Charm++ outside HPC

Question

Does anyone has used Charm++ (http://charm.cs.uiuc.edu/research/charm/) for parallelization outside of HPC (Supercomputers)?

If so, can you tell me about the experience.

Thanks

Answer 1

I'm one of the lead developers of Charm++. Our use cases all center on application users getting the highest performance from whatever hardware they have available to them - really, that's what any sort of parallel computing is about.

For a very large portion of users, that means simply using all of the cores on a multicore desktop workstation or laptop. Many more also use simple Linux clusters with commodity network hardware (Ethernet or Infiniband). These are usually fairly small systems, up to a few dozen nodes - hardly a supercomputer!

We've demonstrated applications for domains as diverse as graphics, resource allocation (e.g. planning, scheduling, combinatorial optimization), applied computer vision, and more. Other users have demonstrated volunteer computing applications using Charm++ (think like SETI@Home or Folding@Home).