Effects of Congestion Management on Energy Saving Techniques in Interconnection Networks

Abstract

In post-Dennard scaling energy becomes more and more important. While most components in data-center and supercomputer become increasingly energy-proportional, this trend seems to pass on interconnection networks. Although previous studies have shown huge potential for saving energy in interconnects, the associated performance decrease seems to be obstructive. An increase of execution time can be caused by a decreased bandwidth as well as by transition times which links need to reconfigure and are not able to transmit data. This leads to more contention on the network than usually interconnects have to deal with. Congestion management is used in similar situations to limit the impact of these contentions only to single links and avoiding them to congest the entire network. Therefore, we propose combining energy saving policies and congestion management queueing schemes in order to maintain performance while saving energy. For synthetic hotspot traffic, which we use to stress the network, this combination shows promising results for multiple topologies. In 3D torus, k-ary n-tree, and dragonfly this combination provides a more than 50% lower latency and increases energy efficiency by more than 50% compared to the baseline. Although both techniques aim for fundamental different goals, non of the investigated configurations seems to suffer any disadvantages from their combination.