Future many-core processors are likely to concurrently execute a large number of diverse applications. How these applications are mapped to cores largely determines the interference between these applications in critical shared resources such as the network-on-chip. In this paper, we propose applicationto-core mapping policies to reduce the contention in network-on-chip and memory controller resources and hence improve overall system performance. The key ideas of our policies are to: 1) map networklatency-sensitive applications to separate node clusters in the network from network-bandwidth-intensive applications such that the former makes fast progress without heavy interference from the latter, 2) map those applications that benefit more from being closer to the memory controllers close to these resources. Contrary to the conventional wisdom of balancing network or memory load across the network-on-chip and controllers, we observe that it is also important to ensure that applications that are more sensitive to network latency experience little interference from applications that are network-bandwidth-intensive, even at the cost of load imbalance.We evaluate the proposed application-to-core mapping policies on a 60-core system with an 8x8 mesh NoC using a suite of 35 diverse applications. Averaged over 128 randomly generated multiprogrammed workloads, the final proposed policy improves system throughput by 16.7% in terms of weighted speedup over a state-of-the-art baseline, while also reducing system unfairness by 22.4% and average interconnect power consumption by 52.3%.

No abstract

No abstract

Future many-core processors are likely to concurrently execute a large number of diverse applications. How these applications are mapped to cores largely determines the interference between these applications in critical shared resources such as the network-on-chip. In this paper, we propose applicationto-core mapping policies to reduce the contention in network-on-chip and memory controller resources and hence improve overall system performance. The key ideas of our policies are to: 1) map networklatency-sensitive applications to separate node clusters in the network from network-bandwidth-intensive applications such that the former makes fast progress without heavy interference from the latter, 2) map those applications that benefit more from being closer to the memory controllers close to these resources. Contrary to the conventional wisdom of balancing network or memory load across the network-on-chip and controllers, we observe that it is also important to ensure that applications that are more sensitive to network latency experience little interference from applications that are network-bandwidth-intensive, even at the cost of load imbalance.We evaluate the proposed application-to-core mapping policies on a 60-core system with an 8x8 mesh NoC using a suite of 35 diverse applications. Averaged over 128 randomly generated multiprogrammed workloads, the final proposed policy improves system throughput by 16.7% in terms of weighted speedup over a state-of-the-art baseline, while also reducing system unfairness by 22.4% and average interconnect power consumption by 52.3%.

No abstract