[Beowulf] RE: Capitalization Rates - How often should you replace a cluster? (resent - 1st sending wasn't posted ).
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Mike Davis jmdavis1 at vcu.eduTue Jan 20 07:39:27 PST 2009
- Previous message: [Beowulf] RE: Capitalization Rates - How often should you replace a cluster? (resent - 1st sending wasn't posted ).
- Next message: [Beowulf] RE: Capitalization Rates - How often should you replace a cluster? (resent - 1st sending wasn't posted ).
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
Lux, James P wrote: > > On 1/19/09 11:14 PM, "Jon Aquilina" <eagles051387 at gmail.com> wrote: > > >> in all honesty is there a need really to replace the cluster. why not just add >> onto it? >> >> > > 1) If all the processors work at the same speed, it's "easier" to distribute > work among them, especially if there are synchronization steps periodically, > where all the work quanta need to be aligned and redistributed for the next > step. > > 2) Newer machines do more computing/kWh of electricity, in general, so it > reduces operating costs. > Another reason to replace machines is upkeep and staff time. Older machines fail more often and require more attention than newer ones.
- Previous message: [Beowulf] RE: Capitalization Rates - How often should you replace a cluster? (resent - 1st sending wasn't posted ).
- Next message: [Beowulf] RE: Capitalization Rates - How often should you replace a cluster? (resent - 1st sending wasn't posted ).
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
