Yong Meng Teo

Bu-Sung Lee

Lee Hing Yan

The last decade has seen a substantial increase in commodity computer and network performance. Increasingly, computing addresses collaboration, cycle and data sharing and other modes of interaction involving distributed resources. Grid computing is an emerging technology that enables large-scale sharing of widely distributed resources and coordinated problem-solving and collaboration between groups of scientists. Riding on the success of the first two workshops, this yearOCOs workshop continues the tradition of providing a useful forum for discussion among researchers, developers and users of grid computing from academia, business and industry. This volume is a collection of the international contributions presented at the workshop, with a focus on grid computing and its applications in science and engineering."

Proceedings of the 3rd International Workshop on Grid Computing and Applications, Biopolis, Singapore, 5-8, 2007

GCA 2007

Gary Tan

Gee Kin Yeo

Stephen John Turner

This book constitutes the refereed proceedings of the 13th International Conference on Systems Simulation, Asia Simulation 2013, held in Singapore, in November 2013. The 45 revised full papers presented together with 18 short papers were carefully reviewed and selected from numerous submissions. The papers address issues such as agent based simulation, scheduling algorithms, simulation methods and tools, simulation and visualization, modeling methodology, simulation in science and engineering, high performance computing and simulation and parallel and distributed simulation.

13th International Conference on Systems Simulation, Singapore, November 6-8, 2013. Proceedings

AsiaSim 2013

National University of Singapore. Dept. of Information Systems and Computer Science

Seng Chuan Tay

Siew Theng Kong

Abstract: "Excessive rollback recoveries due to overoptimistic event execution in Time Warp simulators often degrade their runtime performance. A common approach to handle this problem is to avoid the potential rollback occurrences by limiting the optimism. Some form of synchronization, however, is often used to ensure that simulation proceeds within the constraint. If the number of events available for processing is not sufficient to amortize the synchronization overhead, the control scheme may cause an undesirable performance slow down. Other approaches roll back the simulation to an earlier time even without the occurrence of causality error. This paper uses a two-sided throttling scheme to dynamically adjust the event execution speed of Time Warp simulators. We introduce the terminology called rollback thrashing to describe the rollback phenomena. The proposed throttle is based on a new concept called global progress window, which allows the individual simulation process to position on a global time scale, thereby to accelerate or decelerate their event execution. No global synchronization is required in the throttling scheme, and correct events processed need not be artificially rolled back. To quantify the effect of rollbacks and for purpose of comparing different time warp implementations, we propose two new measures called RPE (number of Rollback events Per committed Event), and [epsilon] (relative Effectiveness in reducing rollback overhead). Our implementation results show that the proposed throttle effectively regulates the proceeding of each simulation process, resulting in a significant reduction in rollback thrashing and elapsed time."

A Throttled Time Warp Scheme for Parallel Discrete-event Simulation

Yong Meng Teo

About

Books

Join the club