<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=windows-1252"
http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
Dear Alexander,<br>
thank you for your experience.<br>
Will it be possible to have the results of the official WIEN benchmark
for this type of node
<pre wrap="">Intel Q6600</pre>
starting from 1 job (1kpoint/1thread) up to 4 jobs (4 kpoints).<br>
<br>
Peter, can we think also in looking the benchmark results of the new
iterrative diagonalization scheme. <br>
If you want that people use this approach for large system, it is
important to know how it performs on various architecture.<br>
Best regards<br>
Florent<br>
<br>
<br>
Alexander Shaposhnikov a écrit :
<blockquote type="cite">
<pre wrap="">Hello Florent,
On Monday 22 October 2007 15:35, Florent Boucher wrote:
</pre>
<blockquote type="cite">
<pre wrap="">Dear Wien users,
</pre>
</blockquote>
<pre wrap=""><!---->***
</pre>
<blockquote type="cite">
<pre wrap="">In that case, if you look the benchmark results below, it is not a good
solution !
bi-Xeon 5320 (overcl 2.67GHz)
</pre>
</blockquote>
<pre wrap=""><!---->******
</pre>
<blockquote type="cite">
<pre wrap="">You can see that even an overclocked solution run slower than an AMD
when putting 8 jobs on it !
The memory band width is much lower than on AMD, due to the memory
architecture. It is better in that case to by more nodes with less
expensive AMD chips for which the efficiency is much better when the
load average is close to 100%.
</pre>
</blockquote>
<pre wrap=""><!---->
I believe those are results i obtained for my machine :)
The scaling is very bad indeed, even though the machine has almost 20% faster
memory than standart non-overclocked bi-Xeon X5355 (and the same CPU
frequency)
</pre>
<blockquote type="cite">
<pre wrap="">For information, we have been able to buy a solution with 20 nodes from
a well known company (1U, 2 x AMD 2.8GHz bicore, 8Go DDR2 per node,
Infinipath DDR 4X, warranty 3 years) for less than 50k€ (without taxes).
The power consumption for such a configuration will be less than 7kW/h.
</pre>
</blockquote>
<pre wrap=""><!---->
You could have done better and pay less.
Typical 24-port infiniband switch is 5k€, 1 node based around Intel Q6600 with
8GB memory is 1k€ including infiniband mem-free network card, so 24k€ for 24
nodes, 30k€ total.
The cluster will have 920Gigaflops, and consume no more than 5KW.
And if you dare :) , you can always trouble-free overclock it to at least
3GHz, increasing to 1.15 Teraflops.
Scaling will be good enough, as the memory performance of Intel desktop
chipsets is adequate.
Best Regards.
_______________________________________________
Wien mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Wien@zeus.theochem.tuwien.ac.at">Wien@zeus.theochem.tuwien.ac.at</a>
<a class="moz-txt-link-freetext" href="http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien">http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien</a>
</pre>
</blockquote>
<br>
<br>
<pre class="moz-signature" cols="80">--
-------------------------------------------------------------------------
| Florent BOUCHER | |
| Institut des Matériaux Jean Rouxel | <a class="moz-txt-link-freetext" href="Mailto:Florent.Boucher@cnrs-imn.fr">Mailto:Florent.Boucher@cnrs-imn.fr</a> |
| 2, rue de la Houssinière | Phone: (33) 2 40 37 39 24 |
| BP 32229 | Fax: (33) 2 40 37 39 95 |
| 44322 NANTES CEDEX 3 (FRANCE) | <a class="moz-txt-link-freetext" href="http://www.cnrs-imn.fr">http://www.cnrs-imn.fr</a> |
-------------------------------------------------------------------------</pre>
</body>
</html>