Abstract. Current interconnect standards providing hardware support for quality of service (QoS) consider up to 16 virtual channels (VCs) for this purpose. However, most implementations do not offer so many VCs because they increase the complexity of the switch and the scheduling delays. In this paper, we show that this number of VCs can be significantly reduced. Some of the scheduling decisions made at network interfaces can be easily reused at switches without significantly altering the global behavior. Specifically, we show that it is enough to use two VCs for QoS purposes at each switch port, thereby simplifying the design and reducing its cost. 1

Network-on-Chips (NoCs) are likely to become a critical shared resource in future many-core processors. The challenge is to develop policies and mechanisms that enable multiple applications to efficiently and fairly share the network, to improve system performance. Existing local packet scheduling policies in the routers fail to fully achieve this goal, because they treat every packet equally, regardless of which application issued the packet. This paper proposes prioritization policies and architectural extensions to NoC routers that improve the overall application-level throughput, while ensuring fairness in the network. Our prioritization policies are application-aware, distinguishing applications based on the stall-time criticality of their packets. The idea is to divide processor execution time into phases, rank applications within a phase based on stall-time criticality, and have all routers in the network prioritize packets based on their applications ’ ranks. Our scheme also includes techniques that ensure starvation freedom and enable the enforcement of system-level application priorities. We evaluate the proposed prioritization policies on a 64-core CMP with an 8x8 mesh NoC, using a suite of 35 diverse applications. For a representative set of case studies, our proposed policy increases average system throughput by 25.6 % over age-based arbitration and 18.4 % over round-robin arbitration. Averaged over 96 randomlygenerated multiprogrammed workload mixes, the proposed policy improves system throughput by 9.1 % over the best existing prioritization policy, while also reducing application-level unfairness.

Traditional Network-on-Chips (NoCs) employ simple arbitration strategies, such as round-robin or oldest-first, to decide which packets should be prioritized in the network. This is suboptimal since different packets can have very different effects on system performance due to, e.g., different level of memory-level parallelism (MLP) of applications. Certain packets may be performance-critical because they cause the processor to stall, whereas others may be delayed for a number of cycles with no effect on application-level performance as their latencies are hidden by other outstanding packets ’ latencies. In this paper, we define slack as a key measure that characterizes the relative importance of a packet. Specifically, the slack of a packet is the number of cycles the packet can be delayed in the network with no effect on execution time. This paper proposes new router prioritization policies that exploit the available slack of interfering packets in order to accelerate performance-critical packets and thus improve overall system performance. When two packets interfere with each other in a router, the packet with the lower slack value is prioritized. We describe mechanisms to estimate slack, prevent starvation, and combine slack-based prioritization with other recently proposed application-aware prioritization mechanisms. We evaluate slack-based prioritization policies on a 64-core CMP with an 8x8 mesh NoC using a suite of 35 diverse applications. For a representative set of case studies, our proposed policy increases average system throughput by 21.0 % over the commonlyused round-robin policy. Averaged over 56 randomly-generated multiprogrammed workload mixes, the proposed policy improves system throughput by 10.3%, while also reducing application-level unfairness by 30.8%.

ii iii ACKNOWLEDGMENTS This dissertation would not have been possible without the tremendous support of my primary adviser Sonia Fahmy and my co–adviser Ness B. Shroff. Their constant encouragement and unwavering support resulted in our publications and ultimately this thesis. During my work, I had to rely on the staff of DETER, Emulab, and WAIL testbeds for my experiments. I am very grateful for their support and patience, in helping me resolve experimental problems. The second half of this dissertation would not have been possible without the help of Michael Blodgett, Prof. Paul Barford, Ron Ostrenga, Terry Benzel, and Prof. Ray Hansen. With the help of these individuals, I was able to obtain access to four commercial routers necessary for the experiments in this thesis. I want to additionally thank Michael Blodgett and Prof. Ray Hansen for their help in configuring the routers. Last but not least, I want to thank my family for their constant support and