Use default stream instead of a new stream per CudaDevice

[Corey Lowman]

Instantiating multiple devices creates multiple streams, and there is tricky synchronization problems between them.

[Max Obreiter]

is it generally a problem to synchronize multiple devices?

[Max Obreiter]

and isn't the default stream non-async (but only for non-explicit async ops?)

[Corey Lowman]

By device in description I meant cudarc::CudaDevice. Each of these will have its own stream at the moment