<FONT face="Default Sans Serif,Verdana,Arial,Helvetica,sans-serif" size=2><div><span tabindex="0" class="s-outline-plus"></span>We've got a couple of weeks max to finalize spec'ing a new cluster. Has
anyone knowledge of lowering latency for NAMD by implementing a
multi-rail IB solution using MVAPICH or Intel's MPI? My research tells
me low latency is key to scaling our code of choice, NAMD, effectively. Has anyone cut down real effective latency
to below 1.0us using multi-rail IB for molecular dynamics codes such Gromacs, Amber, CHARMM, or NAMD? What about lowered latency for parallel abnitio calculations involving NwChem, Jaguar, or Gaussian using multi-rail IB?<br>
<br>If so, what was the configuration of cards and software? Any caveats
involved, except price?
;-)<br><br>Multi-rail IB is not something I know much about so am trying to get up to speed on what is possible and what is not. I do understand that lowering latency using multi-rail has to come from the MPI layer knowing how to use the hardware properly and some MPI implementations have such options and others don't. I understand that MVAPICH has some capabilities to use multi-rail and that NAMD is run on top of MVAPICH on many IB based clusters. Any links or pointers to how I can quickly educate myself on the topic would be appreciated.<br>Best wishes,
<br>Dow<br><br>__________________________________<br>Dow P. Hurst, Research Scientist<br>Department of Chemistry and Biochemistry<br>University of North Carolina at Greensboro<br>435 New Science Bldg.<br>Greensboro, NC 27402-6170<br><a href="mailto:dphurst@uncg.edu">dphurst@uncg.edu</a><br><a href="mailto:Dow.Hurst@mindspring.com">Dow.Hurst@mindspring.com</a><br>336-334-5122 office<br>336-334-4766 lab<br>336-334-5402 fax<br></div></FONT>