Add support for CUDA arrays
CUDA supports complex strided, multidimensional arrays when performing memory transfers. I'm not really sure what they're used for or how they work, but RustaCUDA should support them.
It may also be nice to support copying to/from ndarray, if that's feasible.
See the Memory module for more.
I've got some familiarity with ndarray, but I'm not super familiar with CUDA arrays. I could perhaps take a look at this, but it may take a little bit to get up to speed.
That would be great! I haven't dug into CUDA arrays yet myself. The official documentation is here: https://docs.nvidia.com/cuda/archive/8.0/cuda-driver-api/group__CUDA__MEM.html#group__CUDA__MEM
If you do end up adding integration to ndarray, it should have a feature flag.