[Beowulf] Re: Re: Re: Home beowulf - NIC latencies (Patrick Geoffray)
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.
Andrew Piskorski atp at piskorski.comFri Feb 18 04:45:28 PST 2005
- Previous message: [Beowulf] Re: Re: Re: Home beowulf - NIC latencies (Patrick Geoffray)
- Next message: [Beowulf] Block send mpi
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Tue, Feb 15, 2005 at 10:28:10AM +0100, Ole W. Saastad wrote: > Patrick Geoffray wrote: > > The one with the best potential would be to use HyperThreading on > > Intel chips to have a polling thread burning cycles continuously; > The simple finding is that the kinetics program got somewhat more > than 70% of the CPU cycles and that the polling waisted close to > 30% of the CPU cycles, 30% is not for free. Using what Linux kernel? Using what feature to tell the kernel, "Please run this polling process only on the extra HyperThreaded virtual CPU, never on the real CPU." ? -- Andrew Piskorski <atp at piskorski.com> http://www.piskorski.com/
- Previous message: [Beowulf] Re: Re: Re: Home beowulf - NIC latencies (Patrick Geoffray)
- Next message: [Beowulf] Block send mpi
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
