Abstract
There is two approaches for handling timing constraints in a heterogeneous network; conservatives and optimistic algorithms. In optimistic algorithms, time constraints are allowed to be violated with the help of a time wrap algorithm. Global Virtue Time (GVT) is a necessary mechanism for implementing time wrap algorithm. Mattern [2] has introduced an algorithm for GVT based computation using a ring structure. which showed high latency. The performance of this optimistic algorithm is optimal since it gives accurate GVT approximation. However, this accurate GVT approximation comes at the expense of high GVT latency. Since this resultant GVT latency is not only high but may vary, the multiple processors involve in communication remain idle during that period of time. Consequently, the overall throughput of a parallel and distributed simulation system degrades significantly In this paper, we discuss the potential use of trees and (or) butterflies structures instead of the ring structure. We present our analysis to show the effect of these new mechanisms on the latency of the system.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Gilbert G. Chen and Boleslaw K. Szymanski, Time Quantum GVT: A Scalable Computation of the Global Virtual Time in Parallel Discrete Event Simulations, Scientific International Journal for Parallel and Distributed Computing, pages 423–435, Volume 8, no. 4, December 2007.
F. Mattern, Efficient algorithms for distributed snapshots and global virtual time approximation, J. Parallel and Distributed, Computing 18(4) (1993) pp. 423–434.
Fujimoto, R., Parallel and Distributed Simulation Systems, Willey Series on Parallel Distributed Computing, 2000.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer Science+Business Media B.V.
About this paper
Cite this paper
Elleithy, A., Rizvi, S.S., Elleithy, K.M. (2010). Investigating the Effects of Trees and Butterfly Barriers on the Performance of Optimistic GVT Algorithm. In: Elleithy, K. (eds) Advanced Techniques in Computing Sciences and Software Engineering. Springer, Dordrecht. https://doi.org/10.1007/978-90-481-3660-5_77
Download citation
DOI: https://doi.org/10.1007/978-90-481-3660-5_77
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-3659-9
Online ISBN: 978-90-481-3660-5
eBook Packages: Computer ScienceComputer Science (R0)