tf_device.return %5 : tensor<i1>
      }, {
        %5 = "tf.opC"(%1#0) : (tensor<i1>) -> tensor<i32>
        tf_device.return %5 : tensor<i32>
      }) {} : () -> (tensor<i1>, tensor<i32>)
      tf_executor.yield %4#0, %4#1 : tensor<i1>, tensor<i32>
    }
    tf_executor.fetch %3#0, %3#1 : tensor<i1>, tensor<i32>
  }
  func.return
}

// CHECK:      [[INPUT_A:%.+]], {{%.+}} = tf_executor.island {

  %0 = "tfl.dequantize"(%arg0) : (tensor<1000x1000x!quant.uniform<i8:f32, 7.812500e-03>>) -> tensor<1000x1000xf32>
  %1 = "tfl.gather"(%0, %arg1) {axis = 0 : i32, batch_dims = 0 : i32}: (tensor<1000x1000xf32>, tensor<1x1xi32>) -> tensor<1x1x1000xf32>
  func.return %1 : tensor<1x1x1000xf32>

// CHECK-NEXT: tfl.gather
// CHECK-NEXT: tfl.dequantize
}

      tf_executor.yield %identity_n#0
    }
    tf_executor.fetch %island_0_result, %island_1_result : tensor<i32>, tensor<i32>
  }
  return %graph_results#0, %graph_results#1 : tensor<i32>, tensor<i32>
}
```

will be transformed into:

```mlir
func @my_fn(%arg0: tensor<i32>, %arg1: tensor<i32>) -> (tensor<i32>, tensor<i32>) {

  %next_index = "tf.AddV2"(%index, %one) {device = "/job:localhost/replica:0/task:0/device:CPU:0"} : (tensor<i32>, tensor<i32>) -> tensor<i32>

        %b = "tf.opB"(%a) : (tensor<i1>) -> tensor<i32>
        %c = "tf.opC"(%b) : (tensor<i32>) -> tensor<f32>
        tf_device.return %c, %b : tensor<f32>, tensor<i32>
      }) {device = "CPU:0"} : () -> (tensor<f32>, tensor<i32>)
      %d = "tf.opD"() : () -> tensor<i1>
      tf_executor.yield %a, %launch#0, %launch#1, %d : tensor<i1>, tensor<f32>, tensor<i32>, tensor<i1>
    }
    tf_executor.fetch
  }
  func.return
}

    %4:2 = tf_executor.island wraps "tf.Mul"(%2#1, %2#0) {T = "tfdtype$DT_INT32", device = ""} : (tensor<i32>, tensor<i32>) -> tensor<i32> loc("Square")
    %5:3 = tf_executor.Merge %3#0, %4#0 : tensor<i32> {device = "", N = 2, T = "tfdtype$DT_INT32"} loc("Merge")
    tf_executor.fetch
  }
  func.return

func.func @multiple_return(%arg0 : tensor<*xi32>, %arg1 : tensor<i32>) -> (tensor<*xi32>, tensor<*xi32>) {
  %1 = "tf.Add"(%arg0, %arg1) {} : (tensor<*xi32>, tensor<i32>) -> tensor<*xi32>
  %2 = "tf.Add"(%1, %arg1) {} : (tensor<*xi32>, tensor<i32>) -> tensor<*xi32>
  func.return %1, %2 : tensor<*xi32>, tensor<*xi32>
}

// CHECK-LABEL: func @multiple_return
// CHECK-SAME: (%[[ARG0:.*]]: tensor<*xi32>, %[[ARG1:.*]]: tensor<i32>) -> (tensor<*xi32>, tensor<*xi32>) {

  %conv = "tfl.conv_2d"(%0, %w, %b) {dilation_h_factor = 1 : i32, dilation_w_factor = 1 : i32, fused_activation_function = "NONE", padding = "SAME", stride_h = 2 : i32, stride_w = 2 : i32} : (tensor<1x224x224x3xf32>, tensor<64x3x3x3xf32>, tensor<64xf32>) -> tensor<1x112x112x64xf32>

      tf_executor.yield %1#1, %1#0 : tensor<i32>, tensor<i32>
    }
    tf_executor.fetch
  }
  func.return
}

          tf_device.return %4 : tensor<i64>
        }) : () -> (tensor<i32>, tensor<i64>)
        tf_device.return %3#0, %3#1 : tensor<i32>, tensor<i64>
      }
      tf_executor.yield %2#0, %2#1, %2#2, %2#3 : tensor<i32>, tensor<i32>, tensor<i64>, tensor<i64>
    }
    tf_executor.fetch %1#0, %1#1, %1#2, %1#3 : tensor<i32>, tensor<i32>, tensor<i64>, tensor<i64>
  }
  func.return
}