Skip to main content
SpringerLink
Log in

Statistical measures for quantifying task and machine heterogeneities

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

We study heterogeneous computing (HC) systems that consist of a set of different machines that have varying capabilities. These machines are used to execute a set of heterogeneous tasks that vary in their computational complexity. Finding the optimal mapping of tasks to machines in an HC system has been shown to be, in general, an NP-complete problem. Therefore, heuristics have been used to find near-optimal mappings. The performance of allocation heuristics can be affected significantly by factors such as task and machine heterogeneities. In this paper, we identify different statistical measures used to quantify the heterogeneity of HC systems, and show the correlation between the performance of the heuristics and these measures through simple mapping examples and synthetic data analysis. In addition, we illustrate how regression trees can be used to predict the most appropriate heuristic for an HC system based on its heterogeneity.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Armstrong R, Hensgen D, Kidd T (1998) The relative performance of various mapping algorithms is independent of sizable variances in run-time predictions. In: 7th IEEE heterogeneous computing workshop (HCW ’98), 1998, pp 79–87

    Chapter  Google Scholar 

  2. Ali S, Braun TD, Siegel HJ, Maciejewski AA, Beck N, Bölöni L, Maheswaran M, Reuther AI, Robertson JP, Theys MD, Yao B (2005) Characterizing resource allocation heuristics for heterogeneous computing systems. In: Parallel, distributed, and pervasive computing. Advances in computers, vol 63, pp 91–128

    Google Scholar 

  3. Ali S, Kim JK, Siegel HJ, Maciejewski AA (2008) Static heuristics for robust resource allocation of continuously executing applications. J Parallel Distrib Comput 68(8):1070–1080

    Article  Google Scholar 

  4. Al-Qawasmeh AM, Maciejewski AA, Siegel HJ (2010) Characterizing heterogeneous computing environments using singular value decomposition. In: 19th heterogeneity in computing workshop (HCW 2010), 24th international parallel and distributed processing symposium, workshops and PhD forum (IPDPSW 2010), Apr 2010

    Google Scholar 

  5. Ali S, Siegel HJ, Maheswaran M, Hensgen D, Ali S (2000) Representing task and machine heterogeneities for heterogeneous computing systems. Tamkang J Sci Eng 3(3):195–207. Special 50th anniversary issue

    Google Scholar 

  6. Barada H, Sait SM, Baig N (2001) Task matching and scheduling in heterogeneous systems using simulated evolution. In: 10th heterogeneous computing workshop (HCW 2001), 15th IEEE international parallel and distributed processing symposium (IPDPS 2001), Apr 2001

    Google Scholar 

  7. Banicescu I, Velusamy V (2001) Performance of scheduling scientific applications with adaptive weighted factoring. In: 10th heterogeneous computing workshop (HCW 2001), 15th IEEE international parallel and distributed processing symposium (IPDPS 2001), Apr 2001

    Google Scholar 

  8. Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth, Belmont

    MATH  Google Scholar 

  9. Braun TD, Siegel HJ, Beck N, Bölöni L, Freund RF, Hensgen D, Maheswaran M, Reuther AI, Robertson JP, Theys MD, Yao B (2001) A comparison of eleven static heuristics for mapping a class of independent tasks onto heterogeneous distributed computing systems. J Parallel Distrib Comput 61(6):810–837

    Article  Google Scholar 

  10. Braun TD, Siegel HJ, Maciejewski AA, Hong Y (2008) Static mapping heuristics for tasks with dependencies, priorities, deadlines, and multiple versions in heterogeneous environments. J Parallel Distrib Comput 68(11):1504–1516

    Article  Google Scholar 

  11. Burns A, Punnekkat S, Littlewood B, Wright D (1997) Probabilistic guarantees for fault tolerant real-time systems. Technical Report Design for Validation (DeVa) TR No. 44, Esprit Long Term Research Project No. 20072, Department of Computer Science, University of Newcastle upon Tyne, UK

  12. Canon L, Jeannot E (2009) Precise evaluation of the efficiency and the robustness of stochastic DAG schedules. Research Report 6895, INRIA, April

  13. Chiang RC, Maciejewski AA, Rosenberg AL, Siegel HJ (2010) Statistical predictors of computing power in heterogeneous clusters. In: 19th heterogeneity in computing workshop (HCW 2010), 24th International parallel and distributed processing symposium, workshops and PhD forum (IPDPSW 2010), Apr 2010

    Google Scholar 

  14. Coffman EG (ed) (1976) Computer and job-shop scheduling theory. Wiley, New York

    MATH  Google Scholar 

  15. Couceiro M, Romano P, Rodrigues L (2010) A machine learning approach to performance prediction of total order broadcast protocols. In: 4th IEEE international conference on self-adaptive and self-organizing systems (SASO), 2010

    Google Scholar 

  16. Dhodhi MK, Ahmad I, Yatama A (2002) An integrated technique for task matching and scheduling onto distributed heterogeneous computing systems. J Parallel Distrib Comput 62:1338–1361

    Article  MATH  Google Scholar 

  17. Ding Q, Chen G (2001) A benefit function mapping heuristic for a class of meta-tasks in grid environments. In: CCGRID ’01: 1st international symposium on cluster computing and the grid, May 2001

    Google Scholar 

  18. Eslamnour B, Ali S (2009) Measuring robustness of computing systems. Simul Model Pract Theory 17(9):1457–1467

    Article  Google Scholar 

  19. Fernandez-Baca D (1989) Allocating modules to processors in a distributed system. IEEE Trans Softw Eng 15(11):1427–1436

