On 2012/12/17 12:30, Mark Hahn wrote: >> Thanks for the information. I would like to set up RPi cluster for some >> bioinformatics jobs like sequences alignment and sequences operations. > > you really need to look at where your code is spending its time. > the seq stuff I see is quite IO-intensive, sometimes memory-intensive. How do I know if the application is IO-intensive or memory-intensive? Any tools to measure that? > >> And I would use OGS(Open Grid Scheduler) as DRM to manage those nodes. I > > it hardly matters. for non-shared clusters, full-on scheduers are > massive > overkill. > >> do know that ARM processors cannot provide powerful FP computing so I'm > > let's be honest: they do not provide high values of any metric. > they are relatively slow in any performance metric, low memory, > normally combined with low-performance IO. low power as well, > of course, which is their reason-for-existence. > >> One more thing, I would like to know what field is proper for ARM >> processors. > > uh, the field where they are being used: embedded mobile. the point > is that mobile implies dramatic power sensitivity. to some degree, > there are some datacenter-ish workloads that can use ARM effectively - > certain kinds of large-scale web-related in-memory servers. but it's > unclear > how much of that is happening yet, since there are > infrastructure/packaging > issues.
_______________________________________________ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
