%8 = "tfl.mul"(%2, %3) {fused_activation_function = "NONE"} : (tensor<4xi32>, tensor<4xi32>) -> tensor<4xi32>

  func.return %5, %6, %7, %8 : tensor<i32>, tensor<4xi32>, tensor<4xi32>, tensor<4xi32>
}

// CHECK-LABEL: @add_dense_splat_int
func.func @add_dense_splat_int() -> tensor<4xi32> {
  %0 = arith.constant dense<[-10, -1, 42, 100]> : tensor<4xi32>

      %outputs_45, %control_46 = tf_executor.island wraps "tf.Const"() {device = "/device:CPU:0", value = dense<3> : tensor<1xi32>} : () -> tensor<1xi32>
      %outputs_47, %control_48 = tf_executor.island wraps "tf.Const"() {device = "/device:CPU:0", value = dense<1> : tensor<1xi32>} : () -> tensor<1xi32>

// CHECK-NEXT:      %18 = "tfl.pseudo_const"() <{value = dense<2> : tensor<1xi32>}> : () -> tensor<1xi32>
// CHECK-NEXT:      %19 = "tfl.concatenation"(%18, %17, %16) <{axis = 0 : i32, fused_activation_function = "NONE"}> : (tensor<1xi32>, tensor<1xi32>, tensor<1xi32>) -> tensor<3xi32>
// CHECK-NEXT:      %20 = mhlo.dynamic_reshape %2, %19 : (tensor<2x3x4x?xf32>, tensor<3xi32>) -> tensor<2x3x?xf32>

  %min = arith.constant dense<0.0> : tensor<16xf32>
  %max = arith.constant dense<255.0> : tensor<16xf32>
  %mini = "tf.Identity"(%min) : (tensor<16xf32>) -> tensor<16xf32>
  %maxi = "tf.Identity"(%max) : (tensor<16xf32>) -> tensor<16xf32>
  %fq = "tf.FakeQuantWithMinMaxVarsPerChannel"(%in, %mini, %maxi) {num_bits = 5, narrow_range = false} : (tensor<3x3x3x16xf32>, tensor<16xf32>, tensor<16xf32>) -> tensor<3x3x3x16xf32>

  %min = arith.constant dense<0.0> : tensor<16xf32>
  %max = arith.constant dense<15.0> : tensor<16xf32>
  %mini = "tf.Identity"(%min) : (tensor<16xf32>) -> tensor<16xf32>
  %maxi = "tf.Identity"(%max) : (tensor<16xf32>) -> tensor<16xf32>
  %fq = "tf.FakeQuantWithMinMaxVarsPerChannel"(%in, %mini, %maxi) {num_bits = 3, narrow_range = false} : (tensor<3x3x3x16xf32>, tensor<16xf32>, tensor<16xf32>) -> tensor<3x3x3x16xf32>

  // CHECK: "tf.Cast"(%arg0) <{Truncate = false}> : (tensor<1xi32>) -> tensor<1xi32>
  %0 = "tf.Cast"(%arg0) {Truncate = false} : (tensor<1x!tf_type.qint32>) -> tensor<1xi32>
  func.return %0: tensor<1xi32>
}

// -----

// CHECK-LABEL: func @cast_op_int32_qint32
func.func @cast_op_int32_qint32(%arg0: tensor<1xi32>) -> tensor<1x!tf_type.qint32> {

      Targs = [tensor<32xf32>, tensor<64xf32>, tensor<16xf32>],
      Tresults = [tensor<32xf32>, tensor<16xf32>]}
      : (tensor<32xf32>, tensor<64xf32>, tensor<16xf32>, tensor<2x!tf_type.string>) -> (tensor<32xf32>, tensor<16xf32>)
    tf_device.return %0#0, %0#1 : tensor<32xf32>, tensor<16xf32>
  }) {device = "/job:localhost/replica:0/task:0/device:TPU:0"} : () -> (tensor<32xf32>, tensor<16xf32>)
  // CHECK-NEXT: tf_device.return
  // CHECK-NEXT: })

    %4 = "tf.LayerNorm"(%a1, %a2, %a3, %a4) {_tfl_quant_trait = "fully_quantizable", device = ""} : (tensor<128x128xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xi32>) -> tensor<128x128xf32>
   "tfl.yield"(%4) : (tensor<128x128xf32>) -> ()
  }) {_tfl_quant_trait = "fully_quantizable", device = ""} : (tensor<128x128xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xi32>) -> tensor<128x128xf32>

    %3 = "tf.Const"() {value = dense<2> : tensor<1xi32>} : () -> tensor<1xi32>
    // expected-remark@+1 {{Cost: 1}}
    %4 = "tf.Const"() {value = dense<1> : tensor<1xi32>} : () -> tensor<1xi32>
    // expected-remark@+1 {{Cost: 1}}
    %5 = "tf.Const"() {value = dense<0> : tensor<1xi32>} : () -> tensor<1xi32>
    // expected-remark@+1 {{Cost: 1}}
    %6 = "tf.Const"() {value = dense<3> : tensor<1xi32>} : () -> tensor<1xi32>

// CHECK-LABEL: func @testBroadcastGradientArgs
func.func @testBroadcastGradientArgs(%s0: tensor<4xi32>, %s1: tensor<4xi32>) -> (tensor<1xi32>, tensor<0xi32>) {
  // CHECK:     tf.BroadcastGradientArgs
  %r0, %r1 = "tf.BroadcastGradientArgs"(%s0, %s1) : (tensor<4xi32>, tensor<4xi32>) -> (tensor<1xi32>, tensor<0xi32>)
  func.return %r0, %r1 : tensor<1xi32>, tensor<0xi32>
}

// -----

// CHECK-LABEL: @acos