Using MPI (2nd ed.): portable parallel programming with the message-passing interface
Using MPI (2nd ed.): portable parallel programming with the message-passing interface
Geocomputation's future at the extremes: high performance computing and nanoclients
Parallel Computing - Special issue: High performance computing with geographical data
A Software Infrastructure for Multi-agent Geosimulation Applications
ICCSA '08 Proceeding sof the international conference on Computational Science and Its Applications, Part I
Fundamenta Informaticae - Membrane Computing
A Cellular Automata-Ready GIS Infrastructure for Geosimulation and Territorial Analysis
ICCSA '09 Proceedings of the International Conference on Computational Science and Its Applications: Part I
Environmental Modelling & Software
International Journal of Geographical Information Science
ICCSA'11 Proceedings of the 2011 international conference on Computational science and its applications - Volume Part I
A general-purpose geosimulation infrastructure for spatial decision support
Transactions on Computational Science VI
A comparison of evolutionary algorithms for automatic calibration of constrained cellular automata
ICCSA'10 Proceedings of the 2010 international conference on Computational Science and Its Applications - Volume Part I
Hi-index | 0.00 |
In recent years, urban models based on Cellular Automata (CA) are becoming increasingly sophisticated and are being applied to real-world problems covering large geographical areas. As a result, they often require extended computing times. However, in spite of the improved availability of parallel computing facilities, the applications in the field of urban and regional dynamics are almost always based on sequential algorithms. This paper makes a contribution toward a wider use in the field of geosimulation of high performance computing techniques based on General-Purpose computing on Graphics Processing Units (GPGPU). In particular, we investigate the parallel speedup achieved by applying GPGPU to a popular constrained urban CA model. The major contribution of this work is in the specific modeling we propose to achieve significant gains in computing time, while maintaining the most relevant features of the traditional sequential model.