‘cudaThreadSynchronize’ is deprecated

参考链接：https://stackoverflow.com/questions/13485018/cudastreamsynchronize-vs-cudadevicesynchronize-vs-cudathreadsynchronize

Windows的CUDA版本：

C:\>nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2016 NVIDIA Corporation
Built on Mon_Jan__9_17:32:33_CST_2017
Cuda compilation tools, release 8.0, V8.0.60

Linux的CUDA版本

wlsh@wlsh-ThinkStation:~$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Fri_Feb__8_19:08:17_PST_2019
Cuda compilation tools, release 10.1, V10.1.105

有一个sample代码包含cudaThreadSynchronize，当我在Windows正常运行，转到Linux报下面的错误

add.cu:122:36: warning: ‘cudaError_t cudaThreadSynchronize()’ is deprecated [-Wdeprecated-declarations]
     cudaStatus = cudaThreadSynchronize();  
                                    ^
/usr/local/cuda/bin/../targets/x86_64-linux/include/cuda_runtime_api.h:955:46: note: declared here
 extern __CUDA_DEPRECATED __host__ cudaError_t CUDARTAPI cudaThreadSynchronize(void);

通过上述解决链接解决了问题：

cudaThreadSynchronize在cuda10.0以后被弃用了

Note that this function is deprecated because its name does not reflect its behavior. Its functionality is similar to the non-deprecated function cudaDeviceSynchronize(), which should be used instead.

随后下面解释了三个function的区别：

These are all barriers. Barriers prevent code execution beyond the barrier until some condition is met.

1. cudaDeviceSynchronize() halts execution in the CPU/host thread (that the cudaDeviceSynchronize was issued in) until the GPU has finished processing all previously requested cuda tasks (kernels, data copies, etc.)
2. cudaThreadSynchronize() as you've discovered, is just a deprecated version of cudaDeviceSynchronize. Deprecated just means that it still works for now, but it's recommended not to use it (use cudaDeviceSynchronize instead) and in the future, it may become unsupported. But cudaThreadSynchronize() and cudaDeviceSynchronize() are basically identical.
3. cudaStreamSynchronize() is similar to the above two functions, but it prevents further execution in the CPU host thread until the GPU has finished processing all previously requested cuda tasks that were issued in the referenced stream. So cudaStreamSynchronize() takes a stream id as its only parameter. cuda tasks issued in other streams may or may not be complete when CPU code execution continues beyond this barrier.