From: Gianluca Interlandi (gianluca_at_u.washington.edu)
Date: Mon Jul 06 2015 - 13:08:37 CDT

I just wanted to mention that I was able to improve the performance of
NAMD using the -xHost flag to the icc compiler in both, charm++ and NAMD
compilation (multicore version). I saw a 5-6% increase in performance
running on 24 cores.

I'm not sure whether this could be of interest to anybody, since most
people will download the pre-compiled binaries and not bother tweaking the
compiler. However, in case somebody wants to squeeze the most performance
out of NAMD, -xHost is a nice flag for icc. On the other hand, I saw no
difference using "-O3" so I stick with "-O2".


Gianluca Interlandi, PhD gianluca_at_u.washington.edu
                     +1 (206) 685 4435

Research Assistant Professor at the Department of Bioengineering
at the University of Washington, Seattle WA U.S.A.

This archive was generated by hypermail 2.1.6 : Tue Dec 27 2016 - 23:21:12 CST