// 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

      %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>)

  %1 = "tf.TensorListGetItem"(%0, %arg2, %arg1) {device = "/job:localhost/replica:0/task:0/device:GPU:0"} : (tensor<!tf_type.variant<tensor<1x32xf32>>>, tensor<i32>, tensor<2xi32>) -> tensor<1x32xf32>
  %2 = "tf.TensorListGetItem"(%0, %arg3, %arg1) {device = "/job:localhost/replica:0/task:0/device:GPU:0"} : (tensor<!tf_type.variant<tensor<1x32xf32>>>, tensor<i32>, tensor<2xi32>) -> tensor<1x32xf32>

// result shapes.
// CHECK-LABEL: func @testShapeInvariantWhile
func.func @testShapeInvariantWhile(%arg0: tensor<1x2x3xf32>) -> tensor<1x8x3xf32> {
  %0 = "tf.While"(%arg0) {cond = @cond, body = @body, is_stateless = false, shape_invariant} : (tensor<1x2x3xf32>) -> tensor<1x8x3xf32>
  func.return %0 : tensor<1x8x3xf32>
}

// -----
// WhileRegion tests

// Simple While region
// CHECK-LABEL: testValidWhileRegion

// dimensions into a single dimension. For example,
//
//   %shape = arith.constant dense<[1, 128, 64]> : tensor<3xi32>
//   %reshape = tfl.reshape(%input, %shape) // %input: tensor<128x64xf32>
//   %fc = tfl.fully_connected(%reshape, %filter, %bias)
//           {keep_num_dims = false, weights_format = "DEFAULT"}
//
// can be canonicalized to
//