3x1xf32>} : () -> tensor<2x3x3x1xf32>
        %cst_0 = "tf.Const"() {value = dense<0.400000e+00> : tensor<3xf32>} : () -> tensor<3xf32>
        %cst_1 = "tf.Const"() {value = dense<0.500000e+00> : tensor<3xf32>} : () -> tensor<3xf32>

func.func @func(%arg0: tensor<4xf32>) -> tensor<4xf32> {
  %cst = "tf.Const"() {value = dense<23.0> : tensor<4xf32>} : () -> tensor<4xf32>
  %0 = "tf.XlaSharding"(%arg0) { _XlaSharding = "\01\02\03"} : (tensor<4xf32>) -> tensor<4xf32>
  %1 = "tf.AddV2"(%0, %cst) : (tensor<4xf32>, tensor<4xf32>) -> (tensor<4xf32>)
  %2 = "tf.AddV2"(%cst, %1) : (tensor<4xf32>, tensor<4xf32>) -> (tensor<4xf32>)

    %outputs_2, %control_2 = tf_executor.island wraps "tf.Identity"(%outputs_1) {T = "tfdtype$DT_FLOAT", _tpu_input_identity = true, _tpu_replicate = "cluster", device = "", name = "replicated_input_1"} : (tensor<0xf32>) -> tensor<0xf32>

  %biasadd = "tf.BiasAdd"(%conv, %dq_bias) {data_format = "NHWC", device = ""} : (tensor<*xf32>, tensor<2xf32>) -> tensor<*xf32>
  %res = "tf.Relu6"(%biasadd) : (tensor<*xf32>) -> tensor<*xf32>
  %q_res = "quantfork.qcast"(%res) : (tensor<*xf32>) -> tensor<*x!quant.uniform<i8:f32, 0.023529411764705882:-128>>