-> (tensor<?x2xi64>, tensor<?x2xi64>, tensor<?x!tf_type.string>, tensor<?xi64>, tensor<2xi64>, tensor<2xi64>, tensor<32xf32>, tensor<32xf32>)

  // CHECK: tfrt.return {{.*}}, [[outputs]]#0
  func.return %outputs#0 : tensor<?x2xi64>
}

// CHECK-LABEL: func @no_native

// RUN: tf-opt %s -tfl-prepare-tf -tfl-legalize-tf='run-tfl-runtime-verification=false'  -tfl-optimize | FileCheck %s

func.func @broadcast_to_bf16(%arg0: tensor<3xbf16>, %arg1: tensor<2xi64>) -> tensor<3x3xbf16> {
  %0 = "tf.BroadcastTo"(%arg0, %arg1) : (tensor<3xbf16>, tensor<2xi64>) -> tensor<3x3xbf16>
  func.return %0: tensor<3x3xbf16>

// CHECK-LABEL: broadcast_to_bf16
// CHECK:  [[CST:%.*]] = arith.constant dense<1.000000e+00> : tensor<3x3xbf16>

    %0 = stablehlo.constant dense<500> : tensor<100xi64>
    %1 = stablehlo.constant dense<0> : tensor<100xi64>
    %2 = stablehlo.compare  LT, %arg2, %1 : (tensor<100xi64>, tensor<100xi64>) -> tensor<100xi1>
    %3 = stablehlo.add %arg2, %0 : tensor<100xi64>
    %4 = stablehlo.select %2, %3, %arg2 : tensor<100xi1>, tensor<100xi64>
    %5 = stablehlo.reshape %4 : (tensor<100xi64>) -> tensor<100x1xi64>

// CHECK: %[[CUSTOM_AGGREGATOR_1:.*]], %[[MIN_1:.*]], %[[MAX_1:.*]], %[[HISTOGRAM_1:.*]] = "tf.CustomAggregator"
// CKECK-SAME: <{calibration_method = 5 : i32, id = "keeping_id", num_bins = 32 : i32, max_percentile = 0.000000e+00 : f32, min_percentile = 0.000000e+00 : f32}> : (tensor<1x3x4x3xf32>) -> (tensor<1x3x4x3xf32>, tensor<f32>, tensor<f32>, tensor<512xi64>)

  %cst = "tf.Const"() <{value = dense<0.000000e+00> : tensor<f32>}> : () -> tensor<f32>
  %cst_0 = "tf.Const"() <{value = dense<1> : tensor<1xi64>}> : () -> tensor<1xi64>
  %fill = "tf.Fill"(%cst_0, %cst) : (tensor<1xi64>, tensor<f32>) -> tensor<1xf32>
  tf_device.replicate([%0, %fill] as %arg_r0: tensor<1xf32>) {n = 2 : i32} {
    %1 = "tf_device.launch"() <{device = "TPU_REPLICATED_HOST_0"}> ({