Improvements to/small issues with communication

[clarkedavida]

1. It would be useful to add a short test to the CommunicationBase setup. This way with each run we can be sure e.g. cuda-aware mpi and cuda p2p are working as intended.
2. Apparently the current cuda-aware mpi check only checks if it's supported, rather than used. (A short-term fix to this could be to update the status text to say "supported" rather than "used".)
3. There is a comment "We can only check this reliably for openmpi. TODO: find out how to do it for other mpi libraries" that needs to be resolved.
4. the SpinorHaloTest reports FAILED when using cuda-awari mpi OFF in conjunction with cuda-p2p ON

[luhuhis]

It would be useful to add a short test to the CommunicationBase setup. This way with each run we can be sure e.g. cuda-aware mpi and cuda p2p are working as intended.

@lukas-mazur, wouldn't that be as simple as calling the functions run0 and run1 from main_cudaawareMPItest to CommunicationBase::init()?

[luhuhis]

We could also somehow incorporate https://github.com/lukas-mazur/cudaAwareMPITest into the setup