Abstract
This paper presents a new expression for an isoefficiency function which can be applied both to homogeneous and heterogeneous systems. Using this new function, called H-isoefficiency, it is now possible to analyze the scalability of heterogeneous clusters. In order to show how this new metric can be used, a theoretical a priori analysis of the scalability of a Gauss Elimination algorithm is presented, together with a model evaluation which demonstrates the correlation between the theoretical analysis and the experimental results.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bosque JL, Robles OD, Toharia P, Pastor L (2010) H-isoefficiency: Scalability metric for heterogeneous systems. In: 10th international conference on computational and mathematical methods in science and engineering, CMMSE, Almeria, Spain, June 2010, pp 240–250
Chen Y, Sun X-H, Wu M (2008) Algorithm-system scalability of heterogeneous computing. J Parallel Distrib Comput 68(11):1403–1412
Grama AY, Gupta A, Kumar V (1993) Isoefficiency: Measuring the scalability of parallel algorithms and architectures. IEEE Parallel Distrib Technol 1(3):12–21
Gustafson JL (1988) Reevaluating Amdahl’s law. Commun ACM 31(5):532–533
Gustafson JL, Montry GR, Benner RE (1988) Development of parallel methods for a 1024-processor hypercube. SIAM J Sci Stat Comput 9(4):609–638
Jogalekar P, Woodside M (2000) Evaluating the scalability of distributed systems. IEEE Trans Parallel Distrib Syst 11(6):589–603
Kalinov AYa (2006) Scalability of heterogeneous parallel systems. Program Comput Softw 32(1):1–7
Karp AH, Platt HP (1990) Measuring parallel processor performance. Commun ACM 22(5):539–543
Kumar V, Rao VN (1987) Parallel depth-first search on multiprocessors: Part II: Analysis. Int J Parallel Program 16(6):501–519
Pastor L, Bosque JL (2001) Efficiency and scalability models for heterogeneous clusters. In: Third IEEE international conference on cluster computing, Los Angeles, California, October 2001. IEEE Comput Soc, Los Alamitos, pp 427–434
Sun X-H, Gustafson JL (1991) Sizeup: a new parallel performance metric. In: Proceedings of the 1991 international conference on parallel processing. Software, vol II. CRC Press, Boca Raton, pp 298–299
Sun X.-H., Rover DT (1994) Scalability of parallel algorithm–machine combinations. IEEE Trans Parallel Distrib Syst 5(6):599–613
Yan Y, Zhang X, Ma Q (1997) Software support for multiprocessor latency measurement and evaluation. IEEE Trans Softw Eng 23(1):4–16
Zhang X, Yan Y (1995) Modelling and characterizing parallel computing performance on heterogeneous networks of workstations. In: Proc 7th IEEE symp on parallel and distributed processing, pp 25–35
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bosque, J.L., Robles, O.D., Toharia, P. et al. Evaluating scalability in heterogeneous systems. J Supercomput 58, 367–375 (2011). https://doi.org/10.1007/s11227-011-0593-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-011-0593-5