// CHECK-LABEL: func @parallel_execute_with_tiled_input
  // CHECK-SAME: (%[[ARG_0:[a-z0-9]*]]: tensor<128x10xf32>, %[[ARG_1:[a-z0-9]*]]: tensor<128x10xf32>, %[[ARG_2:[a-z0-9]*]]: tensor<*xi32>, %[[ARG_3:[a-z0-9]*]]: tensor<*xi32>)
  func.func @parallel_execute_with_tiled_input(%arg0: tensor<128x10xf32>, %arg1: tensor<128x10xf32>, %arg2: tensor<*xi32>, %arg3: tensor<*xi32>) -> (tensor<*xi32>, tensor<*xi1>) {
    // CHECK: tf_device.replicate

func.func @expandDims(%arg0: tensor<2x2xf32>, %arg1: tensor<i32>) -> tensor<1x2x2xf32> {
  %0 = "tf.ExpandDims"(%arg0, %arg1) : (tensor<2x2xf32>, tensor<i32>) -> tensor<1x2x2xf32>
  func.return %0 : tensor<1x2x2xf32>

// CHECK-LABEL:expandDims
// CHECK:  "tfl.expand_dims"(%arg0, %arg1) : (tensor<2x2xf32>, tensor<i32>) -> tensor<1x2x2xf32>
}

func.func @squeezeDefault(%arg0: tensor<1x2x2xf32>) -> tensor<2x2xf32> {

      %2 = "tf.Cast"(%arg0) {Truncate = false} : (tensor<1x8x2xi32>) -> tensor<1x8x2xf32>
      tf_device.return %2 : tensor<1x8x2xf32>
    // CHECK: () -> tensor<1x8x2xf32>
    }) {device = "/device:CPU:0"} : () -> tensor<*xf32>
    // CHECK: "tf.Cast"(%{{.*}}) <{Truncate = false}> : (tensor<1x8x2xf32>) -> tensor<*xf32>
    // CHECK: (tensor<i32>, tensor<1x8x2xf32>) -> (tensor<1x8x1xf32>, tensor<1x8x1xf32>)