[Beowulf] "dual" Quad solution from Tyan

Bogdan Costescu Bogdan.Costescu at iwr.uni-heidelberg.de
Tue Feb 28 05:09:03 PST 2006


On Tue, 28 Feb 2006, Mark Hahn wrote:

> > Not quite, this would make no use of two HT channels.  Its like this:
> > 
> > c--c--c--c
> > |  |   \/|
> > |  |   /\|
> > c--c--c--c
> > 
> > (The two leftmost CPUs need their third HT to connect the two chipsets.)
> 
> are you sure about that (ie, inspected the traces, or the HT routing 
> tables)?  by your logic, for instance, a plain 4x would have one 
> cross-link (and I don't think they do.)

According to page 2 of the Tyan datasheet:

ftp://ftp.tyan.com/datasheets/d_s4881_104.pdf

it's like Karsten's draw, which is still missing a "vertical" link
between the CPUs in the third column counting from left.

-- 
Bogdan Costescu

IWR - Interdisziplinaeres Zentrum fuer Wissenschaftliches Rechnen
Universitaet Heidelberg, INF 368, D-69120 Heidelberg, GERMANY
Telephone: +49 6221 54 8869, Telefax: +49 6221 54 8868
E-mail: Bogdan.Costescu at IWR.Uni-Heidelberg.De




More information about the Beowulf mailing list