Multiple devices: Should you do cudaSetDevice() before every cuBLAS call?

[alexgg]

http://docs.nvidia.com/cuda/cublas/#cublas-context says:

The device associated with a particular cuBLAS context is assumed to remain unchanged between the corresponding cublasCreate() and cublasDestory() calls. In order for the cuBLAS library to use a different device in the same host thread, the application must set the new device to be used by calling cudaSetDevice() and then create another cuBLAS context, which will be associated with the new device, by calling cublasCreate().

However, it doesn’t say whether the thread should make sure that the current device ID is correctly set before every cuBLAS library call. Should it?

I find that if it doesn’t, cuBLAS returns error code 13, and works fine otherwise.