[Beowulf] Nehalem memory configs

[richard.walsh at comcast.net]

>----- Original Message ----- 
>From: "Jan Heichler" <jan.heichler at gmx.net> 
>To: "richard walsh" <richard.walsh at comcast.net> 
>Cc: beowulf at beowulf.org 
>Sent: Saturday, April 11, 2009 3:56:10 AM GMT -05:00 US/Canada Eastern 
>Subject: Re[2]: [Beowulf] Nehalem memory configs 
> 


>Hallo richard, 

> 


>Freitag, 10. April 2009, meintest Du: 

> 


	




> 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.  ´ 

> 


> 


>I understood the 35 GB/s to be the transfer rate that you reach when 

>accessing Memory with 8 Cores. So it involves 6 Channels (2 CPUs, 

>3 channels each). ~64 GB/s (theory) - 35 GB/s (real life). Makes sense 

>to me.  



64 GB/sec is the right dual-socket theoretical number for this situation, and Intel 

presents the value of 33 GB/sec for the stream triad for the dual socket boards, 

so 35 GB/sec could be a copy perhaps, but nothing was mentioned about any 

benchmark in the memory piece.  In any case,  I think  we have the right theoretical 

and probable real-world numbers expressed here, if people were wondering. 



rbw                 
_______________________________________________ Beowulf mailing list, Beowulf at beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.scyld.com/pipermail/beowulf/attachments/20090411/bced5da3/attachment.html