APPLICATION OF THE LOAD BALANCING METHOD ON HIGH PARALLEL COMPUTING CLUSTER SYSTEMS
https://doi.org/10.55452/1998-6688-2021-18-1-117-124
Abstract
High parallel efficiency for various large-scale tasks requires that the computational load is evenly distributed among all computational processors. This study presents a dynamic load balancing scheme that improves the performance of complex coupled simulations with non-trivial domain expansions. In addition, the high scaling experiment results show that the benefit of load balancing is proportional to the degree of parallelism.
About the Authors
A. Issakhov
Казахский Национальный университет им. аль-Фараби; АО «Казахстанско-Британский технический университет»
Kazakhstan
Kazakhstan
A. Abylkassymova
АО «Казахстанско-Британский технический университет»
Kazakhstan
Kazakhstan
M. Mansurova
Казахский Национальный университет им. аль-Фараби
Kazakhstan
Kazakhstan
References
1. Doorly, D., Taylor, D., Schroter, R., 2008c. Mechanics of airflow in the human nasal airways. Respir. Physiol. Neurobiol. 163, 100–110.
2. Girardin, M., E. Bilgen, and P. Arbour. Experimental study of velocity fields in a human nasal fossa by laser anemometry. Ann. Otol. Rhinol. Laryngol. 92:231–236, 1983.
3. Croce, C., Fodil, R., Durand, M., Sbirlea-Apiou, G., Caillibotte, G., Papon, J.-F., Blondeau, J.-R., Coste, A., Isabey, D., Louis, B., 2006. In vitro experiments and numerical simulations of airflow in realistic nasal airway geometry. Ann. Biomed. Eng. 34, 997–1007.
4. Keyhani, K., Scherer, P., Mozell, M., 1995. Numerical simulation of airflow in the human nasal cavity. J. Biomech. Eng. 117, 429-441.
5. Wang, T., Chen, D., Wang, P., Chen, J., Deng, J., 2016. Investigation on the nasal airflow characteristics of anterior nasal cavity stenosis. Braz. J. Med. Biol. Res. 49.
6. Naftali S, Rosenfeld M, Wolf M, Elad D (2005) The air-conditioning capacity of the human nose. Ann Biomed Eng 33:545–553.
7. Hendrickson B., Devine K. Dynamic load balancing in computational mechanics, Comp. Methods in Appl. Mech. Eng., vol. 184, no. 2–4, pp. 485–500, Apr. 2000.
8. Pinar A., Aykanat C. Fast optimal load balancing algorithms for 1D partitioning, J. Parallel Distrib. Comput., vol. 64, no. 8, pp. 974–996, Aug. 2004.
9. Pilkington J. R., Baden S. B. Dynamic partitioning of non-uniform structured workloads with spacefilling curves, IEEE Trans. Parallel Distrib. Syst., vol. 7, no. 3, pp. 288–300, Mar. 1996.
10. Lieber M., Nagel W. E. Scalable high-quality 1D partitioning, in HPCS, 2014, pp. 112–119.
11. Pinar A., Kartal Tabak E., Aykanat C. One-dimensional partitioning for heterogeneous systems: Theory and practice, J. Parallel Distrib. Comput., vol. 68, pp. 1473–1486, Nov. 2008.
12. Menon H., Jain N., Zheng G., Kale L. Automated load balancing invocation based on application characteristics, in IEEE Cluster Comput., 2012, pp. 373–381.
13. Issakhov A. Mathematical modeling of the discharged heat water effect on the aquatic environment from thermal power plant under various operational capacities // Applied Mathematical Modelling, –2016, Volume 40, Issue 2, pp. 1082–1096
14. Ashby S. The Opportunities and Challenges of Exascale Computing. ASCAC subcommittee, US - DOE Report, 2010.
15. Böhme D. Characterizing Load and Communication Imbalance in Parallel Applications, ser. IAS. Forschungszentrum Jülich, 2014, vol. 23.
16. DeRose L., Homer B., Johnson D. Detecting Application Load Imbalance on High End Massively Parallel Systems, Parallel Processing, pp. 150–159, Aug. 2007.
17. Anderson E., Bai Z., Bischof C., Blackford S., Demmel J., Dongarra J., Du Croz J., Greenbaum A., Hammarling S., McKenney A., Sorensen D. LAPACK Users’ Guide, 3rd ed. SIAM, 1999. ISBN 0-89871-447-8
18. Lieber M., Gößner K., Nagel W. E. The potential of diffusive load balancing at large scale, in EuroMPI, 2016, pp. 154–157.
19. Zhang X., Yan Y. Modeling and characterizing parallel computing performance on heterogeneous networks of workstations, Parallel Distrib. Comput., pp. 25–34, Oct. 1995.
20. Zheng G., Bhatelé A., Meneses E., Kalé L. V. Periodic hierarchical load balancing for large supercomputers, Int. J. High Perform. Comput. Appl., vol. 25, no. 4, pp. 371–385, Nov. 2011.
Review
For citations:
Issakhov A., Abylkassymova A., Mansurova M. APPLICATION OF THE LOAD BALANCING METHOD ON HIGH PARALLEL COMPUTING CLUSTER SYSTEMS. Herald of the Kazakh-British technical university. 2021;18(1):117-124. (In Russ.) https://doi.org/10.55452/1998-6688-2021-18-1-117-124
Views:
345
Email this article 