<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
</head>
<body bgcolor="#ffffff" text="#000000">
Sangamesh B wrote:
<blockquote
cite="mid:cb60cbc40809140507l753022a7r93efd1ee4ba57575@mail.gmail.com"
type="cite">
<div dir="ltr">Hi Tim,<br>
<br>
Recently I benchmarked a Fortran based Scientific application on
both Intel Xeon Quad core and AMD Opteron Quad core with RHEL 5.
Following are the results:<br>
<br>
AMD-2.3GHz
INTEL-2.33GHz<br>
<br>
1. Serial 147.719
sec 73.952 sec<br>
<br>
2. Parallel 4 core 39.798
sec 32.317 sec<br>
<br>
3. Parallel 8 core 26.880
sec 30.371 sec<br>
</div>
</blockquote>
I'll go ahead and assume your "Fortran based Sci app" is memory bound
and this might be why the AMD based parallel version scales a little
better given it's using HT as communication fabric (non-shared MMU).<br>
<blockquote
cite="mid:cb60cbc40809140507l753022a7r93efd1ee4ba57575@mail.gmail.com"
type="cite">
<div dir="ltr"><br>
<br>
For AMD, I used GCC compiler(gfortran), which is released by AMD
for its barcelona-AMD fam10 based processors.<br>
<br>
For Intel, Intel 10 compilers.<br>
</div>
</blockquote>
Which compile flags were used? Also, note that I've had issues with icc
generating really fast but inaccurate code (fp model is not IEEE *by
default*, I am sure _everyone_ knows this and I am stating the obvious
here).<br>
<br>
The figures are interesting but you could get a tad higher in the
information by using the time utility ( the one from
<a class="moz-txt-link-freetext" href="http://www.gnu.org/directory/time.html">http://www.gnu.org/directory/time.html</a> ) with the -v option. This way
we can get a hint of cache use/misses and all sorts of generally neat
stuff (without getting into profiling).<br>
<blockquote
cite="mid:cb60cbc40809140507l753022a7r93efd1ee4ba57575@mail.gmail.com"
type="cite">
<div dir="ltr"><br>
Thank you,<br>
Sangamesh<br>
Conultant-HPC<br>
<br>
<br>
<br>
<div class="gmail_quote">On Mon, Sep 8, 2008 at 11:46 PM, Carsten
Aulbert <span dir="ltr"><<a moz-do-not-send="true"
href="mailto:carsten.aulbert@aei.mpg.de">carsten.aulbert@aei.mpg.de</a>></span>
wrote:<br>
<blockquote class="gmail_quote"
style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">Hi
Tim,<br>
<div class="Ih2E3d"><br>
Tim Chipman wrote:<br>
> Does anyone have any 'real world' experience with 'both' of these
CPUs, in terms of relative performance for 'whatever work you do' ?<br>
><br>
> I realize the xeon is a faster mhz part (3.16ghz xeon vs 2.3ghz
opteron) so I'm more concerned with "relative performance per mhz"<br>
><br>
> I'm involved with a cluster project, and we have 2 options from
our vendor,<br>
><br>
> - 25 compute nodes, dual-quadcore intel 5460, or<br>
> - 32 compute nodes, dual-quadcore amd 2356<br>
><br>
>>From what I've been able to glean (Spec.org / SpecCPU 2006),<br>
><br>
> - the intel chips have better integer performance<br>
> - the amd chips have better FPU performance<br>
><br>
> so the likely anticipated real-world performance result .. will
depend on how a given application blends / balances things.<br>
<br>
</div>
We have "only" the Quad-Xeon boxes with E5435 and these are quite fast,<br>
indeed it seems that FFTW seems to run faster on Xeons but I have not<br>
made any benchmarks for the past ~ 9 months, so I don't know about the<br>
latest Opterons.<br>
<br>
I think you need to come up with a real world scenario of what will be<br>
run on the cluster and maybe compile a little benchmark yourself ans aks<br>
the vendor to run both (or get hands on on both boxes. I think that's<br>
the only "fair" comparison that's possible.<br>
<br>
HTH<br>
<font color="#888888"><br>
Carsten<br>
</font>
<div>
<div class="Wj3C7c">_______________________________________________<br>
Beowulf mailing list, <a moz-do-not-send="true"
href="mailto:Beowulf@beowulf.org">Beowulf@beowulf.org</a><br>
To change your subscription (digest mode or unsubscribe) visit <a
moz-do-not-send="true"
href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank">http://www.beowulf.org/mailman/listinfo/beowulf</a><br>
</div>
</div>
</blockquote>
</div>
<br>
</div>
<pre wrap="">
<hr size="4" width="90%">
_______________________________________________
Beowulf mailing list, <a class="moz-txt-link-abbreviated" href="mailto:Beowulf@beowulf.org">Beowulf@beowulf.org</a>
To change your subscription (digest mode or unsubscribe) visit <a class="moz-txt-link-freetext" href="http://www.beowulf.org/mailman/listinfo/beowulf">http://www.beowulf.org/mailman/listinfo/beowulf</a>
</pre>
</blockquote>
<br>
</body>
</html>