Simulating artificial life is a computationally demanding task as quite large systems need to be modelled for long timescales but over many different starting conditions to ascertain useful reductionist measurements from a model. It is therefore valuable to be able to incorporate parallelism to speed up the calculations. However incorporating concurrency into a model implies a knowledge of the mening of time and synchronisation properties of a model. In this paper we discuss the implications of local and global synchronisation in models for artificial life. These issues affect the possible ways that paralleism can be incorporated into our simulation models.
Keywords: artificial life, simulation, parallel computing; synchronisation.
Full Document Text: PDF version.
Citation Information: In Proc. 16th IASTED Int. Conf. on Parallel and Distributed Computing and Systems (PDCS), pp, 815--820, Boston, November 2004.
BiBTeX reference:
@inproceedings{PDCS2004,
Address = {Cambidge, MA, USA},
Author = {H. A. James and C. J. Scogings and K. A. Hawick},
Booktitle = {Proc. 16th IASTED Int. Conf. on Parallel and Distributed Computing and Systems (PDCS)},
Editor = {Teofilo Gonzalez},
Month = {November},
Pages = {815--820},
Title = {Parallel Syncronization Issues in Simulating Artifical Life},
Year = {2004}
}
\bibitem{ CSTN-009,
H.A.James, C.Scogings and K.A.Hawick,
Parallel Synchronisation issues in Simulating Artificial Life,
in Proc IASTED Int. Conf on Parallel and Distributed
Computing and Systems (PDCS), MIT, Cambridge, November 2004.}