// 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>

    -> (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

  // CHECK-NEXT:  return [[FIND]] : tensor<*xi64>
  func.return %1 : tensor<*xi64>
}

// -----

// Test for case with int64 -> string hashtable.
func.func @hashtable_int64_to_string(%arg0: tensor<i64>) -> tensor<*x!tf_type.string> {
  %cst = arith.constant dense<"f"> : tensor<!tf_type.string>

module {
  func.func @main() -> tensor<1xi64> {
  %0 = "tfl.custom"() {custom_code = "stablehlo.constant", custom_option = #tfl<const_bytes : "0x76616C75650001020109010101062C022401">} : () -> tensor<1xi64>
  func.return %0 : tensor<1xi64>
  }
}

// CHECK:  module {
// CHECK-NEXT:    func @main() -> tensor<1xi64> {
// CHECK-NEXT:    %[[c0:.+]] = stablehlo.constant dense<2> : tensor<1xi64>
// CHECK-NEXT:    return %[[c0]] : tensor<1xi64>

// CHECK: %[[XLA_CALL_MODULE:.+]] = "tf.XlaCallModule"(%[[CUSTOM_AGGREGATOR_0]], %[[CST]])
// CHECK-SAME: _entry_function = @composite_dot_general_fn_1, _original_entry_function = "composite_dot_general_fn_1"

// -----

func.func @foldDivF64() -> tensor<2xf64> {
  %0 = stablehlo.constant dense<[2.0, 3.0]> : tensor<2xf64>
  %1 = stablehlo.constant dense<[4.0, 6.0]> : tensor<2xf64>
  %2 = stablehlo.divide %0, %1 : tensor<2xf64>
  return %2 : tensor<2xf64>
}

// CHECK-LABEL: foldDivF64
// CHECK: stablehlo.constant dense<5.000000e-01> : tensor<2xf64>

// -----

func.func @foldDivI32() -> tensor<2xi32> {

  %1:4 = "tf.CustomAggregator"(%arg0) {id = "1", calibration_method = 1 : i32, num_bins = 0 : i32, max_percentile = 0.000000e+00 : f32, min_percentile = 0.000000e+00 : f32} : (tensor<8x8x8x8xf32>) -> (tensor<8x8x8x8xf32>, tensor<f32>, tensor<f32>, tensor<*xi64>)
  func.return %0#0, %1#0 : tensor<8x8x8x8xf32>, tensor<8x8x8x8xf32>
}
// CHECK: func @customAggregator

  %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"}> ({

  %2 = "tf.XlaCallModule"(%1#0, %0) <{Sout = [#tf_type.shape<1x3>], dim_args_spec = [], disabled_checks = [], has_token_input_output = false, module = "", platforms = [], version = 5 : i64}> {_entry_function = @composite_dot_general_fn_1, _o...

  func.func @init_all_tables()
  attributes {tf_saved_model.exported_names = ["__tf_saved_model_session_initializer"]} {
    %cst = arith.constant dense<[1, 2, 3, 4]> : tensor<4xi64>
    %cst_0 = arith.constant dense<["a", "b", "c", "d"]> : tensor<4x!tf_type.string>