// CHECK-DAG: %[[SIGN:.*]] = "tf.Sign"(%[[PROX]]) : (tensor<4xf32>) -> tensor<4xf32>
    // CHECK-DAG: %[[ABS:.*]] = "tf.Abs"(%[[PROX]]) : (tensor<4xf32>) -> tensor<4xf32>
    // CHECK-DAG: %[[SCALED_L1:.*]] = "tf.Mul"(%[[ADAGRAD_LR]], %[[L1]]) : (tensor<4xf32>, tensor<f32>) -> tensor<4xf32>
    // CHECK-DAG: %[[PROX_NEW:.*]] = "tf.Sub"(%[[ABS]], %[[SCALED_L1]]) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>

  %1 = "tf.TPUCompileMlirAndExecute"(%0) {metadata = "metadata", mlir_module = "mlir_module", operandSegmentSizes = array<i32: 1, 0>, producer_name = "producer_name"} : (tensor<f32>) -> tensor<i32>
  func.return %1 : tensor<i32>
}

// -----

func.func @executeop_input_same_execute_op(%arg0: tensor<i32>, %arg1: tensor<2xf32>) -> (tensor<i32>) {

      "tfl.yield"(%wrap_result): (tensor<1xf32>)->()
      }): (tensor<1xf32>, tensor<1xf32>) -> (tensor<1xf32>)
  %tmp3 = "tfl.add"(%const, %tmp2) { fused_activation_function = "NONE" } : (tensor<1xf32>, tensor<1xf32>) -> (tensor<1xf32>)
  %tmp4 = "tf.AddV2"(%tmp2, %tmp2) { device = "" } : (tensor<1xf32>, tensor<1xf32>) -> (tensor<1xf32>)

    %0 = "tf.Div"(%arg1, %cst_0) : (tensor<?x?xf32>, tensor<f32>) -> tensor<?x?xf32>
    %1 = "tf.AddV2"(%0, %cst_1) : (tensor<?x?xf32>, tensor<f32>) -> tensor<?x?xf32>
    %2 = "tf.Floor"(%1) : (tensor<?x?xf32>) -> tensor<?x?xf32>
    %3 = "tf.ClipByValue"(%2, %cst_5, %cst_6) : (tensor<?x?xf32>, tensor<f32>, tensor<f32>) -> tensor<?x?xf32>
    %4 = "tf.Cast"(%3) {Truncate = false} : (tensor<?x?xf32>) -> tensor<?x?xi8>

  %relu = "tf.Relu"(%y#0) : (tensor<8x8x8x8xf32>) -> tensor<8x8x8x8xf32>
  func.return %relu : tensor<8x8x8x8xf32>
}

// CHECK-LABEL: func @FusedBatchNormAddRelu
func.func @FusedBatchNormAddRelu(%arg0: tensor<8x8x8x8xf32>, %arg1: tensor<8xf32>, %arg2: tensor<8xf32>, %arg3: tensor<8xf32>, %arg4: tensor<8xf32>) -> (tensor<8x8x8x8xf32>) {

  // Confirm that attributes that cannot be stored in the flatbuffer options
  // for a given operator are dropped silently.
  %1 = "tfl.squared_difference"(%arg0, %0) {fused_activation_function = "NONE"} : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("squared_difference")
  %2 = "tfl.mul"(%arg0, %1) {fused_activation_function = "NONE"} : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("mul")

    %add = "tf.AddV2"(%call, %call) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
    "tf.Yield"(%call, %add) : (tensor<4xf32>, tensor<4xf32>) -> ()
  },  {
    %call_0 = func.call @test_if_else1(%arg1) : (tensor<4xf32>) -> tensor<4xf32>
    "tf.Yield"(%call_0, %call_0) : (tensor<4xf32>, tensor<4xf32>) -> ()
  }) {is_stateless = false} : (tensor<i1>) -> (tensor<*xf32>, tensor<4xf32>)

module {
func.func @main(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>, %arg2: tensor<1xf32>, %arg3: tensor<1xf32>) -> tensor<2x1xf32> attributes {tf.entry_function = {inputs = "input0,input1,input2,input3", outputs = "output"}} {
  %0 = "tfl.add"(%arg0, %arg1) {fused_activation_function = "RELU6"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
  %1 = "tfl.mul"(%0, %arg2) {fused_activation_function = "RELU6"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

      %outputs_9, %control_10 = tf_executor.island wraps "tf.Mul"(%outputs_7, %outputs) {T = "tfdtype$DT_FLOAT", _tpu_replicate = "cluster", device = "", name = "mul"} : (tensor<0xf32>, tensor<f32>) -> tensor<0xf32>
      %outputs_11, %control_12 = tf_executor.island wraps "tf.Placeholder"() {device = "", dtype = "tfdtype$DT_FLOAT", name = "y", shape = "tfshape$dim { }"} : () -> tensor<0xf32>

  func.return %1 : tensor<1xf32>
}

func.func @cond_true(%arg0: tensor<*xf32>, %arg1: tensor<*xf32>) -> tensor<*xf32> {
  %0 = tfl.add %arg0, %arg1 {fused_activation_function = "NONE"} : tensor<*xf32>
  func.return %0 : tensor<*xf32>
}

func.func @cond_false(%arg0: tensor<*xf32>, %arg1: tensor<*xf32>) -> tensor<*xf32> {