    Article  Google Scholar 

  20. Ghanbari S, Meybodi MR (2005) On-line mapping algorithms in highly heterogeneous computational grids: a learning automata approach. In: International conference on information and knowledge technology (IKT ’05), May 2005

    Google Scholar 

  21. Ghafoor A, Yang J (1993) A distributed heterogeneous supercomputing management system. IEEE Trans Comput 26(6):78–86

    Google Scholar 

  22. Gubner JA (2006) Probability and random processes for electrical and computer engineering. Cambridge University Press, Cambridge

    Google Scholar 

  23. Huang D, Yuan Y, Zhang L, Zhao K (2009) Research on tasks scheduling algorithms for dynamic and uncertain computing grid based on a + bi connection number of SPA. J Softw 4(10):1102–1109

    Google Scholar 

  24. Ibarra OH, Kim CE (1977) Heuristic algorithms for scheduling independent tasks on nonidentical processors. J ACM 24(2):280–289

    Article  MathSciNet  MATH  Google Scholar 

  25. Jinquan Z, Lina N, Changjun J (2005) A heuristic scheduling strategy for independent tasks on grid. In: 8th international conference on high-performance computing in Asia–Pacific region, Nov 2005

    Google Scholar 

  26. Kafil M, Ahmad I (1998) Optimal task assignment in heterogeneous distributed computing systems. IEEE Concurr 6(3):42–51

    Article  Google Scholar 

  27. Kaya K, Ucar B, Aykanat C (2007) Heuristics for scheduling file-sharing tasks on heterogeneous systems with distributed repositories. J Parallel Distrib Comput 67(3):271–285

    Article  MATH  Google Scholar 

  28. Khan SU, Ahmad I (2006) Non-cooperative, semi-cooperative, and cooperative games-based grid resource allocation. In: 20th international parallel and distributed processing symposium (IPDPS 2006), Apr 2006

    Google Scholar 

  29. Khokhar A, Prasanna VK, Shaaban ME, Wang C (1993) Heterogeneous computing: challenges and opportunities. IEEE Trans Comput 26(6):18–27

    Google Scholar 

  30. Kim J-K, Hensgen DA, Kidd T, Siegel HJ, John DS, Irvine C, Levin T, Porter NW, Prasanna VK, Freund RF (2006) A flexible multi-dimensional QoS performance measure framework for distributed heterogeneous systems. Cluster Comput 6(3):281–296. Special issue on cluster computing in science and engineering

    Article  Google Scholar 

  31. Maheswaran M, Ali S, Siegel HJ, Hensgen D, Freund RF (1999) Dynamic mapping of a class of independent tasks onto heterogeneous computing systems. J Parallel Distrib Comput 59(2):107–121

    Article  Google Scholar 

  32. Mehta AM, Smith J, Siegel HJ, Maciejewski AA, Jayaseelan A, Ye B (2007) Dynamic resource allocation heuristics that manage trade-off between makespan and robustness. J Supercomput 42(1):33–58. Special issue on grid technology

    Article  Google Scholar 

  33. Michalewicz Z, Fogel DB (eds) (2000) How to solve it: modern heuristics. Springer, New York

    MATH  Google Scholar 

  34. Poe J, Cho C-B, Li T (2008) Using analytical models to efficiently explore hardware transactional memory and multi-core co-design. In: 20th international symposium on computer architecture and high performance computing, 2008

    Google Scholar 

  35. Press WH, Flannery BP, Teukolsky SA, Vetterling WT (1988) Numerical recipes in C. Cambridge University Press, Cambridge

    MATH  Google Scholar 

  36. Singh H, Youssef A (1996) Mapping and scheduling heterogeneous task graphs using genetic algorithms. In: 5th IEEE heterogeneous computing workshop (HCW ’96), 1996, pp 86–97

    Google Scholar 

  37. Wu M, Shu W, Zhang H (2000) Segmented Min-Min: a static mapping algorithm for meta-tasks on heterogeneous computing systems. In: 9th IEEE heterogeneous computing workshop, Mar 2000, pp 375–385

    Google Scholar 

  38. Wu M, Shu W (2001) A high-performance mapping algorithm for heterogeneous computing systems. In: 15th international parallel and distributed processing symposium (IPDPS 2001), Apr 2001

    Google Scholar 

  39. Xu D, Nahrstedt K, Wichadakul D (2001) QoS and contention-aware multi-resource reservation. Cluster Comput 4(2):95–107

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO, USA

    Abdulla M. Al-Qawasmeh, Anthony A. Maciejewski, Jay Smith, Howard Jay Siegel & Jerry Potter

  2. Department of Computer Science, Colorado State University, Fort Collins, CO, USA

    Howard Jay Siegel

  3. Department of Statistics, Colorado State University, Fort Collins, CO, USA

    Haonan Wang

  4. DigitalGlobe Inc., Longmont, CO, USA

    Jay Smith

Authors
  1. Abdulla M. Al-Qawasmeh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anthony A. Maciejewski
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Haonan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jay Smith
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Howard Jay Siegel
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jerry Potter
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Abdulla M. Al-Qawasmeh.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Al-Qawasmeh, A.M., Maciejewski, A.A., Wang, H. et al. Statistical measures for quantifying task and machine heterogeneities. J Supercomput 57, 34–50 (2011). https://doi.org/10.1007/s11227-011-0572-x

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-011-0572-x

Keywords

Search

Navigation