An Efficient and Congestion Aware Fuzzy Based Output Selection Strategy for On-Chip Routers

Abstract

The network performance of an adaptive router largely depends on well designed selection strategy. The selection function selects one of the accepted output directions returned by the routing function. The effectiveness of any selection strategy relies on its congestion free traffic distribution mechanism for each incoming packet. This article proposes a fuzzy based output selection strategy that considers the congestion information from both neighboring routers as well as routers on global path. The strategy efficiently balances the traffic load by using the knowledge base of fuzzy controllers. Performance evaluation is carried out using a cycle accurate simulator under synthetic traffic conditions. The experimental results show that the fuzzy based selection strategy improves the performance by increased throughput and reduced packet latency when compared with other traditional selection strategies.