Thanks Thomas,<br><br>I referred the site you introduced, <a href="http://numrel.aei.mpg.de/Research/Peyote/Docs/mpiP.html">http://numrel.aei.mpg.de/Research/Peyote/Docs/mpiP.html</a>. I didn't try IPM yet.<br><br>I recently made a cluster of 10 computing nodes with dual quad core Xeon (Harpertown E5420). The nodes are connected with a usual giagabit switch. Unfortunately, when I tested the system performance using Cactus benchmarks, BSSN_PUGH and BSSN_Carpet_Whisky, I got a bad scalability (~700sec for 1CPU, 1500sec for 64CPU). It's not a code problem. I got similar reports from my colleague that it required unexpectedly large communication time for his GADGET-2 test. I did ping-pong test for the network and heard that it is relatively good as a gigabit system. <br>
<br>So, I'm trying to get profiling information. Actually, I don't know what I can do next with it and whether it could be improved by a user-level prescription. Anyway I think the problem looks serious. I don't think it's soley a problem of the large latency network because the benchmarks will not require large communications. Now I'm going to apply Open-MX to reduce latency time. I haven't heard any benchmarks for this Harpertown cluster with gigabit network. I appreciate any comments and suggestions.<br>
<br>Wishes,<br><br>Hee Il<br><br><br><br><div><span class="gmail_quote">2008/3/31, Thomas Radke <<a href="mailto:tradke@aei.mpg.de">tradke@aei.mpg.de</a>>:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
Hee Il Kim wrote:<br> > Hi,<br> ><br> > I'm trying to profile Cactus run using mpiP. I could do it for a simple test<br> > and could view the ouput using mpipview. But it failed to make an ouput file<br> > for Cactus run. To save building time (actually it seems hang for a<br>
> sophisticate configuration), I took the minimal configuration for profiling.<br> > Do I need more options? Thanks in advance.<br> <br> <br>There are two webpages describing how to profile Cactus simulations with<br>
mpiP and IPM on one of our clusters at AEI:<br> <br> <a href="http://numrel.aei.mpg.de/Research/Peyote/Docs/mpiP.html">http://numrel.aei.mpg.de/Research/Peyote/Docs/mpiP.html</a><br> <a href="http://numrel.aei.mpg.de/Research/Peyote/Docs/IPM.html">http://numrel.aei.mpg.de/Research/Peyote/Docs/IPM.html</a><br>
<br> The information there is about 2 years old but might still work.<br> <br> What's the actual problem with creating an mpiP output file for your<br> Cactus simulation ?<br> <br><br> --<br> Cheers, Thomas.<br> _______________________________________________<br>
Users mailing list<br> <a href="mailto:Users@cactuscode.org">Users@cactuscode.org</a><br> <a href="http://www.cactuscode.org/mailman/listinfo/users">http://www.cactuscode.org/mailman/listinfo/users</a><br> </blockquote></div>
<br><br clear="all"><br><br>