diff --git a/paddle/operators/nccl/nccl_gpu_common.h b/paddle/operators/nccl/nccl_gpu_common.h
index 96b3bb801af6ffc0ebe18485dec8700f3757d814..4a375fcc36a1f07287332aed985de132f94d5929 100644
--- a/paddle/operators/nccl/nccl_gpu_common.h
+++ b/paddle/operators/nccl/nccl_gpu_common.h
@@ -1,3 +1,17 @@
+/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+   http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License. */
+
 #pragma once
 
 #include <algorithm>
@@ -106,5 +120,5 @@ class NCCLManager {
       comm_table;
 };
 
-}  // namespace operators
+}  // namespace platform
 }  // namespace paddle
diff --git a/paddle/operators/nccl/nccl_gpu_common_test.cc b/paddle/operators/nccl/nccl_gpu_common_test.cc
index 9b46ea31ba1ae8411a766b7eb25009b38b3e4b0a..6f6a4ac886ddc9b45de38b06b0968fa07f45815d 100644
--- a/paddle/operators/nccl/nccl_gpu_common_test.cc
+++ b/paddle/operators/nccl/nccl_gpu_common_test.cc
@@ -6,9 +6,12 @@
 #include <thread>
 #include <vector>
 
+namespace paddle {
+namespace platform {
+
 TEST(WaitGroup, wait) {
   WaitGroup wg;
-  auto run_thread = [](int idx) {
+  auto run_thread = [&wg](int idx) {
     wg.Add(1);
     std::this_thread::sleep_for(std::chrono::seconds(1));
     wg.Done();
@@ -20,4 +23,11 @@ TEST(WaitGroup, wait) {
     ths.emplace_back(std::thread(run_thread, i));
   }
   wg.Wait();
+
+  for (int i = 0; i < TNUM; ++i) {
+    ths[i].join();
+  }
 }
+
+}  // namespace platform
+}  // namespace paddle