Hi! A few questions:

- How do you deal with software that has been previously run with coarse grained parallelism, optimized for Multicore/Multinode x86? In my experience, GPGPU porting often leads to a tedious, mostly mechanical conversion from coarse grained to fine grained, which usually includes privatizing all your data manually in your parallel domains.

- Can you do multinode / multi-GPU without wrapping everything in MPI?

- Can ArrayFire also run on CPU clusters?

- How do you deal with different storage orders? Up until now, GPUs often require a different storage order than CPUs, (wide vs. narrow vector processor) - and how does that factor into the last point?

Sidenote: I've been dealing with above problems in a Fortran based research project and have created a preprocessor framework[1] to deal with it.

[1]https://github.com/muellermichel/Hybrid-Fortran

GPUs love hashing things, do you think ArrayFire would make that easy to do? I would LOVE to use the library to create an opensource GPU cracking program. Hashcat is amazing but is closed source. I am giddy with excitement at the prospect. Thanks!

Which libraries are your competitors and why would ArrayFire be better than these?