Parallelized implementation

Asked by Alvin on 2011-07-26

Hi, I would like to know if there is a limited of cpus when parallelized implementation, and so on the number of balls generated.

Thanks in advance, Alvin

Question information

Language:
English Edit question
Status:
Solved
For:
Yade Edit question
Assignee:
No assignee Edit question
Solved by:
Bruno Chareyre
Solved:
2011-08-12
Last query:
2011-08-12
Last reply:
2011-07-27
Anton Gladky (gladky-anton) said : #1

Hi Alvin,

could you, please, be more specific? You want to know how many
particles can be in one simulation?

Anton

On Tue, Jul 26, 2011 at 4:51 AM, Alvin
<email address hidden> wrote:
> New question #165997 on Yade:
> https://answers.launchpad.net/yade/+question/165997
>
> Hi, I would like to know if there is a limited of cpus when parallelized implementation, and so on the number of balls generated.
>
> Thanks in advance, Alvin
>
> --
> You received this question notification because you are a member of
> yade-users, which is an answer contact for Yade.
>
> _______________________________________________
> Mailing list: https://launchpad.net/~yade-users
> Post to     : <email address hidden>
> Unsubscribe : https://launchpad.net/~yade-users
> More help   : https://help.launchpad.net/ListHelp
>

Alvin (lyj5300625) said : #2

Hi Anton,
 you got what i mean. I want to know how many particles can be simulated in
one test, and how many cpus of the computer can be called in one simulation.
Is there a limitaton for that? I mean the capacity of YADE in simulation.

Alvin

2011/7/27 Anton Gladky <email address hidden>

> Your question #165997 on Yade changed:
> https://answers.launchpad.net/yade/+question/165997
>
> Status: Open => Answered
>
> Anton Gladky proposed the following answer:
> Hi Alvin,
>
> could you, please, be more specific? You want to know how many
> particles can be in one simulation?
>
> Anton
>
>
>
> On Tue, Jul 26, 2011 at 4:51 AM, Alvin
> <email address hidden> wrote:
> > New question #165997 on Yade:
> > https://answers.launchpad.net/yade/+question/165997
> >
> > Hi, I would like to know if there is a limited of cpus when parallelized
> implementation, and so on the number of balls generated.
> >
> > Thanks in advance, Alvin
> >
> > --
> > You received this question notification because you are a member of
> > yade-users, which is an answer contact for Yade.
> >
> > _______________________________________________
> > Mailing list: https://launchpad.net/~yade-users
> > Post to : <email address hidden>
> > Unsubscribe : https://launchpad.net/~yade-users
> > More help : https://help.launchpad.net/ListHelp
> >
>
> --
> If this answers your question, please go to the following page to let us
> know that it is solved:
> https://answers.launchpad.net/yade/+question/165997/+confirm?answer_id=0
>
> If you still need help, you can reply to this email or go to the
> following page to enter your feedback:
> https://answers.launchpad.net/yade/+question/165997
>
> You received this question notification because you asked the question.
>

--
Ying-Jing LIU
Doctor Candidate in Geotechnical Engineering
Department of Civil Engineering
Shanghai Jiao Tong University
Dongchuan Road 800
Minhang Shanghai, 200240
Tel: +86 21 3420 7003
Cell: +86 13918150942
Email: <email address hidden> <email address hidden>

Anton Gladky (gladky-anton) said : #3

Yade is paralleled with OpenMP, but the number of particles is
__very__ dependent on your simulation, how many contacts you have, how
"dynamic" is your simulation etc.
I am using 6x-core CPU for some tests. Roughly - 5*10^5 particles is,
probably, the upper border.
But again: it can be sufficiently more or less.

Anton

Alvin (lyj5300625) said : #4

Thank you! Anton, I got it!

2011/7/27 Anton Gladky <email address hidden>

> Question #165997 on Yade changed:
> https://answers.launchpad.net/yade/+question/165997
>
> Status: Open => Answered
>
> Anton Gladky proposed the following answer:
> Yade is paralleled with OpenMP, but the number of particles is
> __very__ dependent on your simulation, how many contacts you have, how
> "dynamic" is your simulation etc.
> I am using 6x-core CPU for some tests. Roughly - 5*10^5 particles is,
> probably, the upper border.
> But again: it can be sufficiently more or less.
>
> Anton
>
> --
> You received this question notification because you are a member of
> yade-users, which is an answer contact for Yade.
>
> _______________________________________________
> Mailing list: https://launchpad.net/~yade-users
> Post to : <email address hidden>
> Unsubscribe : https://launchpad.net/~yade-users
> More help : https://help.launchpad.net/ListHelp
>

Actually, the maximum number of particles only depends on you RAM memory
(well, you could also swap...). It is independant on parallelization.
I remember that my PFC2D simulations (almost 10 years ago...) needed to
specify an allocated RAM of 8Mo via a DOS command, in order to simulate
more than 10k particles. Else it wouldn't fit.

With modern RAM capacities, I guess you can reach 10 millions easily in
Yade. If your simulation needs 10 time steps, that's ok. If it needs
more that 100k, it will be a little long...

Alvin (lyj5300625) said : #6

Thanks Chareyre, that solved my question.