This Article 
 Bibliographic References 
 Add to: 
The Virtual Marathon: Parallel Computing Supports Crowd Simulations
July/August 2009 (vol. 29 no. 4)
pp. 26-33
Erdal Yilmaz, Middle East Technical University
Veysi Isler, Middle East Technical University
Yasemin Yardimci Çetin, Middle East Technical University
To be realistic, an urban model must include appropriate numbers of pedestrians, vehicles, and other dynamic entities. Using a parallelcomputing architecture, researchers simulated a marathon with more than a million participants. To simulate participant behavior, they used fuzzy logic on a GPU to perform millions of inferences in real time.

1. L. Nyland et al., "Fast N-Body Simulation with CUDA," GPU Gems 3, Addison-Wesley, 2008, pp. 677–695.
2. M. Silberstein et al., "Efficient Computation of Sum-Products on GPUs through Software-Managed Cache," Proc. 22nd Ann. Int'l Conf. Supercomputing (SC 08), ACM Press, 2008, pp. 309–318.
3. L. Howes and D. Thomas, "Efficient Random Number Generation and Application Using CUDA," GPU Gems 3, Addison-Wesley, 2008, pp. 805–830.
4. E. Millan and I. Rudomin, "Impostors, Pseudo-Instancing and Image Maps for GPU Crowd Rendering," Int'l J. Virtual Reality, vol. 6, no. 1, 2007, pp. 35–44.
5. P. Baillie-de Byl, , Programming Believable Characters for Computer Games, Charles River Media, 2004, pp. 212–230.
6. I. Rudomín, E. Millán, and B. Hernández, "Fragment Shaders for Agent Animation Using Finite State Machines," Simulation Modeling Practice and Theory, vol. 13, no. 8, 2005, pp. 741–751.
7. Q. Hou et al., "BSGP: Bulk-Synchronous GPU Programming," ACM Trans. Graphics, vol. 27, no. 3, 2008, article 19.

Index Terms:
virtual, populace, parallel, simulation
Erdal Yilmaz, Veysi Isler, Yasemin Yardimci Çetin, "The Virtual Marathon: Parallel Computing Supports Crowd Simulations," IEEE Computer Graphics and Applications, vol. 29, no. 4, pp. 26-33, July-Aug. 2009, doi:10.1109/MCG.2009.77
Usage of this product signifies your acceptance of the Terms of Use.