Abstract
In this paper, we propose a method for accelerating CFD (computational fluid dynamics) simulations by integrating a conventional CFD solver with our AI module. The investigated phenomenon is responsible for chemical mixing. The considered CFD simulations belong to a group of steady-state simulations and utilize the MixIT tool, which is based on the OpenFOAM toolbox. The proposed module is implemented as a CNN (convolutional neural network) supervised learning algorithm. Our method distributes the data by creating a separate AI sub-model for each quantity of the simulated phenomenon. These sub-models can then be pipelined during the inference stage to reduce the execution time or called one-by-one to reduce memory requirements.
We examine the performance of the proposed method depending on the usage of the CPU or GPU platforms. For test experiments with varying quantities conditions, we achieve time-to-solution reductions around a factor of 10. Comparing simulation results based on the histogram comparison method shows the average accuracy for all the quantities around 92%.
The authors are grateful to the byteLAKE company for their substantive support. We also thank Valerio Rizzo and Robert Daigle from Lenovo Data Center and Andrzej Jankowski from Intel for their support.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Archibald, R., et al.: Integrating deep learning in domain sciences at exascale. arXiv preprint arXiv:2011.11188v1 (2020)
Bhatt, D., Zhang, B.W., Zuckerman, D.M.: Steady-state simulations using weighted ensemble path sampling. J. Chem. Phys. 133(1), 014110 (2010)
Chen, D., Hu, F., Nian, G., Yang, T.: Deep residual learning for nonlinear regression. Entropy 22(2), 193 (2020)
Jim, M., Ray, D., Hesthaven, J.S., Rohde, C.: Constraint-aware neural networks for Riemann problems. arXiv preprint arXiv:3327.50678 (2019)
Paul, E.L., Atiemo-Obeng, V., Kresta, S.M. (eds.): Handbook of Industrial Mixing: Science and Practice. Wiley, Hoboken (2004)
Jouppi, N.P., Young, C., Patil, N., Patterson, D.: A domain-specific architecture for deep neural networks. Commmun. ACM 61(9), 50–59 (2018)
Kim, B., et al.: Deep fluids: a generative network for parameterized fluid simulations. arXiv preprint arXiv:1806.02071v2 (2019)
Kreitmayer, D. et al.: CFD-based characterization of the single-use bioreactor XcellerexTM XDR-10 for cell culture process optimization. arXiv preprint arXiv:3461.77983 (2020)
Maulik, R., Sharma, H., Patel, S., Lusch, B., Jennings, E.: Accelerating RANS turbulence modeling using potential flow and machine learning. arXiv preprint arXiv:1910.10878 (2019)
MixIT: the enterprise mixing analysis tool. https://mixing-solution.com/. Accessed 5 Feb 2021
Mostafazadeh, B., Marti, F., Pourghassemi, B., Liu, F., Chandramowlishwaran, A.: Unsteady Navier-Stokes computations on GPU architectures. In: 23rd AIAA Computational Fluid Dynamics Conference (2017). https://doi.org/10.2514/6.2017-4508
Obiols-Sales, O., Vishnu, A., Malaya, N., Chandramowlishwaran, A.: CFDNet: a deep learning-based accelerator for fluid simulations. In: Proceedings of the 34th ACM International Conference on Supercomputing (ICS 2020), pp. 1–12. ACM (2020)
OpenFOAM: the open source CFD toolbox. https://www.openfoam.com. Accessed 5 Feb 2021
Rojek, K., et al.: Adaptation of fluid model EULAG to graphics processing unit architecture. Concurr. Comput. Pract. Exp. 27(4), 937–957 (2015)
Rojek, K., Wyrzykowski, R., Kuczynski, L.: Systematic adaptation of stencil-based 3D MPDATA to GPU architectures. Concurr. Comput. Pract. Exp. 29(9), e3970 (2017)
Rojek, K., Halbiniak, K., Kuczynski, L.: CFD code adaptation to the FPGA architecture. Int. J. High Perform. Comput. Appl. 35(1), 33–46 (2021)
Sanchez-Gonzalez, A., et al.: Learning to simulate complex physics with graph networks. arXiv preprint arXiv:3394.45567 (2020)
Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green AI. Commmun. ACM 63(12), 54–63 (2020)
Szustak, L., Rojek, K., Olas, T., Kuczynski, L., Halbiniak, K., Gepner, P.: Adaptation of MPDATA heterogeneous stencil computation to Intel Xeon Phi coprocessor. Sci. Program., 14 (2015). https://doi.org/10.1155/2015/642705
Szustak, L., Wyrzykowski, R., Olas, T., Mele, V.: Correlation of performance optimizations and energy consumption for stencil-based application on Intel Xeon scalable processors. IEEE Trans. Parallel Distrib. Syst. 31(11), 2582–2593 (2020)
Tompson, J., Schlachter, K., Sprechmann, P., Perlin, K.H.: Accelerating Eulerian fluid simulation with convolutional networks. In: ICML2017: Proceedings of the 34th International Conference on Machine Learning, PLMR 70, pp. 3424–3433 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Rojek, K., Wyrzykowski, R., Gepner, P. (2021). AI-Accelerated CFD Simulation Based on OpenFOAM and CPU/GPU Computing. In: Paszynski, M., Kranzlmüller, D., Krzhizhanovskaya, V.V., Dongarra, J.J., Sloot, P.M.A. (eds) Computational Science – ICCS 2021. ICCS 2021. Lecture Notes in Computer Science(), vol 12743. Springer, Cham. https://doi.org/10.1007/978-3-030-77964-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-77964-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77963-4
Online ISBN: 978-3-030-77964-1
eBook Packages: Computer ScienceComputer Science (R0)