Archives


- Beowulf
- Beowulf Announce
- Scyld-users
- Beowulf on Debian

[Beowulf] Nehalem memory configs

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.

Search

richard.walsh at comcast.net richard.walsh at comcast.net
Thu Apr 9 17:10:33 PDT 2009




> Kilian CAVALOTTI wrote: 
>> On Wednesday 08 April 2009 19:48:30 Joe Landman wrote: 
>>> As an FYI, Beowulf veteran Jeff Layton wrote up a nice article on 
>>> memory 
>>> configuration issues for Nehalem (I had seen some discussion on this 
>>> previously). 
>>> 
>>> Link is here: 
>>> http://www.delltechcenter.com/page/04-08-2009+-+Nehalem+and+Memory+Configur 
>>> ations 
>> 
>> That's a great write-up, gathering all the useful information in one 
>> place. A must read. Thanks Jeff! 


It is a good write up, very good ... but there looks to be an error under "Memory Bandwidth 

Performance" ... first, for socket-local-memory, I am not sure of the relevance of 

the QPI GT rate.  I would calculate the maximum rate to socket-local-memory 

with 1 DIMM per channel at: 



1.333 GHz  x 3 Channels x 8 bytes =  31.992 GBytes/sec 



not 35 GByters/sec.  Maybe I am doing something wrong.  Rates to socket-remote 

memory would be lower of course, bounded by the QPI 6.4 GT/sec transfer rate, which 

on this 2 byte duplex channel would be 25.6 GBytes/sec I believe. There would also 

be a performance drop due to the latency increase from 60 nanos to 100 nanos. 



Perhaps I have made an error somewhere ... if so, I would love have someone tell where I 

made my mistake. 



rbw
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.scyld.com/pipermail/beowulf/attachments/20090410/3a9d6435/attachment.html


More information about the Beowulf mailing list