GPU-Accelerated Vibration Analysis Using PYTORCH and Cuda: Cutting Multi-Day Structural Simulations to Minutes
Keywords:
GPU acceleration, Structural vibration analysis, PyTorch, CUDA, High-performance computing, Structural dynamics, Finite element simulation.Abstract
Though traditional CPU-based simulation techniques frequently demand a significant amount of computational time, especially for large-scale and high-fidelity models, structural vibration analysis is essential to the design, safety assessment, and performance evaluation of complex engineering systems. In order to greatly improve computing performance in structural dynamics simulations, this paper proposes a hypothetical GPU-accelerated vibration analysis framework that combines PyTorch and CUDA. The suggested approach allows for the concurrent execution of matrix construction, modal analysis, and time-domain integration by reformulating finite element-based vibration problems into GPU-optimized tensor operations. Comparative performance evaluation shows that GPU acceleration can finish simulations that would typically take several days on CPU architectures in a matter of minutes, with speed-up factors rising as model complexity increases. Close agreement between GPU-based and CPU-based solutions is confirmed by accuracy evaluation, with just slight differences in modal parameters and dynamic response quantities. The results establish GPU-enabled vibration analysis as a potent computational paradigm for real-time analysis, next-generation structural simulation, and data-driven structural engineering workflows by highlighting its scalability, numerical stability, and practical application.
Downloads
References
T. T. Khuat and B. Gabrys, “Accelerated training algorithms of general fuzzy min–max neural network using GPU for very high dimensional data,” in Proc. Int. Conf. Neural Information Processing, Cham, Switzerland: Springer, Dec. 2019, pp. 583–595.
K. Ota, M. S. Dao, V. Mezaris, and F. G. D. Natale, “Deep learning for mobile multimedia: A survey,” ACM Trans. Multimedia Comput., Commun., Appl., vol. 13, no. 3s, pp. 1–22, 2017.
Y. Xiang and H. Kim, “Pipelined data-parallel CPU/GPU scheduling for multi-DNN real-time inference,” in Proc. IEEE Real-Time Systems Symp. (RTSS), Dec. 2019, pp. 392–405.
C. B. Murthy, M. F. Hashmi, N. D. Bokde, and Z. W. Geem, “Investigations of object detection in images/videos using various deep learning techniques and embedded platforms—A comprehensive review,” Applied Sciences, vol. 10, no. 9, Art. no. 3280, 2020.
B. Spears, B. Van Essen, C. Clouse, R. Neely, and M. McCoy, “Potential ideas for an El Capitan Center of Excellence (COE) around intelligent simulation,” Lawrence Livermore Nat. Lab., Livermore, CA, USA, Tech. Rep. LLNL-TR-748599, 2018.
S. A. Jacobs, B. Van Essen, D. Hysom, J. S. Yeom, T. Moon, R. Anirudh, et al., “Parallelizing training of deep generative models on massive scientific datasets,” in Proc. IEEE Int. Conf. Cluster Computing (CLUSTER), Sep. 2019, pp. 1–10.
J. O. Parker, “Design and implementation of a 6U CubeSat for low Earth orbit computer vision,” M.S. thesis, Univ. of Georgia, Athens, GA, USA, 2020.
R. Milton and F. Roumpani, “Accelerating urban modelling algorithms with artificial intelligence,” in Proc. 5th Int. Conf. Geographical Information Systems Theory, Applications and Management, vol. 1, May 2019, pp. 105–116.
Y. Liu, “Detection and localization of gravitational waves using convolutional neural networks,” Ph.D. dissertation, Tokyo Inst. of Technology, Tokyo, Japan, 2018.
F. Sastre Cabot, “Scalability study of deep learning algorithms in high performance computer infrastructures,” M.S. thesis, Universitat Politècnica de Catalunya, Barcelona, Spain, 2017.
S. Caldera, “Learning to grasp in unstructured environments with deep convolutional neural networks using a Baxter Research Robot,” 2019.
L. Zhou, C. Zhang, F. Liu, Z. Qiu, and Y. He, “Application of deep learning in food: A review,” Comprehensive Reviews in Food Science and Food Safety, vol. 18, no. 6, pp. 1793–1811, 2019.
A. Abrol, Z. Fu, M. Salman, R. Silva, Y. Du, S. Plis, and V. Calhoun, “Hype versus hope: Deep learning encodes more predictive and robust brain imaging representations than standard machine learning,” bioRxiv, Apr. 2020.
W. G. Hatcher and W. Yu, “A survey of deep learning: Platforms, applications and emerging research trends,” IEEE Access, vol. 6, pp. 24411–24432, 2018.
F. S. Cabot, “Scalability study of deep learning algorithms in high performance computer infrastructures,” Ph.D. dissertation, Universitat Politècnica de Catalunya, Facultat d’Informàtica de Barcelona, Barcelona, Spain, 2017.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
