Unlike the tower before that where a GPU upgrade was a magical thing with drastic quality improvements. Sure, it was a benefit in that case that the one failed component was not enough to sink that particular Ship of Theseus at that time, but on the other hand, I don't think I otherwise would have replaced the GPU on it before I replaced the entire tower. The last GPU replacement I did (a tower ago and a couple years back) was because the GPU fried itself, rather than for any perceived performance gain.
I think the diminishing returns of the performance benefits from GPU model year to model year seem to be pushing a lengthening upgrade cycle where I find my towers outlasting the need to upgrade their GPUs. I think the question is how big the niche remains. This is very different than rigid body dynamics where most shipping games use a licensed physics engine (Havok, PhysX, Bullet, ODE, etc.) ) which is used in a lot of games (Fantastic contraption, Gish, World of Goo, various Bridge builders, etc.) In all cases the developers are using custom physics code and not using a library. Because PDB is basically an extension of Jakobsen style verlet physics (. The only game that I'm aware of that uses position based dynamics on the GPU is Claybook (. Scrawk converted the code to C# in order to support Unity and implemented a Unity based version of the fluid dynamics code that runs on the GPU (using portable compute shaders instead of CUDA) as well. The GPU implementation is not open, but this code can be adapted to run on the GPU outside of Flex.
If you want OSS Position Based Dynamics code you can get Mueller's original C++ implementation here (.
0 kommentar(er)
