On Sat, Feb 14, 2009 at 10:13 AM, Nicholas M Glykos <span dir="ltr"><<a href="mailto:glykos@mbg.duth.gr">glykos@mbg.duth.gr</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<br>
Hi Tiago,<br>
<br>
<br>
<snip><br>
> I tried with Gromacs ...<br>
</snip><br>
<br>
Concerning your MD tests, would it be worthwhile to check also NAMD's<br>
parallel efficiency ? Based on past experience, I would suggest that you<br>
try both the UDP- & TCP-based versions (don't forget to use the +giga and<br>
possibly the +atm flags). Also, keep in mind that parallel efficiency<br>
varies greatly with problem size (for example, you should expect very<br>
different results from, say, a 1,500 atom peptide system, as compared with<br>
a 100,000 atoms large protein system).</blockquote><div></div><div>I will try NAMD like you say. Can you give me a usual performance test you have, to which I can compare to? Gromacs tests I've been able to scale better are the ones with 100k+ atoms.</div>
<div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><br>
<div class="Ih2E3d"><br>
<br>
> From what I could also digg around, it seems that some switches have too<br>
> much latency and hamper any kind of proper performance from GbE. Were this<br>
> my case, any benchmarks I could use to test that theory out?<br>
<br>
</div>We have been using NetPipe (<a href="http://www.scl.ameslab.gov/netpipe/" target="_blank">http://www.scl.ameslab.gov/netpipe/</a>) to<br>
measure latency, but the experts on this list will probably tell you more<br>
about the subjest that you'd ever wished to know ;-)<br><br></blockquote><div></div><div>Ok, thanks! Much appreciated.</div><div></div><div>Best regards,</div><div> Tiago Marques</div><div> </div>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Nicholas<br>
<font color="#888888"><br>
--<br>
<br>
<br>
Dr Nicholas M. Glykos, Department of Molecular<br>
Biology and Genetics, Democritus University of Thrace,<br>
University Campus, 68100 Alexandroupolis, Greece, Fax +302551030620<br>
Tel ++302551030620 (77620), <a href="http://www.mbg.duth.gr/~glykos/" target="_blank">http://www.mbg.duth.gr/~glykos/</a><br>
<br>
<br>
</font></blockquote><br>
<br />--
<br />This message has been scanned for viruses and
<br />dangerous content by
<a href="http://www.mailscanner.info/"><b>MailScanner</b></a>, and is
<br />believed to be clean.