← Back to team overview

yade-mpi team mailing list archive

Re: Yade-MPI sending/receiving serialized bodies

 

Great work. I’m following this because I’m interested in making sure that the mpi implementation fits the criteria for:
 "We should have something like this : the mpi version of a simulation script shouldn't be very different from the usual yade script”
also in the case of quantum mechanics and Navier Stokes equations (which Marek Krzaczek is working on right now).
best regards
Janek
On 30 Apr 2019, 16:15 +0200, Bruno Chareyre <bruno.chareyre@xxxxxxxxxxxxxxx>, wrote:
>
>
> > On Tue, 30 Apr 2019 at 15:01, François <francois.kneib@xxxxxxxxx> wrote:
> > > > In the case without merge, the results are exactly the same in comparison to mpy.py (test2D_MPI.py, no merge.) . We need to add a a list of things to be done (and which are already done ) in the gitlab issue page. I will start his.
> > > Yes, this is also what I have seen but I can't remember: was it already like that at the end of the hackathon ?
> >
> > Yes it was. Because the initial scene is splitted at iteration 0 when there is no interactions, hence nothing is lost in the split by definition.
> > Splitting a scene with existing interactions would make things wrong just like the current merge does.
> > Sorry for being a bit AFK, teachings and lot of other things atm.
> > I'll check the todo's.
> >
> > Bruno
> >
> --
> Mailing list: https://launchpad.net/~yade-mpi
> Post to : yade-mpi@xxxxxxxxxxxxxxxxxxx
> Unsubscribe : https://launchpad.net/~yade-mpi
> More help : https://help.launchpad.net/ListHelp

References