Bubble Task: A Dynamic Execution Throttling Method for Multi-core Resource Management

  • Dongyou Seo
  • Myungsun Kim
  • Hyeonsang Eom
  • Heon Y. Yeom
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8828)

Abstract

Memory bandwidth is a major resource which is shared among all CPU cores. The development speed of memory bandwidth cannot catch up with the increasing number of CPU cores. Thus, the contention for occupying more memory bandwidth among concurrently executing tasks occurs. In this paper, we have presented Bubble Task method which mitigates memory contention via throttling technique. We made a memory contention modeling for dynamically deciding throttling ratio and implemented both software and hardware versions to present trade-off between fine-grained adjustment and stable fairness. Bubble Task can lead to performance improvement in STREAM benchmark suite which is one of the most memory hungry benchmark by 21 % and fairness in memory bandwidth sharing among SPEC CPU 2006 applications which have different memory access patterns.

Keywords

Multicore processor SMP platform CPU execution throttling Resource contention Bandwidth fairness 

References

  1. 1.
  2. 2.
  3. 3.
    Patterson, D.: Latency lags bandwidth. In: Communication of the ACM (2004)Google Scholar
  4. 4.
    Zhuravlev, S., Blagodurov, S., Fedorova, A.: Addressing shared resource contention in multicore processors via Scheduling. In: ASPLOS (2010)Google Scholar
  5. 5.
    Zhuravlev, S., Saez, J.C., Blagodurov, S., Fedorova, A.: Survey of scheduling techniques for addressing shared resources in multicore processors. In: ACM Computing Surveys, September 2011Google Scholar
  6. 6.
    Kim, S., Eom, H., Yeom, H.Y.: Virtual machine consilidation based on interference modeling. J. Supercomput. 64, 28–37 (2013)CrossRefGoogle Scholar
  7. 7.
    Merkel, A., Stoess, H., Bellosa, F.: Resource-conscious scheduling for energy efficiency on multicore processors. In: EuroSys (2010)Google Scholar
  8. 8.
    Jiang, Y., Shen, X., Chen, J., Tripathi, R.: Analysis and approximation of optimal co-scheduling on chip multiprocessors. In: PACT (2008)Google Scholar
  9. 9.
    Xie, Y., Loh, G.: Dynamic classification of program memory behaviors in CMPs. In: Proceedings of CMP-MSI, held in conjunction with ISCA (2008)Google Scholar
  10. 10.
    Ahn, J., Kim, C., Han, J.: Dynamic virtual machine scheduling in clouds for architectural shared resources. In: HotCloud (2012)Google Scholar
  11. 11.
    Chandra, D., Guo, F., Kim, S., Solihin, Y.: Predicting interthread cache contention on a chip multi-processor architecture. In: HPCA (2005)Google Scholar
  12. 12.
    Zhang, X., Dwarkadas, S., Shen, K.: Hardware execution throttling for multi-core resource management. In: ATC (2009)Google Scholar
  13. 13.
    Naveh, A., Rotem, E., Mendelson, A., Gochman, S., Chabukswar, R., Krishnan, K., Kumar, A.: Power and thermal management in the Intel Core Duo processor. Intel Technol. J. 10(2), 109–122 (2006)CrossRefGoogle Scholar
  14. 14.
    Fedorova, A., Seltzer, M., Smith, M.: Improving performance isolation on chip multiprocessors via an operating system scheduler. In: 16th International Conference on Parallel Architecture and Compilation Techniques, pp. 25–36. Brasov, Romania, September 2007Google Scholar
  15. 15.
    Mars, J., Tang, L., Hundt, R., Skdron, K., Soffa, M.L.: Bubble-up: increasing utilization in modern warehouse scale computers via sensible co-locations. In: MICRO (2011)Google Scholar
  16. 16.
  17. 17.
  18. 18.
  19. 19.
    Intel(R) 64 and IA-32 Arhcitectures Software Develper’s Manual, Volume 3B. System Programming Guide, Part 2Google Scholar
  20. 20.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Dongyou Seo
    • 1
  • Myungsun Kim
    • 2
  • Hyeonsang Eom
    • 1
  • Heon Y. Yeom
    • 1
  1. 1.School of Computer Science and EngineeringSeoul National UniversitySeoulKorea
  2. 2.DMC R&D Samsung ElectronicsSuwonKorea

Personalised recommendations