// CHECK-NEXT: tf.GatherV2
// CHECK-NEXT: tf.Mul
// CHECK-NEXT: tf.GatherV2
// CHECK-NEXT: tf.Mul
// CHECK-NEXT: tf_mlrt.tf_await
// CHECK-NEXT: tf_mlrt.tf_await
// CHECK-NEXT: tf.TensorListSetItem
// CHECK-NEXT: tf.TensorListSetItem
// CHECK-NEXT: tf_mlrt.tf_promise
// CHECK-NEXT: tf_mlrt.tf_promise
// CHECK-NEXT: return

// CHECK-LABEL: tf.MultiListWhileRegion_cond

  // |item| is expanded to have the same dimension as input_handle and
  // |index| is expanded to [index, 0, 0, ...] as the indices to input_handle.
  // On a high level, it's doing something like:
  // def : Pat<(TensorListSetItem($input_handle, $index, $item)),
  //           (XlaDynamicUpdateSlice($input_handle, ExpandDims($item, 0),
  //              Concat(ExpandDims($index, 0), [0, 0, 0, ...])))>

_Replicate TensorList init ops for correct shape assignments in shape inference_

If we pass same TensorList to a while op as multiple arguments or just use
the same TensorList at multiple places and assign different
TensorListSetItem to elements of TensorList, the shape inference is then
unable to identify the Shape of these args and thus the input TensorList
shape is unidentifiable.

      "TensorListFromTensor",
      "TensorListGather",
      "TensorListGetItem",
      "TensorListLength",
      "TensorListPopBack",
      "TensorListPushBack",
      "TensorListReserve",
      "TensorListSetItem",
      "TensorListSplit",
      "TensorListStack",
      "TensorScatterAdd",
      "TensorScatterMax",
      "TensorScatterMin",
      "TensorScatterSub",
      "TensorScatterUpdate",