[Beowulf] Rackable / SGI
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.comSun Apr 5 12:26:57 PDT 2009
- Previous message: [Beowulf] ssh authenticity issue
- Next message: [Beowulf] Breaking: IBM pulls bid for Sun Microsoft+Yahoo redux
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Sun, Apr 05, 2009 at 08:49:22PM +0200, Eugen Leitl wrote: > On Sat, Apr 04, 2009 at 12:19:02PM -0700, Greg Lindahl wrote: > > > Exactly like shared-bus multiprocessors. > > > > The incremental method of solving this is what Opteron/Nehalem does. > > None of these had to deal with hundreds or thousands of cores in a > single socket yet I didn't say they were identical. I said they were related. > SMP (shared global memory) in general would fall flat on its face > well before kilocore, not even talking about mega or gigacore. Not only are there kilocore SMP machines already, but the HPC community is well aware of ways to do non-SMP mega-core machines. Of course, these existing examples say you need a lot of memory bandwidth, more than today's sockets come with. -- greg
- Previous message: [Beowulf] ssh authenticity issue
- Next message: [Beowulf] Breaking: IBM pulls bid for Sun Microsoft+Yahoo redux
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
