[Beowulf] HPL on an ad-hoc cluster
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.
Lombard, David N dnlombar at ichips.intel.comThu Mar 8 09:05:56 PST 2007
- Previous message: [Beowulf] HPL on an ad-hoc cluster
- Next message: [Beowulf] number of NFS daemons
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Wed, Mar 07, 2007 at 06:12:33PM +0200, Olli-Pekka Lehto wrote: > I'm currently evaluating the possibility of building a ad-hoc cluster > (aka. flash mob) at a large computer hobbyist event using Linux live > CDs. The "cluster" would potentially feature well over a thousand > personal computers connected by a good GigE -network. > Take a look at MapReduce as a mechanism to do some suitable analysis that you still need to define. MR will handle the variabilities of your cluster nicely. Tuning the work packages so the slowest nodes can complete their job while being sufficiently large for the fastest nodes nodes could be interesting. A good starting point is <http://en.wikipedia.org/wiki/MapReduce> -- David N. Lombard, Intel, Irvine, CA I do not speak for Intel Corporation; all comments are strictly my own.
- Previous message: [Beowulf] HPL on an ad-hoc cluster
- Next message: [Beowulf] number of NFS daemons
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
