ACM Transactions on Programming Languages and Systems (TOPLAS)
Distributed discrete-event simulation
ACM Computing Surveys (CSUR)
Parallel discrete event simulation: a shared memory approach
SIGMETRICS '87 Proceedings of the 1987 ACM SIGMETRICS conference on Measurement and modeling of computer systems
Efficient parallel simulations of dynamic Ising spin systems
Journal of Computational Physics
ACM Transactions on Programming Languages and Systems (TOPLAS)
Asynchronous distributed simulation via a sequence of parallel computations
Communications of the ACM - Special issue on simulation modeling and statistical computing
Theory of Modelling and Simulation
Theory of Modelling and Simulation
Parallel algorithms for multiple processor architectures.
Parallel algorithms for multiple processor architectures.
Asynchronous updates in large parallel systems
Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Runtime efficient event scheduling in multi-threaded network simulation
Proceedings of the 4th International ICST Conference on Simulation Tools and Techniques
Hi-index | 0.00 |
Simulating asynchronous multiple-loop networks is commonly considered a difficult task for parallel programming. This paper presents two examples of asynchronous multiple-loop networks: a stylized queuing system and an Ising model. The network topology in both cases is an nX n grid on a torus. A new distributed simulation algorithm is demonstrated on these two examples. The algorithm combines three elements: 1) the bounded lag restriction, 2) precomputed minimal propagation delays, and 3) the so-called opaque periods. Theoretical performance evaluation suggests that if N processing elements (PEs) execute the algorithm in parallel and the simulated system exhibits sufficient density of events, then, in average, processing one event would require &Ogr;(logN) instructions of one PE. In practice, the algorithm has achieved substantial speed-ups: the speed-up is greater than 16 using 25 PEs on a shared memory MIMD bus computer, and greater than 1900 using 214 PEs on a SIMD computer.