Mapping Parallel Simulation onto Distributed-Memory Systems: Model and Performance
No Thumbnail Available
Date
1995-03-01T00:00:00Z
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This paper presents an analytical model to evaluate the performance of conservative parallel simulation using a finite-buffered multistage interconnection network as an example. The model is formalized based on two important time components in parallel and distributed processing: computation time and communication time. Performance metrics such as elapsed time, speedup and simulation bandwidth associated with different schemes for partitioning/mapping parallel simulation onto physical processors are evaluated. Our mathematical analysis identifies the major constituents of simulation overheads in these mapping strategies necessary for improving parallel simulation efficiency. We also show that a perfectly balanced workload distribution may not necessarily translates into better performance. On the contrary, we have shown that a balanced mapping of workload may increase communication overheads resulting in a longer simulation elapsed time. The analytical performance model has been validated against implementation results from a parallel simulation model. The analytical framework can be easily extended to analyze other conservative parallel simulation schemes.