On Sat, 26 Jun 2010, Edward Ned Harvey wrote: > I am aware of this. I've been a long time user and supporter of dells and > custom built blackboxes, workstations and servers, running usually linux of > various kinds, clustered via SGE.
Hi Edward. I misunderstood sorry. I read your original email as 'I'm getting in to HPC' and responded as such :) > The root concept is: Break away from the assumption of xeon or equivalent > amd processors. Jump down to the super small, super low-power, super cheap > class of processors, atom, arm, etc... and use them to beat the xeons for > some situations, such as distributed work load, or server virtualization. I'm quite open to this possibility. One problem with using many small processors is that many problems _are not_ heavily parallelizable[1]. If you can break your task into thousands of subtasks then great - it may well be an good choice but there are alot of variables involved. [1] Waaaay back at University I got to code on a MASPAR[2] for several courses, which was great fun. 4096 CPUs in a 64x64 array. Suffice to say the programming assignments did involve highly parallelizable tasks like heat flow over a surface :) [2] http://en.wikipedia.org/wiki/Maspar Cheers, Rob -- Email: [email protected] Linux counter ID #16440 IRC: Solver (OFTC & Freenode) Web: http://www.practicalsysadmin.com Open Source: The revolution that silently changed the world _______________________________________________ Tech mailing list [email protected] http://lopsa.org/cgi-bin/mailman/listinfo/tech This list provided by the League of Professional System Administrators http://lopsa.org/
