// before `StartExecute` is called again. Using `StartExecute` with `Join`
  // allows the caller to schedule computation on multiple ParallelDevices
  // without sequencing those operations (first call `StartExecute` on each
  // parallel device, then call `Join` on each; even if some of the `Join`s
  // return a bad status the caller must run all of the `Join`s or any future
  // `StartExecute`s will deadlock).
  //

TF_Buffer* ProcessGetKeyValueResult(absl::StatusOr<std::string> value,
                                    TF_Status* status) {
  status->status = value.status();
  if (!value.ok()) {
    return nullptr;
  }
  // Caller is responsible to call `TF_DeleteBuffer` to release the buffer.
  TF_Buffer* result = TF_NewBuffer();
  const std::string& value_str = *value;
  void* data = malloc(value_str.length());

  // finished, if any.
  //
  // `cancellation_manager` must live until after `Join` finishes and pending
  // `is_async` operations finish. In addition to allowing the caller to cancel
  // the operation, its `StartCancel` method will be called if op execution
  // fails on any device in order to cancel the others.
  void StartExecute(TFE_Context* context, const char* operation_name,