[ODE] is ODE multi-threaded?

Thomas Yeh tomyeh at CS.UCLA.EDU
Wed Oct 10 12:55:31 MST 2007

Hi All,

   I have implemented a parallel version of ODE 0.8 for research purposes. 
The profile stats and simulation results have been published in several 
papers posted on my website here: www.cs.ucla.edu/~tomyeh

  Tom Yeh

On Tue, 2 Oct 2007, Bram Stolk wrote:

> ODE is not multithreaded.
> If you profile your application, and it turns out that collision detection
> and the solver have similar runtimes, you could try application-space
> multithreading. (2 threads).
> However, you would end up with a 2-stage pipeline, where the solver for
> frame N uses collisions from frame N-1.
> Not sure if you would encounter race-conditions though.
> You would at minimum need to use two different joint-groups for contacts.
> It would make an interesting experiment.
> Anyone here got some profile stats lying around that can be shared?
> I'm interested in the comparision between dSpaceCollide() and
> dWorldQuickStep()
>   Bram
> On 10/2/07, Erick van Rijk < emvr at etv.cx> wrote:
>> Hi,
>> I had a quick question about ODE.
>> Is it multi-threaded so it can take advantage of multi-core
>> architectures?
>> I looked at the mailing list archives and there was mention of the
>> possibility of multi-threaded ODE back in 2006.
>> But nothing recent has shown up in my googles. the FAQ also doesn't
>> explicitly mention anything anything about parallelism.
>> Thanks
>> Erick
>> _______________________________________________
>> ODE mailing list
>> ODE at ode.org
>> http://ode.org/mailman/listinfo/ode
> -- 
> Zapp: Captain's log, stardate...er..
> Kif: Ohhh. April 13th.
> Zapp: April 13th. Point 2.

More information about the ODE mailing list