A Novel Flow Control Scheme for Best Effort Traffic in NoC Based on Source Rate Utility Maximization

Advances in semiconductor technology, has enabled designers to put complex, massively parallel multiprocessor systems on a single chip. Network on chip (NoC) that supports high degree of reusability and scalablity, is a new paradigm for designing core based System-on-Chip. NoCs provide efficient communication services to IPs: communication services with guarantees on throughput and latency (GS) and communication services with no guarantees on them (BE). However, the run-time management of communication in NoC, especially congestion control mechanism is a challenging task. This paper considers a congestion control scenario which models flow control as a utility-based optimization problem. Since BE traffic is prone to congestion, we assume that GS traffic requirements are being preserved at the desired level and regulate BE source rates with the solution of the optimization problem. We propose an iterative algorithm to solve the optimization problem based on Newton's method. The proposed algorithm can be implemented by a centralized controller with low computation and communication overhead.