A link arbitration scheme for quality of service in a latency-optimized network-on-chip

摘要

Networks-on-chip (NoC) for general-purpose multiprocessors require quality of service mechanisms to allow realtime streaming applications to be executed along with latency-sensitive general purpose processing tasks. In this paper, we propose a NoC link arbitration technique that supports bandwidth guarantees along with best effort latency optimizations. In contrast to many existing quality of service mechanisms, our technique prioritizes best effort over guaranteed bandwidth traffic for optimal latency. Distributed traffic shaping is used to offer bandwidth guarantees over previously reserved connections, which are established dynamically using control messages. Initial simulation results show that our arbitration scheme can provide tight bandwidth guarantees for streaming traffic under network overload conditions. At the same time, the average latency of best effort traffic is improved compared to a simple prioritization of streaming traffic.