CHECK_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
    TFE_Execute(matmul, &retvals[0], &num_retvals, status);
    CHECK_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
    if (state.iterations() >= state.max_iterations && async) {
      TFE_Executor* executor = TFE_ContextGetExecutorForThread(ctx);
      TFE_ExecutorWaitForAllPendingNodes(executor, status);
      ASSERT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);

// an array of length at least `max_inputs` (ideally set to
// TF_OperationNumInputs(oper)).  Beware that a concurrent
// modification of the graph can increase the number of inputs of
// an operation.
TF_CAPI_EXPORT extern void TF_OperationAllInputs(TF_Operation* oper,
                                                 TF_Output* inputs,
                                                 int max_inputs);