Guard devctx

paddle/fluid/platform/device_context.cc

@@ -159,6 +159,7 @@ CUDADeviceContext::~CUDADeviceContext() {
 Place CUDADeviceContext::GetPlace() const { return place_; }
 
 void CUDADeviceContext::Wait() const {
+  std::lock_guard<std::mutex> guard(this->mutex_);
   PADDLE_ENFORCE(cudaStreamSynchronize(stream_));
   PADDLE_ENFORCE(cudaGetLastError());
 }

paddle/fluid/platform/device_context.h

@@ -110,6 +110,7 @@ class CUDADeviceContext : public DeviceContext {
   int compute_capability;
   int multi_process;
   int max_threads_per_mp;
+  mutable std::mutex mutex_;
 };
 
 template <>