Re: work-load imbalance (again, but for SPH calculation)

From: yanbin YANG <yanbin.yang_at_gmail.com>
Date: Sun, 04 Jul 2010 09:20:27 +0800

Dear Yves,

I haven't finished the whole simulations, but I already see the
improvement about this two lines changes.

this line with "NTask * NTask" has twice faster performance than the
other. Perhaps this is also related
to the number of particles I used: 2M. As I understand from Volker's
suggestion, this options work well
with larger N.

My code was come with
    (TOPNODEFACTOR * NTask)
rather than
    (TOPNODEFACTOR * NTask * NTask)
have no idea why.

Anyway, Now I saved half of the time, I'm already very happy with!

best regards,
Yanbin.


On 30/06/2010 4:39 PM, Yves Revaz wrote:
> Hi Yanbin,
>
> Did you first try to change
>
> if(TopNodes[sub].Count> All.TotNumPart / (TOPNODEFACTOR * NTask * NTask))
> to
> if(TopNodes[sub].Count> All.TotNumPart / (TOPNODEFACTOR * NTask))
>
> as proposed by Volker ?
>
> http://www.mpa-garching.mpg.de/gadget/gadget-list/
>
> see : Domain decomposition takes too much time
>
>
> Cheers,
>
> yves
>
>
>> I feel the imbalance is linked to the domain decomposition. Because
>> during the merger, the gas component may be decoupled from baryon
>> strongly, while the domain decomposition is a global process ignoring
>> the type of particles (I don't know if I'm correct), Thus when N_CPU
>> increases, more regions are created. Some CPUs may have very large
>> number of gas particles, some may have few gas particles.
>> One thing I should tell you is that at the early stage of the simulation,
>> the work-load looks nice, the imbalance become significant after
>> the interaction begins.
>>
>>
>> Am I right? If I'm, is that possible to improve that? Any comments are
>> welcome.
>>
>> Thanks in advance.
>> Yanbin.
>>
>>
>>
>>
>> -----------------------------------------------------------
>>
>> If you wish to unsubscribe from this mailing, send mail to
>> minimalist_at_MPA-Garching.MPG.de with a subject of: unsubscribe gadget-list
>> A web-archive of this mailing list is available here:
>> http://www.mpa-garching.mpg.de/gadget/gadget-list
>>
>>
>
>
Received on 2010-07-04 03:20:39

This archive was generated by hypermail 2.3.0 : 2022-09-01 14:03:42 CEST