[ODE] parallel ODE

[Thomas Yeh]

We have submitted a research paper that includes what you described here
and more.

We have implemented some of the parallelization of the physics
engine. More work needs to be done to optimize the implementation.

We are currently submitting another paper related to this topic.
We welcome collaborative contributions to fine tune our implementation.

Tom Yeh

On Thu, 23 Feb 2006, Misha Smelyanskiy wrote:

> Yes that is what I mean. Either stepping islands in parallel, or parallelizing a single island, if there are only a few islands. For CD, I mean parallelizing a given space: both broad and narrow phases.
>   Seems like none has done it yet.
>   Mike
>
> Vast <vasko.tim at gmail.com> wrote:
>     This sounds interesting, if I understand you correctly. When you say in parallel, do you mean to like.. multithread the collision system? and run multiple collision detection calls in different threads?
>
>   I hope I got it right, but either way, the way I got it sounds like a Very good idea (no reason in particular) and it also seems to be very do-able.
>
>   Regards,
>   Tim
>
>
>   On 2/23/06, J. Perkins <starkos at gmail.com> wrote:   On 2/22/06, Misha Smelyanskiy <mmaloff2002 at yahoo.com> wrote:
> > Can you please advice if anyone tried to parallelize ODE and what the
> > results of this are in terms of scalability?
>
> I'm curious about this as well, but haven't yet had a chance to try
> it. Has anyone tried stepping islands in parallel, or running
> collision tests in parallel?
>
> Jason
>
> _______________________________________________
> ODE mailing list
> ODE at q12.org
> http://q12.org/mailman/listinfo/ode
>
>
>
>
> --
> Tim Vasko
> VaskoSoftware Development Company
> - President
>
>