Thanks a lot!<br><br><div><span class="gmail_quote">2006/9/14, Cesar Araujo <<a href="mailto:cesar.araujo@oulu.fi">cesar.araujo@oulu.fi</a>>:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<br>> ------------------------------<br>><br>> Message: 7<br>> Date: Thu, 14 Sep 2006 09:27:45 +0200<br>> From: "Qiao Baofu" <<a href="mailto:qiaobf@gmail.com">qiaobf@gmail.com</a>><br>> Subject: Re: [gmx-users] Re: Question about parallazing Gromacs (Qiao
<br>> Baofu)<br>> To: "Discussion list for GROMACS users" <<a href="mailto:gmx-users@gromacs.org">gmx-users@gromacs.org</a>><br>> Message-ID:<br>> <<a href="mailto:6a91f07b0609140027u68ac3085tb01120f19b854545@mail.gmail.com">
6a91f07b0609140027u68ac3085tb01120f19b854545@mail.gmail.com</a>><br>> Content-Type: text/plain; charset="iso-8859-1"<br>><br>> Hi,<br>><br>> Thanks. I have test different cpus. Our institute has two clusters: one is
<br>> each node has 4 cpu (A), one is one node has only 1 cpu (B). I made<br>> different tests on the two clusters and my local computer using the same<br>> system. See the following result:<br>><br>> A (For 1 hour)
<br>> # of cpus ; MD steps<br>> 4 finished (200000steps for 26:21)<br>> 8 finished (200000steps for 40:57)<br>> 12 87950<br>> 20 42749
<br>> 44 5962 !!!!!<br>> B (For 1 hour)<br>> # of cpu ; MD steps<br>> 1 156991 for 56:12<br>> 2 179820<br>> 3 200,000 for 54:20
<br>> 4 200,000 for 51:12<br>> c. Local(single cpu), 200000 steps For 1h52:38<br>><br>> One can see that<br>> 1. On cluster A, one nodes(4 cpu) is just as 4 times fast as my local<br>> computer.
<br>> 2. More than one nodes will decrease the performancs the gromacs,<br>> 3. On cluster B, the more cpu used, the faster gromacs runs. But the<br>> difference of speed is not apparent.<br>> 4. Cluster B with 4 cpus is slow as half as that Cluster A with 1 node (4
<br>> cpus)<br>><br>> I wonder if anyone can tell the bottlenack: the hardware on the cluster or<br>> gromacs?<br>><br>><br><br>Well, probably it is a combination of bottlenecks in both software and<br>hardware.
<br>Both of them should be optimized to guarantee the best performance. From the<br>hardware side the delays in inter-node communication across the network can<br>be the reason. But also, it can be related with software issues related to
<br>the operating<br>system and network configuration. I think that the first thing to do is work<br>in cluster<br>setup to achieve the best performance for your hardware configuration.<br><br>In addition, take into account that inter-node communication between two
<br>CPU's<br>inside the same machine should be faster than between two CPU's across the<br>network.<br><br>>From the software side (Gromacs) the algorithms should be optimized with<br>regard<br>to the parallel programming model. David said in a previous answer that they
<br>have detected some problems in the software implementation and they are<br>working<br>to solve that issue in the next version of Gromacs.<br><br>Regards,<br>-----------------------------------------------------------<br>
Cesar Araujo, Lic. of Chemistry<br>Department of Molecular Endocrynology<br>Oulu University Hospital<br>FIN-90029 OYS, OULU, FINLAND<br><br>phone: +358 8 3155632<br>e-mail: <a href="mailto:cesar.araujo@oulu.fi">cesar.araujo@oulu.fi
</a><br><br>_______________________________________________<br>gmx-users mailing list <a href="mailto:gmx-users@gromacs.org">gmx-users@gromacs.org</a><br><a href="http://www.gromacs.org/mailman/listinfo/gmx-users">http://www.gromacs.org/mailman/listinfo/gmx-users
</a><br>Please don't post (un)subscribe requests to the list. Use the<br>www interface or send it to <a href="mailto:gmx-users-request@gromacs.org">gmx-users-request@gromacs.org</a>.<br>Can't post? Read <a href="http://www.gromacs.org/mailing_lists/users.php">
http://www.gromacs.org/mailing_lists/users.php</a><br></blockquote></div><br><br clear="all"><br>-- <br>Sincerely yours,<br>**********************************************<br>Baofu Qiao, PhD<br>Frankfurt Institute for Advanced Studies
<br>Max-von-Laue-Str. 1<br>60438 Frankfurt am Main, Germany TEL:+49-69-7984-7529<br>**********************************************