Efficient Master/Worker Parallel Discrete Event Simulation

The master/worker (MW) paradigm can be used to implement parallel discrete event simulations (PDES) on metacomputing systems. MW PDES applications incur overheads not found in conventional PDES executions executing on tightly coupled machines. We introduce four techniques for reducing these overheads on public resource and desktop grid infrastructures Work unit caching, pipelined state updates, expedited message delivery, and adaptive work unit scheduling mechanisms are described that provide significant reduction in overall overhead when used in tandem. We present performance results showing that an optimized MW PDES system can exhibit performance comparable to a traditional PDES system for a queueing network and a particle physics simulation.

[1]  Richard M. Fujimoto,et al.  A scalable framework for parallel discrete event simulations on desktop grids , 2007, 2007 8th IEEE/ACM International Conference on Grid Computing.

[2]  Anoop Gupta,et al.  Cache-coherent distributed shared memory: perspectives on its development and future challenges , 1999, Proc. IEEE.

[3]  Richard M. Fujimoto,et al.  Scalable Simulation of Electromagnetic Hybrid Codes , 2006, International Conference on Computational Science.

[4]  Richard M. Fujimoto,et al.  Optimistic Parallel Simulation over Public Resource-Computing Infrastructures and Desktop Grids , 2008, 2008 12th IEEE/ACM International Symposium on Distributed Simulation and Real-Time Applications.

[5]  Emin Gün Sirer,et al.  Staged simulation: A general technique for improving simulation scale and performance , 2004, TOMC.

[6]  Richard M. Fujimoto,et al.  Aurora: An Approach to High Throughput Parallel Simulation , 2006, 20th Workshop on Principles of Advanced and Distributed Simulation (PADS'06).

[7]  Yanhong A. Liu,et al.  Caching intermediate results for program improvement , 1995, PEPM '95.

[8]  Richard M. Fujimoto,et al.  Parallel and Distribution Simulation Systems , 1999 .

[9]  Maria Hybinette,et al.  Towards adaptive caching for parallel and discrete event simulation , 2004, Proceedings of the 2004 Winter Simulation Conference, 2004..

[10]  Kalyan S. Perumalla,et al.  /spl mu/sik - a micro-kernel for parallel/distributed simulation systems , 2005, Workshop on Principles of Advanced and Distributed Simulation (PADS'05).

[11]  K. Walsh,et al.  Staged simulation for improving scale and performance of wireless network simulations , 2003, Proceedings of the 2003 Winter Simulation Conference, 2003..