Re: is ODE multi-threaded?

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 < [email protected]> 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
>> [email protected]
>> http://ode.org/mailman/listinfo/ode
>>
>
>
>
> -- 
> Zapp: Captain's log, stardate...er..
> Kif: Ohhh. April 13th.
> Zapp: April 13th. Point 2.
>