From: Thomas Albers (talbers_at_binghamton.edu)
Date: Mon Apr 02 2012 - 14:17:13 CDT
Norman Geist wrote:
> 1. You did something wrong when compiling. Check the timing of a self
> compiled 2.8 build. One can see that the precompiled 2.9b2 builds
> were faster than yours on one node.
Unlikely:
NAMD 2.9b2 Linux-x86_64-ibverbs, UIUC binary 32 cores: 0.160 s/step
NAMD 2.8 Linux-x86_64-ibverbs, UIUC Binary 32 cores: 0.160 s/step
NAMD 2.9.b2, compiled w/ gcc 4.5.3, 32 cores: 0.160 s/step
NAMD 2.8, compiled w/ gcc 4.5.3, 32 cores: 0.156 s/step
> 2. A little part more is done on the gpu now, check your settings in
> script if they harm this (low outputenergies that mess up your pcie
> bandwidth etc.)
outputEnergies is set to 500, increasing to 1000 does not make a
difference in timing
> Check your overall scaling. You only get a speedup of 6
> instead of 8 even with 2.8 from 4 to 32 cores. That’s not that nice
> and should scale better even with SDR.
I thought 25 % administrative overhead was acceptable. What is everyone
else's experience with SDR infiniband?
Thomas
This archive was generated by hypermail 2.1.6 : Mon Dec 31 2012 - 23:21:23 CST