Association for Computing Machinery
Network-on-Chips (NoCs) in heterogeneous systems containing both CPU and GPU cores must be designed to satisfy the performance requirements of both latency-sensitive CPU traffic and throughput-intensive GPU traffic. DVFS and adaptive routing can potentially improve NoC energy and performance efficiency. The author's further notice that GPU traffic can sometimes tolerate a slack defined as the number of cycles a packet can be delayed without causing performance penalty. In this paper, they take advantage of the slack in GPU packets to route packets through non-minimal path, so that routers can operate at a lower frequency without suffering performance penalty.