[Opensim-dev] PhysicalPrimMax numbers for BulletSim

[Justin Clark-Casey]

Very nice.  And various helpful bug reports I see - ra is going to be busy :)

On 08/11/12 20:41, Teravus Ovares wrote:
> Not sure if you saw, however this is some good stuff.
> http://opensimulator.org/mantis/view.php?id=6409
> :)
> Regards
> Teravus
>
> On Wed, Nov 7, 2012 at 4:35 PM, Adams, Robert <robert.adams at intel.com <mailto:robert.adams at intel.com>> wrote:
>
>     There has been an ongoing discussion on physical prim maximum size. Lani Global did some testing and published a
>     graph of her results at http://opensimulator.org/wiki/User:LaniGlobal#PhysicalPrimMax_Size_Testing . Her testing
>     showed that, for ODE, a max size of 32m resulted in a livable frame rate degradation.____
>
>     __ __
>
>     I performed the same tests with BulletSim and discovered that a single sphere (native physical shape) or a single
>     torus (mesh/hull shape) did not reduce simulator frame rate no matter the size of the object.____
>
>     __ __
>
>     So, I created a single, standalone region with lumpy terrain and dropped different quantities of large shapes. The
>     resulting frame rates were:____
>
>     __ __
>
>                   Number                                Number____
>
>     SPHERE    1   4   8  16  32            TORUS[2] 1   4   8  32  64____
>
>             +--------------------                 +--------------------____
>
>          10 | 55  55  55  55  55               10 | 55  55  55  55  55____
>
>     S  20 | 55  55  55  55  55             S 20 | 55  55  55  26  13____
>
>     i  32 | 55  55  55  55  55             i 32 | 55  55  40  16____
>
>     z  64 | 55  55  55  49  49             z 64 | 55  50  20____
>
>     e  100| 55  54  49  47  [1]            e 100| 40  15____
>
>     __ __
>
>        [1] My setup wasn’t large enough to hold 32 100m spheres.____
>
>        [2] The torus height is about one third of the width because I preferred the doughnut shape.____
>
>     __ __
>
>     A few pictures of the experiments (one region with walls):____
>
>     https://dl.dropbox.com/u/86260377/20121107_009.png ____
>
>     https://dl.dropbox.com/u/86260377/20121107_012.png ____
>
>     https://dl.dropbox.com/u/86260377/20121107_017.png ____
>
>     https://dl.dropbox.com/u/86260377/20121107_019.png ____
>
>     https://dl.dropbox.com/u/86260377/20121107_022.png ____
>
>     https://dl.dropbox.com/u/86260377/20121107_026.png ____
>
>     __ __
>
>     It looks like, for BulletSim, a physical object max size of 32m is acceptable and 64m would probably be OK. ____
>
>     The physics frame rate is a function of the number and size of large, physical prims.  The above numbers are for
>     multiple of the same object. The next tests should be on large sized linksets (for instance, two 5m cubes that are
>     32m apart and linked and physical).____
>
>     __ __
>
>     -- ra____
>
>     __ __
>
>
>     _______________________________________________
>     Opensim-dev mailing list
>     Opensim-dev at lists.berlios.de <mailto:Opensim-dev at lists.berlios.de>
>     https://lists.berlios.de/mailman/listinfo/opensim-dev
>
>
>
>
> _______________________________________________
> Opensim-dev mailing list
> Opensim-dev at lists.berlios.de
> https://lists.berlios.de/mailman/listinfo/opensim-dev
>


-- 
Justin Clark-Casey (justincc)
OSVW Consulting
http://justincc.org
http://twitter.com/justincc