[Beowulf] simplistic prime factorization benchmarking
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.
Vincent Diepeveen diep at xs4all.nlTue May 10 16:07:44 PDT 2005
- Previous message: [Beowulf] Re: Beowulf Digest, Vol 15, Issue 16
- Next message: [Beowulf] Re: quick and dirty method for starting job on another node?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
hi, Prime factorization benchmarks (own hobby software in order to try to win http://www.eff.org/awards/coop.html) : opteron 2.2Ghz : 46.840000 seconds itanium2 1.5Ghz : 59.180000 seconds k7 MP2600 : 93.520000 seconds P4 2.8Ghz Xeon : 137.919998 seconds (it is embarrassingly parallel software) RAM doesn't matter for the software, it's just working within L1 cache at any processor. It's of course like all prime type software utmost tiny. I do not know about IA64, but for x86 it uses 'cmov' type instructions of course, in order to avoid branches. Vincent Vincent
- Previous message: [Beowulf] Re: Beowulf Digest, Vol 15, Issue 16
- Next message: [Beowulf] Re: quick and dirty method for starting job on another node?
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list