Tackling QoS-induced aging in exascale systems through agile path selection
Dean Michael Ancajas, Koushik Chakraborty, Sanghamitra Roy, Jason M. Allred · 2014
Network-On-Chips (NoCs) have become the standard communication platform for future massively parallel systems due to their performance, flexibility and scalability advantages. However, reliability issues brought about by scaling in the sub-20nm era threaten to undermine the benefits offered by NoCs. In this paper, we showthat QoS policies exacerbate the reliability profile of an exascale system. To mitigate this imposing challenge, we propose Dynamic Wearout Resilient Routing (DWRR) algorithms in QoS-enabled exascale NoCs. Our proposal includes two novel DWRR algorithms enabled by a critical-pathmonitor and a broadcast-based routing configuration. Using PARSEC benchmarks, our best algorithm improves QoS and long-term sustainability (Mean Time To Failure) of the system by an average of 16% and 25% compared to a state-of-the-art fault tolerant technique, respectively.