[gmx-developers] benchmark Lys errors?

[Josh Hursey]

> Subject: Re: [gmx-developers] benchmark Lys errors?
> From: David <spoel at xray.bmc.uu.se>
> To: gmx-developers at gromacs.org
> Date: Sun, 28 Mar 2004 20:32:05 +0200
> Reply-To: gmx-developers at gromacs.org
> 
> On Sun, 2004-03-28 at 19:03, Josh Hursey wrote:
> 
>>>Subject: Re: [gmx-developers] benchmark Lys errors?
>>>From: David <spoel at xray.bmc.uu.se>
>>>To: gmx-developers at gromacs.org
>>>Date: Sat, 27 Mar 2004 23:28:23 +0100
>>>Reply-To: gmx-developers at gromacs.org

>>>Yes, your protein has now more atoms than what fits on one processor.
>>>Although it maybe shouldn't crash, you are already way beyond the
>>>maximum performancewise. More than 4 processors is not worthwhile for
>>>such small systems...
>>
>>Is there a rough metric for determing when one has allocated too many processors for a given system?
>>'
> 
> Depends on the communication speed. For cut-off sims you need a few
> thousand atoms per processor, for PME sims more than that.


So when looking at a General Protein, what determines the scaling limit? I assume it involves an evaluation of the number of 
atoms in the system and the type of calculation involved.

I want to provide GROMACS as a general tool to a group of researchers, and would like to make appropriate use of our 
clustering environments. I would like to know how far I can stretch the Protein/System over our nodes, and need a general 
algorithm for matching the Maximum number of nodes to a given System.

Thanks, Josh