[Feature]: CUDA Support

[JTHesse]

What are you trying to do and how would you want to do it differently?

PeriLab should allow utilizing GPUs https://cuda.juliagpu.org/stable/

Is it something you currently cannot do? Is this related to an issue/problem?

No response

Implementation details

CUDA.jl should allow the needed features. In the future CUDA aware MPI also worth looking into.

Would you be willing to submit a PR?

Yes