A Congestion Controlled and Load Balanced Selection Strategy for Networks on Chip

Abstract

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.