[gmx-users] PME scaling

Erik Lindahl lindahl at sbc.su.se
Fri Feb 10 16:38:01 CET 2006


Hi Rob,

CVS is stable for normal decomposition. Domain decomposition is still  
under development, but works fine for test systems consistion of  
single-charge-group molecules such as water.

Unless Berk implemented this week, that is - our twins were born last  
friday, so I've been almost entirely offline...

Cheers,

Erik

On Feb 10, 2006, at 4:05 PM, Robert Bjornson wrote:

> Hi Erik,
>
> I'm still interested in improving the scaling of gromacs on my GigE
> cluster.  I'm wondering if the current state of the head is such that
> it would make sense for me to give it a try?
>
> I've been studying a ppt I found that Carsten gave at
> Forschungszentrum Juelich in April 2005.  Is there something more
> up-to-date that describes the design changes that are taking place for
> PME in gromacs?
>
> Thanks,
>
> Rob Bjornson
>
> On 1/10/06, Erik Lindahl <lindahl at sbc.su.se> wrote:
>> Hi Rob,
>>
>> The head branch of CVS has major scaling improvements, but it's
>> changing quite a lot right now, so unless you really like to iron out
>> bugs I'd recommend waiting a couple of weeks until it's stabilized a
>> bit.
>>
>> For instance, the current version partitions the system into separate
>> PME and direct space nodes, but depending on the performance we might
>> actually decide to reverse that and do PME on all nodes again.
>>
>>
>> Cheers,
>>
>> Erik
>>
>> On Jan 10, 2006, at 5:45 PM, Robert Bjornson wrote:
>>
>>> Hi,
>>>
>>> I'm experiencing very poor scaling when using PME on gromacs-3.3,  
>>> and
>>> looking through the list indicates that this is a known issue with
>>> that release.  However, there was some indication that work has been
>>> done on parallelizing PME, and that the top of CVS might contain a
>>> version that is worth trying.
>>>
>>> Has anyone tried this?  Did your PME performance improve?  If so,  
>>> did
>>> you simply take the top of cvs, or is there a tag that is more  
>>> likely
>>> to work successfully?
>>>
>>> thanks,
>>>
>>> Rob Bjornson
>>> _______________________________________________
>>> 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.
>>>
>>
>> -----------------------------------------------------------
>> Erik Lindahl  <lindahl at sbc.su.se>     Backup address:
>> <erik.lindahl at gmail.com>
>> Assistant Professor, Computational Structural Biology
>> Stockholm Bioinformatics Center, Stockholm University, SE 106 91
>> Stockholm
>> Phone: +46 8 5537 8564     Fax: +46 8 5537 8214
>>
>>
>>
>>
>>

-----------------------------------------------------------
Erik Lindahl  <lindahl at sbc.su.se>     Backup address:  
<erik.lindahl at gmail.com>
Assistant Professor, Computational Structural Biology
Stockholm Bioinformatics Center, Stockholm University, SE 106 91  
Stockholm
Phone: +46 8 5537 8564     Fax: +46 8 5537 8214







More information about the gromacs.org_gmx-users mailing list