func.return %0 : tensor<3x2x3xi16>
}

// -----

func.func @testBitcast_v8(%arg0: tensor<3x2xi32>) -> tensor<3x2xi16> {
  // expected-error @+1 {{rank of input tensor is 2. rank of output tensor is expected to be 3, instead of 2.}}
  %0 = "tf.Bitcast"(%arg0) : (tensor<3x2xi32>) -> tensor<3x2xi16>
  func.return %0 : tensor<3x2xi16>
}

// -----

  func.return %0: tensor<3x2xf16>
}

func.func @sparse_qu8() -> tensor<3x2x!quant.uniform<u8<1:255>:f32, 1.0>> {
  // CHECK-LABEL: @sparse_qu8

  func.return %0: tensor<3x2xf16>
}

func.func @sparse_qu8() -> tensor<3x2x!quant.uniform<u8<1:255>:f32, 1.0>> {
  // CHECK-LABEL: @sparse_qu8

func.func @bitcastI32ToI16(%arg0: tensor<8xi32>) -> tensor<8x2xi16> {
  %0 = "tf.Bitcast"(%arg0) : (tensor<8xi32>) -> tensor<8x2xi16>
  func.return %0 : tensor<8x2xi16>

// CHECK-LABEL: bitcastI32ToI16
// CHECK: %[[RES0:.*]] = "tfl.bitcast"(%arg0) : (tensor<8xi32>) -> tensor<8x2xi16>
// CHECK:  return %[[RES0]] : tensor<8x2xi16>
}

func.func @bitcastI16ToUI32(%arg0: tensor<8x2xi16>) -> tensor<8xui32> {

// CHECK:         }
func.func @select_multidimensional(%arg0: tensor<3x2xi1>, %arg1: tensor<3x2xi32>, %arg2: tensor<3x2xi32>) -> tensor<3x2xi32> {
  %0 = "mhlo.select"(%arg0, %arg1, %arg2) : (tensor<3x2xi1>, tensor<3x2xi32>, tensor<3x2xi32>) -> tensor<3x2xi32>
  func.return %0 : tensor<3x2xi32>
}

// CHECK-LABEL:   func @selectv2(
// CHECK-SAME:                   %[[VAL_0:.*]]: tensor<2xi1>,

// RUN: tf-mlir-translate -mlir-to-graph %s -o - | FileCheck %s

func.func @main() -> (tensor<1x2xf16>, tensor<2xf16>) {
  %graph:2 = tf_executor.graph {
    %0:2 = tf_executor.island wraps "tf.Const"() {device = "", dtype = "tfdtype$DT_HALF", value = dense<1.0> : tensor<1x2xf16>} : () -> tensor<1x2xf16> loc("const1")
// CHECK: node {
// CHECK-NEXT: name: "const1"
// CHECK-NEXT: op: "Const"
// CHECK: dtype: DT_HALF
// CHECK: half_val: 15360

func.func @main(tensor<3x2xi32>) -> tensor<3x2xi32> {
^bb0(%arg0: tensor<3x2xi32>):
  %0 = "arith.constant"() {name = "Const2", value = dense<10> : tensor<i32>} : () -> tensor<i32>
  %1 = "tfl.add"(%0, %arg0) {fused_activation_function = "NONE", name = "add"} : (tensor<i32>, tensor<3x2xi32>) -> tensor<3x2xi32>
  func.return %1 : tensor<3x2xi32>

// CHECK-NEXT: }

  %0 = "tfl.pseudo_const" () {value = dense<[[1, 2], [3, 4], [5, 6]]> : tensor<3x2xi32>} : () -> tensor<3x2xi32> loc("Const")
  %1,%control_1 = tfl.control_node controls "tfl.sub" (%arg0, %0) {fused_activation_function = "RELU6"} : (tensor<3x2xi32>, tensor<3x2xi32>) -> tensor<3x2xi32> loc("sub")
  %2 = "arith.constant" () {value = dense<10> : tensor<i32>} : () -> tensor<i32> loc("SameNameAsOutput")

  // CHECK-NEXT:     [[SCALAR:%.*]] = "tfl.pseudo_const"() <{value = dense<10> : tensor<i32>}> : () -> tensor<i32>
  // CHECK-NEXT:     [[ADD:%.*]] = tfl.add([[SCALAR]], [[SUB]]) {fused_activation_function = "NONE"} : (tensor<i32>, tensor<3x2xi32>) -> tensor<3x2xi32>
  // CHECK-NEXT:     return [[ADD]] : tensor<3x2xi32>

  %0 = "tfl.pseudo_const" () {value = dense<[[1, 2], [3, 4], [5, 6]]> : tensor<3x2xi32>} : () -> tensor<3x2xi32> loc("Const")

func.func @main(%arg0: tensor<3x2xf32>) -> tensor<3x2xi32> {
  // CHECK-LABEL: @main
  // CHECK: "tfl.bucketize"(%arg0) <{boundaries = [0.000000e+00 : f32, 1.000000e+01 : f32, 1.000000e+02 : f32]}> : (tensor<3x2xf32>) -> tensor<3x2xi32>
  %0 = "tfl.bucketize"(%arg0) {boundaries = [0.0 : f32, 10.0 : f32, 100.0 : f32]} : (tensor<3x2xf32>) -> tensor<3x2xi32>
  func.return %0 : tensor<3x2xi32>