<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space; ">
Hi,<div><br class="webkit-block-placeholder"></div><div>Quad-core is the way to go. I recently benchmarked the scaling of the CVS version, and with 8 independent jobs we get 85-97% throughput scaling, depending on the type of simulation. And you get essentially the same performance if you run two jobs using 4 cores each.</div><div><br class="webkit-block-placeholder"></div><div>Even for a single simulation parallelizing over all 8 cores (lots of communication), the scaling is 70-90% with CVS.</div><div><br class="webkit-block-placeholder"></div><div>However, unless you're in a rush you might want to wait until November when Intel is rumored to ship Harpertown (Penryn quad-core) with more cache, higher frequencies, and lower price. AMD will also release Barcelona (true quad-cores) in September, with higher frequencies expected in october/november. </div><div><br class="webkit-block-placeholder"></div><div>Cheers,</div><div><br class="webkit-block-placeholder"></div><div>Erik</div><div><br class="webkit-block-placeholder"></div><div><br class="webkit-block-placeholder"></div><div><div><div>On Aug 24, 2007, at 12:53 AM, Alan Chen wrote:</div><br class="Apple-interchange-newline"><blockquote type="cite"><p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">If anyone has some gromacs benchmarks numbers they'd be willing to share from clovertown</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">quad cores. ..<span class="Apple-converted-space"> </span>we're having to decide between buying 3.0 ghz DPDC woodcrest nodes (which</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">we already have several of and are quite happy with) vs 2.66 ghz DP/QC clovertowns for the same price.</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">I haven't seen any clovertown results in the benchmark page or in past listserv messages. .</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Helvetica; min-height: 14.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">Obviously, we don't<span class="Apple-converted-space"> </span>expect the clovertowns to scale perfectly for single jobs due to the architecture, but I'm very</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">curious how they do with multiple jobs on the same node - we tend to run lots of independent trajectories of medium</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">(~100,000 atom) sized systems in our lab.</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Helvetica; min-height: 14.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">If anyone can share their experiences with gromacs on clovertown XEON systems it would be greatly appreciated!</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Helvetica; min-height: 14.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">Thanks!</font></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px; font: 12.0px Helvetica; min-height: 14.0px"><br></p> <p style="margin: 0.0px 0.0px 0.0px 0.0px"><font face="Helvetica" size="3" style="font: 12.0px Helvetica">Alan Chen</font></p> </blockquote></div><br></div></body></html>