[gmx-users] Haphazard Results with LAM-MPI

[David van der Spoel]

On Mon, 2003-04-14 at 01:03, Venkat Ramanan K wrote:
> Thanx a lot Dallas and David....
> 
> I have tried running the DPPC system on the cluster...which has a 
> 100Mbit/S ethernet (switched) and I obtained the following 
> results.
> 
> 16 nodes  - 9hr 28.54
> 8 nodes   - 12hr 59:20
> 4 nodes   - 12hr 27:47
> 2 nodes   - 21hr 01.55
> 
> Previously my system had about 8000 atoms, thats the reason why I 
> had a problem as you had suggested. Even here the running time for 
> 8 nodes and 4 nodes are quite conflicting...How can we explain 
> this?
Lots of factors still...
- is the cluster used for other things simultaneously? Even switches
have a maximum bandwidth
- did you compile LAM using an increased minimum block size (to say 512
kb)?
- CPU time still seems excessively long...

> 
> Venky
> _______________________________________________________________________
> Odomos - the only  mosquito protection outside 4 walls -
> Click here to know more!
> http://r.rediff.com/r?http://clients.rediff.com/odomos/Odomos.htm&&odomos&&wn
> 
> _______________________________________________
> gmx-users mailing list
> gmx-users at gromacs.org
> http://www.gromacs.org/mailman/listinfo/gmx-users
> Please don't post (un)subscribe requests to the list. Use the 
> www interface or send it to gmx-users-request at gromacs.org.
> 
-- 
Groeten, David.
________________________________________________________________________
Dr. David van der Spoel, 	Dept. of Cell & Mol. Biology
Husargatan 3, Box 596,  	75124 Uppsala, Sweden
phone:	46 18 471 4205		fax: 46 18 511 755
spoel at xray.bmc.uu.se	spoel at gromacs.org   http://xray.bmc.uu.se/~spoel
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++