Hi - We've been experimenting running julia code on a large Cray XC40 system at the Swiss National Supercomputing Center (CSCS) . It's still too early to really say anything concrete about the performance, but at least as far as getting the code running, the transition from using a laptop or a small cluster to using this large system has been encouragingly smooth.
Most of the time getting things to work was figuring out how to work within the confines of the Cray system, which does not allow direct access to compute nodes (or TCP/IP communication between them). The heavy lifting to make this happen was done by the julia team, notably Amit Murty who expanded the capabilities in MPI.jl There are also challenges associated with monitoring and debugging the code, as many available diagnostic tools involve instrumenting application code, which is not directly applicable to julia's JIT-compiled code. I'll be giving a quick-shot presentation on these topics at JuliaCon in the summer, so it'd be very useful to hear what kinds of things people could do with this emerging capability! -Patrick On Tuesday, April 28, 2015 at 5:12:42 PM UTC-7, Lyndon White wrote: > > Hi, > > I have a big numerical problem that julia is nice for. > But I really want to farm it out over a few hundren cores. > > I know my local research supercomputing provider (iVec since I am in > Western Australia), > prefers it if you are running programs in C or Fortran. > > But I know they have run things in Python and Matlab. > I know they losely appreciate the trade off between development time and > CPU time. > But I think there main hesitation is the knowledge that the CPU cycles > python wastes could be going to another project, > and that other project could be curing cancer etc. > > Julia on the other hand is comparable to C or Fortran, so that objection > is out. > It is on the other hand imature and not exactly well known. > (I would not be surpised if i was the only user in my universivy. > > It would help any argument I might have, > or explination I need to render if I could say: They are using it on the > super-computers in X. > > Have you, or do you know of anyone who used it on supercomputers / > medium-large clusters? > > Did it go well? > What are the pitfalls >
