A scalable synthetic traffic model of Graph500 for computer networks analysis

Abstract

SUMMARYThe Graph500 benchmark attempts to steer the design of High-Performance Computing systems to maximize the performance under memory-constricted application workloads. A realistic simulation of such benchmarks for architectural research is challenging due to size and detail limitations. By contrast, synthetic traffic workloads constitute one of the least resource-consuming methods to evaluate the performance. In this work, we provide a simulation tool for network architects that need to evaluate the suitability of their interconnect for BigData applications. Our development is a low computation-and memory-demanding synthetic traffic model that emulates the behavior of the Graph500 communications, and is publicly available in an open-source network simulator. The characterization of network traffic is inferred from a profile of several executions of the benchmark with different input parameters. We verify the validity of the equations in our model against an execution of the benchmark with a different set of parameters. Furthermore, we identify the impact of the node computation capabilities and network characteristics in the execution time of the model in a Dragonfly network.

TianheGraph: Customizing Graph Search for Graph500 on Tianhe Supercomputer

“…Several variations from CSR are proposed for concisely describing the graphs. In addition, bitmap-based sparse matrix representation has been designed to further reduce memory footprint which achieves nearly 60% reduction according to Ueno et al [22][23].…”

“…Architectural optimization is to exploit the hardware designs of target supercomputers for fast graph processing, represented by Tianhe, Sunway TaihuLight, K, and Fugaku supercomputers [23,[26][27][30][31][32][33][34][35][36][37]. For example, Graph500 on Tianhe have utilized the hardware prefetching and leveraged the routing topology of fat-tree to improve the performance [2,38,39], which can be viewed as the preliminary design of this paper.…”

“…For example, Graph500 on Tianhe have utilized the hardware prefetching and leveraged the routing topology of fat-tree to improve the performance [2,38,39], which can be viewed as the preliminary design of this paper. Ueno et al proposed an efficient BFS algorithm based on Tofu network configured in K computer, which won the best graph500 performance by achieving 38621.4 GTEPS [23,27,32]. They retained the advantage in Graph500 to Fugaku [31].…”

“…They retained the advantage in Graph500 to Fugaku [31]. A scalable graph traverse method on Sunway TaihuLight and a Shentu framewok is proposed by Lin et al [23][24]. For scaling Graph500 to Sunway TaihuLight, researchers fully explored architectural details of SW26010 CPU, shared memory among MPEs and CPEs, and Network topology of TaihuLight.…”

Algorithms and applications towards the convergence of high‐end data‐intensive and computing systems

“…In spite of former solutions, network traffic is always a major problem in HEDICS due to data movements. In their paper A scalable synthetic traffic model of Graph500 for computer networks analysis , Fuentes et al provide a simulation tool for network architects that need to evaluate the suitability of their interconnect for Big Data applications. Their development is a low computation‐ and memory‐demanding synthetic traffic model that emulates the behaviour of the Graph500 communications and is publicly available in an open‐source network simulator.…”