2692-4048ISSN (Online)
2770-0070ISSN (Print)
Volume 15 , Issue 1 , PP: 214-226, 2024 | Cite this article as | XML | Html | PDF | Full Length Article
NoorUlhuda S. Ahmed 1 * , Esraa H. Alwan 2 , Ahmed B. M. Fanfakh 3
Doi: https://doi.org/10.54216/FPA.150117
This work investigates the use of ensemble machine-learning algorithms to optimize loop-tiling in computing systems, with the goal of improving performance by predicting optimal tile sizes. It compares two approaches: independent training and averaging (soft voting) and an ensemble technique (hard voting) that employs models such as linear regression, ridge regression, and random forests. Experiments on an Intel Core i7-8565U CPU with several benchmark programs revealed that the hard voting Ensemble Approach beat the soft voting technique, providing more dependable and accurate predictions across a range of computing environments. The hard voting technique reduced execution time by around 87.5% for dynamic features and 89.89% for static features, whereas the soft voting approach showed an average drop of 75.45% for dynamic features and 78.13% for static characteristics. This work demonstrates the effectiveness of hard voting ensemble machine learning approaches in improving cache efficiency and total execution time, opening the way for future advances in high-performance computing settings.
Tiling , Ensemble Machine Learning , Computing System Performance , Cache Efficiency , LLVM
[1] E. Hammami and Y. Slama, “An overview on loop tiling techniques for code generation,” in Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA, IEEE Computer Society, Jul. 2017, pp. 280–287. doi: 10.1109/AICCSA.2017.168.
[2] V. Kelefouras, K. Djemame, G. Keramidas, and N. Voros, “A Methodology for Efficient Tile Size Selection for Affine Loop Kernels,” Int J Parallel Program, vol. 50, no. 3–4, pp. 405–432, Aug. 2022, doi: 10.1007/s10766-022-00734-5.
[3] Alwan, E., Al Baity, R. "Optimizing Program Efficiency with Loop Unroll Factor Prediction", Information Sciences Letters, 2023, 12(6), pp. 2207–2213
[4] S. Parsa and M. Hamzei, “NESTED-LOOPS TILING FOR PARALLELIZATION AND LOCALITY OPTIMIZATION,” Computing and Informatics, vol. 36, pp. 566–596, 2017, doi: 10.4149/cai.
[5] T. Sharma, A. Jatain, S. Bhaskar, and K. Pabreja, “Ensemble Machine Learning Paradigms in Software Defect Prediction,” in Procedia Computer Science, Elsevier B.V., 2022, pp. 199–209. doi: 10.1016/j.procs.2023.01.002.
[6] https://www.kaggle.com/datasets/noorasalam/tile-size-selection
[7] D. Joseph, J. L. Aragón, J.-M. Parcerisa, and A. González, “TCOR: A Tile Cache with Optimal Replacement.”
[8] H. Wu and D. Levinson, “The ensemble approach to forecasting: A review and synthesis,” Transp Res Part C Emerg Technol, vol. 132, Nov. 2021, doi: 10.1016/j.trc.2021.103357.
[9] T. M. Hope, "Linear regression," in Machine Learning, Academic Press, 2020, pp. 67-81.
[10] M. P. Rajan, "An efficient Ridge regression algorithm with parameter estimation for data analysis in machine learning," SN Computer Science, vol. 3, no. 2, p. 171, Mar. 2022.
[11] P. Jain, A. Choudhury, P. Dutta, K. Kalita, and P. Barsocchi, "Random forest regression-based machine learning model for accurate estimation of fluid flow in curved pipes," Processes, vol. 9, no. 11, p. 2095, Nov. 2021.
[12] U. Kumar, R. Bondhugula, B-Tech, P. Sadayappan, A. Atanas, R. Gagan, and A. J. Ramanujam, “Effective Automatic Parallelization and Locality Optimization Using The Polyhedral Model Dissertation Committee.”
[13] U. Bondhugula, M. Baskaran, S. Krishnamoorthy, J. Ramanujam, A. Rountev, and P. Sadayappan, “Automatic Transformations for Communication-Minimized Parallelization and Locality Optimization in the Polyhedral Model.”
[14] J. M. Cardoso, J. G. F. Coutinho, and P. C. Diniz, "Chapter 5-Source code transformations and optimizations," in Embedded Computing for High Performance, pp. 137-183, 2017.
[15] F. Johnson, O. Oluwatobi, O. Folorunso, A. Ojumu, and A. Quadri, "Optimized ensemble machine learning model for software bugs prediction," in Innovations in Systems and Software Engineering, vol. 19, pp. 1-11, 2022, doi: 10.1007/s11334-022-00506-x.
[16] S. Afrifa, V. Varadarajan, P. Appiahene, T. Zhang, and E. A. Domfeh, “Ensemble Machine Learning Techniques for Accurate and Efficient Detection of Botnet Attacks in Connected Computers,” Eng, vol. 4, no. 1, pp. 650–664, Mar. 2023, doi: 10.3390/eng4010039.
[17] S. Liu, Y. Cui, Q. Jiang, Q. Wang, and W. Wu, “An efficient tile size selection model based on machine learning,” J Parallel Distrib Comput, vol. 121, pp. 27–41, Nov. 2018, doi: 10.1016/j.jpdc.2018.06.005.
[18] https://www.ece.lsu.edu/jxr/pluto/index.html
[19] A. C. De Melo, "The new linux 'perf' tools," in Slides from Linux Kongress, vol. 18, pp. 1-42, Sep. 2010.
