From: Thomas Albers (talbers_at_binghamton.edu)
Date: Sun Jun 19 2011 - 21:32:42 CDT
> Do you see an actual performance improvement from Open-MX?
The odd thing is - we do not. With TCP networking time/step remains
fairly constant throughout the simulation, but with Open-MX (through
OpenMPI) it varies by a factor of 3. Something else is wrong here,
and I can't quite see what.
This archive was generated by hypermail 2.1.6 : Mon Dec 31 2012 - 23:20:28 CST