For an on-chip router, the suitability of a particular routing algorithm relies on its selection of the best possible output paths. For representing congestion, the selection function of a routing algorithm uses an appropriate metric. The preferred selection metric will thus help in deciding the congested free path for any incoming flit. In this article, the fuzzy-based selection function is designed by using a cumulative flit count as a global metric of traffic estimation. The strategy provides an added advantage of effectively utilizing the links and thus regulates the traffic flow by keeping track of buffer usage and flits flow history simultaneously. The experimental results obtained under different traffic conditions, shows the proposed scheme outperforms other traditional, fuzzy based schemes in terms of both performance and power requirements.
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.
Networks on chip are being developed as a communication infrastructure in the design of Multiprocessor SOCs. With the reduction in feature size, transient faults on the links are becoming a major issue on the performance of NOCs. In this paper, two fault-tolerant algorithms are proposed. In the first algorithm, a faulty link tolerant algorithm is designed which by measuring network loads on the links will reduce transient faults and balances the load. To address the effect of hardware faults, fault and congestion controlled algorithm is designed that not only control the congestion, but also the faults on both links and the nodes. The proposed strategies are evaluated on two different synthetic traffic patterns and the results so obtained shows better network and hardware performance of both the routing in comparison with non-fault-tolerant routing.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.