Modern Graphics Processing Units (GPUs) have been shown to provide a viable means to accelerating compute-intensive applications. The main goal of any of the following projects is to develop GPU data structures and algorithms to accelerate certain graphics-related applications, through NVidia's CUDA GPU programming paradigm.
Currently the following projects are available:
- Particle-based simulations of fluids, smoke, etc, see e.g., SPH-based fluid simulation, SPH movie;
- Implicit surface editing based on level sets, see Level-set modeling;
- Computation of geodesic curves on (triangular) meshes using level sets.
For details on the projects above, or for other interesting, GPU-related proposals for potential projects, contact Andrei Jalba (a.c.jalba@). tue.nl