[Beowulf] standards for GFLOPS / power consumption measurement?
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.
Mark Hahn hahn at physics.mcmaster.caTue May 10 08:13:10 PDT 2005
- Previous message: [Beowulf] standards for GFLOPS / power consumption measurement?
- Next message: [Beowulf] standards for GFLOPS / power consumption measurement?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
> How do you categorize second hand bought systems? > I bought for 325 euro a third dual k7 mainboard + 2 processors. I categorize them as "not worth the bother by most professionals". they are great if you have EP workload and a relatively supply of cheap labor (and I don't mean that derogatorily). dual k7's have a mostly-deserved reputation for being finicky or even flakey, as this list has heard complaints of. that doesn't mean they can't be made to do useful work! most researchers, though, will be reluctant want to invest their own time into fussing with such machines since they're relatively slow and labor-intensive. this is really the essence of Orion's appeal. personally, I think Orion's design is a bit imbalanced, but that just means that I'm exposed to more memory-intensive and tightly-coupled codes than Orion's main customers.
- Previous message: [Beowulf] standards for GFLOPS / power consumption measurement?
- Next message: [Beowulf] standards for GFLOPS / power consumption measurement?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
