White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

Flexible high performance agent based modelling on graphics card hardware

Richmond, Paul Andrew (2010) Flexible high performance agent based modelling on graphics card hardware. PhD thesis, University of Sheffield.

[img] Text (522373.pdf)

Download (29Mb)


Agent Based Modelling is a technique for computational simulation of complex interacting systems, through the specification of the behaviour of a number of autonomous individuals acting simultaneously. This is a bottom up approach, in contrast with the top down one of modelling the behaviour of the whole system through dynamic mathematical equations. The focus on individuals is considerably more computationally demanding, but provides a natural and flexible environment for studying systems demonstrating emergent behaviour. Despite the obvious parallelism, traditionally frameworks for Agent Based Modelling fail to exploit this and are often based on highly serialised mobile discrete agents. Such an approach has serious implications, placing stringent limitations on both the scale of models and the speed at which they may be simulated. Serial simulation frameworks are also unable to exploit multiple processor architectures which have become essential in improving overall processing speed. This thesis demonstrates that it is possible to use the parallelism of graphics card hardware as a mechanism for high performance Agent Based Modelling. Such an approach is in contrast with alternative high performance architectures, such as distributed grids and specialist computing clusters, and is considerably more cost effective. The use of consumer hardware makes the techniques described available to a wide range of users, and the use of automatically generated simulation code abstracts the process of mapping algorithms to the specialist hardware. This approach avoids the steep learning curve associated with the graphics card hardware's data parallel architecture, which has previously limited the uptake of this emerging technology. The performance and flexibility of this approach are considered through the use of benchmarking and case studies. The resulting speedup and locality of agent data within the graphics processor also allow real time visualisation of computationally and demanding high population models.

Item Type: Thesis (PhD)
Academic Units: The University of Sheffield > Faculty of Engineering (Sheffield) > Computer Science (Sheffield)
The University of Sheffield > Faculty of Science (Sheffield) > Computer Science (Sheffield)
Identification Number/EthosID: uk.bl.ethos.522373
Depositing User: EThOS Import Sheffield
Date Deposited: 17 May 2019 11:28
Last Modified: 17 May 2019 11:28
URI: http://etheses.whiterose.ac.uk/id/eprint/21828

You do not need to contact us to get a copy of this thesis. Please use the 'Download' link(s) above to get a copy.
You can contact us about this thesis. If you need to make a general enquiry, please see the Contact us page.

Actions (repository staff only: login required)