@inproceedings{e5e76bf820a84799bc0bd9e924bb5489,
title = "Strong Scaling of OpenACC enabled Nek5000 on several GPU based HPC systems",
abstract = "We present new results on the strong parallel scaling for the OpenACC-accelerated implementation of the high-order spectral element fluid dynamics solver Nek5000. The test case considered consists of a direct numerical simulation of fully-developed turbulent flow in a straight pipe, at two different Reynolds numbers Reτ = 360 and Reτ = 550, based on friction velocity and pipe radius. The strong scaling is tested on several GPU-enabled HPC systems, including the Swiss Piz Daint system, TACC's Longhorn, J{\"u}lich's JUWELS Booster, and Berzelius in Sweden. The performance results show that speed-up between 3-5 can be achieved using the GPU accelerated version compared with the CPU version on these different systems. The run-time for 20 timesteps reduces from 43.5 to 13.2 seconds with increasing the number of GPUs from 64 to 512 for Reτ = 550 case on JUWELS Booster system. This illustrates the GPU accelerated version the potential for high throughput. At the same time, the strong scaling limit is significantly larger for GPUs, at about 2000 - 5000 elements per rank; compared to about 50 - 100 for a CPU-rank.",
keywords = "Benchmarking, Computational Fluid Dynamics, Nek5000, OpenACC, Scaling",
author = "Jonathan Vincent and Jing Gong and Martin Karp and Adam Peplinski and Niclas Jansson and Artur Podobas and Andreas Jocksch and Jie Yao and Fazle Hussain and Stefano Markidis and Matts Karlsson and Dirk Pleiter and Erwin Laure and Philipp Schlatter",
note = "Funding Information: Financial support was provided by the SeRC Exascale Simulation Software Initiative (SESSI), the European Commission Horizon 2020 project grant “EXCELLERAT: The European Centre of Excellence for Engineering Applications” (grant reference 823691), the Foundation for Strategic Research (SSF) via the Infrastructure Fellow programme, and EuroCC Project which has received funding from the European Union{\textquoteright}s Horizon 2020 research and innovation programme under Grant 951732. JY and FH are funded by TTU Distinguished Chair. Part of the computations were enabled by resources provided by the Swedish National Infrastructure for Computing (SNIC), partially funded by the Swedish Research Council through grant agreement no. 2018-05973. We also acknowledge computations performed on Longhorn at the Texas Advanced Computing Center (TACC), on Piz Daint at the Swiss National Supercomputing Centre (CSCS), on Berzelius at the National Supercomputer Centre (NSC) and on JUWELS Booster at the J{\"u}lich Supercomputing Centre (JSC). Publisher Copyright: {\textcopyright} 2022 ACM.; 5th International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2022 ; Conference date: 12-01-2022 Through 14-01-2022",
year = "2022",
month = jan,
day = "7",
doi = "10.1145/3492805.3492818",
language = "English (US)",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
pages = "94--102",
booktitle = "Proceedings of International Conference on High Performance Computing in Asia-Pacific Region, HPC Asia 2022",
address = "United States",
}