Sparse matrix solvers on the GPU
Jeff Bolz, Ian Farmer, Eitan Grinspun et al. · ACM SIGGRAPH Conference Papers (SIGGRAPH) · 2003
Many computer graphics applications require high-intensity numerical simulation. We show that such computations can be performed efficiently on the GPU, which we regard as a full function streaming processor with high floating-point performance. We implemented two basic, broadly useful, computational kernels: a sparse matrix conjugate gradient solver and a regular-grid multigrid solver. Real time applications ranging from mesh smoothing and parameterization to fluid solvers and solid mechanics can greatly benefit from these, evidence our example applications of geometric flow and fluid simulation running on NVIDIA's GeForce FX.
Cited by 107 works. doi:10.1145/1201775.882364
Authors
References
- Multi-Grid Methods and Applications
- Implicit fairing of irregular meshes using diffusion and curvature flow
- Stable fluids
- A progressive refinement approach to fast radiosity image generation
- A user-programmable vertex engine
- Interactive multi-resolution modeling on arbitrary meshes
- Two fundamental issues in multiprocessing
- Linear algebra operators for GPU implementation of numerical algorithms
- Fast computation of generalized Voronoi diagrams using graphics hardware
- Visual simulation of smoke