Analytical Estimation of the Scalability of Iterative Numerical Algorithms on Distributed Memory Multiprocessors
- 11 Downloads
This article presents a new high-level parallel computational model named BSF "— Bulk Synchronous Farm. The BSF model extends the BSP model to deal with the computeintensive iterative numericalmethods executed on distributed-memory multiprocessor systems. The BSF model is based on the master-worker paradigm and the SPMD programming model. The BSF model makes it possible to predict the upper scalability bound of a BSF-program with great accuracy. The BSF model also provides equations for estimating the speedup and parallel efficiency of a BSF-program.
Keywords and phrasesParallel computation model bulk synchronous farm BSF model iterative algorithms distributed memory scalability bound
Unable to display preview. Download preview PDF.
- 1.G. Bilardi and A. Pietracaprina, “Models of computation, Theoretical,” in Encyclopedia of Parallel Computing (Springer US, Boston, MA, 2011), pp. 1150–1158. doi 10.1007/978-0-387-09766-4_218Google Scholar
- 8.D. Culler, R. Karp, D. Patterson, A. Sahay, K. E. Schauser, E. Santos, R. Subramonian, and T. von Eicken, “LogP: towards a realistic model of parallel computation,” in Proceedings of the 4th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming—PPOPP’93 (ACM Press, New York, 1993), pp. 1–12. doi 10.1145/155332.155333Google Scholar
- 10.G. Liu, Y. Wang, T. Zhao, J. Gu, and D. Li, “mHLogGP: a parallel computation model for CPU/GPU,” in Network and Parallel Computing, Proceedings of the 9th IFIP International Conference NPC 2012, Gwangju, Korea, Sept. 6–8, 2012, Ed. by J. J. Park, A. Zomaya, and S. S. Yeo (Springer, Berlin, Heidelberg, 2012), pp. 217–224. doi 10.1007/978-3-642-35606-3_25Google Scholar
- 14.L. Yuan, Y. Zhang, Y. Tang, L. Rao, and X. Sun, “LogGPH: a parallel computational model with hierarchical communication awareness,” in Proceedings of the 2010 13th IEEE International Conference on Computational Science and Engineering CSE’10 (IEEE Comput. Soc., Washington, DC, 2010), pp. 268–274. doi 10.1109/CSE.2010.40Google Scholar
- 15.A. Tiskin, “BSP (Bulk Synchronous Parallelism),” in Encyclopedia of Parallel Computing (Springer US, Boston, MA, 2011), pp. 192–199. doi 10.1007/978-0-387-09766-4_311Google Scholar
- 19.S. Ma and A. Chronopoulos, “Implementation of iterative methods for large sparse nonsymmetric linear systems on a parallel vector machine,” Int. J. High Perform. Comput. Appl. 4 (4), 9–24 (1990). doi 10.1177/109434209000400402Google Scholar
- 22.F. Darema, “SPMD computational model,” in Encyclopedia of Parallel Computing (SpringerUS, Boston, MA, 2011), pp. 1933–1943. doi 10.1007/978-0-387-09766-4_26Google Scholar
- 23.I. Sokolinskaya and L. B. Sokolinsky, “On the solution of linear programming problems in the age of big data,” in Parallel Computational Technologies. PCT 2017, Commun. Comput. Inform. Sci. 753, 86–100 (2017). doi 10.1007/978-3-319-67035-5_7Google Scholar
- 24.I. Sokolinskaya and L. B. Sokolinsky, “Scalability evaluation of NSLP algorithm for solving non-stationary linear programming problems on cluster computing systems,” in Supercomputing, RuSCDays 2017, Commun. Comput. Inform. Sci. 793, 40–53 (2017). doi 10.1007/978-3-319-71255-0_4Google Scholar