From: Ajasja Ljubetiè (ajasja.ljubetic_at_gmail.com)
Date: Thu Jun 02 2011 - 09:46:55 CDT
> Sorry for the TOFU style reply. I am working on our largest cluster right
> now hoping to salvage a busted raid.
No problem (I did have to google "TOFU style reply" though :) Good luck with
I would go for all 32-core opteron and get time on GPU clusters externally.
> GPU machines are currently much less in demand than conventional ones, so it
> is much easier to get time on them (and more). At best I would just buy one
> GPU node for learning and testing. Unless you want to start a career as a
> sysadmin or HPC specialist, you are better off buying something that is less
> work to run well so you can focus on your research.
I'll definitely buy one GPU node (It's fun to learn). But you are right -
it's not exactly the point of my PHD...
In re: benchmarks. They are rarely using a representative data set and only
> use som "kernel" of NAND and other codes. This is what vendors like since
> this just gives you a single number to compare to. In real life you need a
> balanced system and that is more than the fastest CPU.
Thanks for the advice,
I'll go browsing for prices now:)
This archive was generated by hypermail 2.1.6 : Wed Feb 29 2012 - 15:57:13 CST