Author: Gian-Carlo Pascutto
Date: 11:07:33 09/03/03
Go up one level in this thread
On September 03, 2003 at 13:29:02, Robert Hyatt wrote: >>I don't understand. >> >>Even the slowest access on a NUMA Opeteron is twice as fast as on a SMP >>Xeon. >> >>How can it be slower then? > >You keep changing the subject. It's my first post in this part of the thread. If this was already answered elsewhere, 'oops'. >I am not comparing apples to oranges. I am >comparing two machines that are _identical_ in every way except one has a pure >SMP memory interconnection while the other has a pure NUMA interconnection. > >No references to X86 vs Opteron. No references to Cray vs Sun. If you give >me two boxes that are identical except for SMP vs NUMA, the SMP box will >_always_ have a speed advantage. It might not be much for small numbers of >processors, but it _will_ be there. I don't agree at all. The reason why the Opteron is so fast is (among others) that it has a Northbridge on chip. This _forces_ it to be NUMA when there's two or more chips. But it's by definition _faster_ than what it could be if you would force SMP (and hence, a seperate memory controller that is not on-chip). -- GCP
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.