Multithreading OpenCV GPU Crash
My multithreaded application (using C++, OpenCV 2.4.10, CUDA 5.2) crashes frequently, the debugger hangs always at a "cudaSafeCall( cudaDeviceSynchronize() );" call.
But the "cudaDeviceSynchronize" call is performed from different origins: cv::gpu::resize (resize.cu - line 265), cv::gpu::abs (transform_detail.hpp - line 364), cv::gpu::threshold (transform_detail.hpp - line 364).
I'm using a single GPU device and the default GPU device context (NVIDIA GeForce GTX 960). All application threads call OpenCV GPU functions and use the same GPU device context.
What I'm doing wrong? Or is there are common problem with multithreaded applications using OpenCV GPU support?
Afaik the OpenCV CUDA code is NOT thread safe for the moment by itself, which means that you are accessing the device at the same time from different threads. This will cause these errors in my experience.