[Beowulf] Re: SMPs + One processor machines = Heterogeneous 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.
Greg Lindahl lindahl at pbm.comThu Apr 3 21:08:12 PDT 2008
- Previous message: [Beowulf] Re: SMPs + One processor machines = Heterogeneous Cluster
- Next message: [Beowulf] Re: SMPs + One processor machines = Heterogeneous Cluster
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Thu, Apr 03, 2008 at 10:24:39AM +0800, Cally K wrote: > answers my question but just to be on the safe side, i would like to know > the response from the mailing list users. Well, just like the word "SMP", heterogeneous has a definition which depends on context. If I'm scheduling a job on a cluster, I think it's heterogeneous if some nodes have a different amount of memory or a different clock, or anything which makes their performance non-uniform. Most MPI codes only run as fast as their slowest process. That's the most picky definition, the least is the "do I have to recompile?" definition. -- greg
- Previous message: [Beowulf] Re: SMPs + One processor machines = Heterogeneous Cluster
- Next message: [Beowulf] Re: SMPs + One processor machines = Heterogeneous Cluster
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
