A scalable synthetic traffic model of Graph500 for computer networks analysis

Abstract

The Graph500 benchmark attempts to steer the design of High-Performance Computing sys-tems to maximize the performance under memory-constricted application workloads. A realisticsimulation of such benchmarks for architectural research is challenging due to size and detail lim-itations. By contrast, synthetic traffic workloads constitute one of the least resource-consumingmethods to evaluate the performance. In this work, we provide a simulation tool for networkarchitects that need to evaluate the suitability of their interconnect for BigData applications. Ourdevelopment is a low computation- and memory-demanding synthetic traffic model that emu-lates the behavior of the Graph500 communications and is publicly available in an open-sourcenetwork simulator. The characterization of network traffic is inferred from a profile of several exe-cutions of the benchmark with different input parameters. We verify the validity of the equationsin our model against an execution of the benchmark with a different set of parameters. Further-more, we identify the impact of the node computation capabilities and network characteristics inthe execution time of the model in a Dragonfly network.