High Performance Computing and Grid in Asia Pacific Region, International Conference on (2005)
Nov. 30, 2005 to Dec. 3, 2005
Abbas Eslami Kiasari , IPM School of Computer Science, Iran
Hamid Sarbazi-Azad , IPM School of Computer Science and Sharif University, Iran
Mustafa S. Rezazad , IPM School of Computer Science , Iran
The star graph was introduced as an attractive alternative to the well-know hypercube and its properties have been well studied in the past. Most of these studies have focused on topological properties and algorithmic aspects of this network. In this paper, the performance of nine fully-adaptive routing algorithm in the star network are studied under uniform (with and without locality) and hotspot traffic patterns. The performance fictors considered are the average message latency and network utilizationn. We consider three basic routing algorithms (two hop scheme routing algorithm: positive-hop and negative-hop, and Msick routing algorithm) and two other improved sets of improved algorithm based on the basic algorithm, The improved algorithm are the result of applyng simple modifications to the basic algorithm. Simulation results show that for uniform (with and without locality) and hotspot traffic (with a low hotspot portion) patterns, the first set of improved routing algorithm yields a better performance compared to the basic algorithm. The second set of improved routing algorithm outperform the other two sets (the basic set and the first set of improved algorithm) under different working conditions.
H. Sarbazi-Azad, M. S. Rezazad and A. E. Kiasari, "Performance Comparison of Adaptive Routing Algorithms in the Star Network," High Performance Computing and Grid in Asia Pacific Region, International Conference on(HPCASIA), Beijing, China, 2005, pp. 257-264.