Abstract | ||
---|---|---|
To meet the demand for exascale-level performance from high-performance computing (HPC) interconnects, many system architects are turning to simulation results for accurate and reliable predictions of the performance of prospective technologies. Testing full-scale networks with a variety of benchmarking tools, including synthetic workloads and application traces, can give crucial insight into what ideas are most promising without needing to physically construct a test network.
While flexible, however, this approach is extremely compute time intensive. We address this time complexity challenge through the use of large-scale, optimistic parallel simulation that ultimately leads to faster HPC network architecture innovations. In this paper we demonstrate this innovation capability through a real-world network design case study. Specifically, we have simulated and compared four extreme-scale interconnects: Dragonfly, Megafly, Slim Fly, and a new dual-rail-dual-plane variation of the Slim Fly network topology.
We present this new variant of Slim Fly, dubbed Fit Fly, to show how interconnect innovation and evaluation---beyond what is possible through analytic methods---can be achieved through parallel simulation. We validate and compare the model with various network designs using the CODES interconnect simulation framework. By running large-scale simulations in a parallel environment, we are able to quickly generate reliable performance results that can help network designers break ground on the next generation of high-performance network designs.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3316480.3325515 | SIGSIM-PADS '19: SIGSIM Principles of Advanced Discrete Simulation
Chicago
IL
USA
June, 2019 |
Keywords | Field | DocType |
Interconnection Networks, High Performance Computing, Parallel Discrete Event Simulation, Modeling | Parallel simulation,Computer science,Parallel computing,Interconnection,Distributed computing | Conference |
ISBN | Citations | PageRank |
978-1-4503-6723-3 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
neil mcglohon | 1 | 6 | 1.51 |
Noah Wolfe | 2 | 14 | 3.32 |
Mubarak Misbah | 3 | 134 | 14.22 |
Christopher D. Carothers | 4 | 1022 | 61.60 |