Reinforcement learning-based spatial sorting based dynamic task allocation on networked multicore GPU processors

Abstract

Owing to the advancements in cloud computing our lives are significantly altering the means of utilizing data by the data-intensive business and research. The coming era of ubiquitous computing is greatly supported by the evolution of cloud computing with networked multicore GPU processors to avail consistent data utilization. In such a domain, computing, data stockpiling and correspondence turns into a utility. In this paper, a new algorithm is devised that aids in ranking the tasks based on generated cluster indices. The proposed algorithm offers a new strategy for simultaneous task partitioning, it’s ranking and load assignment, thus improving the computational performance of the given workload.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

References

  1. Andersen TD, Mascagni M (2019) Memory efficient lagged-Fibonacci random number generators for GPU supercomputing. Monte Carlo Methods Appl. https://doi.org/10.1515/mcma-2014-0017

    Article  MATH  Google Scholar 

  2. Cheng Y, Xu G (2019) A novel task provisioning approach fusing reinforcement learning for big data. IEEE Access 7:143699–143709

    Article  Google Scholar 

  3. Dave A, Patel B, Bhatt G (2016) Load balancing in cloud computing using optimization techniques: a study. In: 2016 international conference on communication and electronics systems (ICCES). https://doi.org/10.1109/cesys.2016.7889883

  4. Denoyelle N, Goglin B et al (2018) Modeling non-uniform memory access on large compute nodes with the cache-aware roofline model. IEEE Trans Parallel Distrib Syst 30(6):1374–1389. https://doi.org/10.1109/TPDS.2018.2883056

    Article  Google Scholar 

  5. Gill SK, Singh VP, Sharma P, Kumar D (2019) A comparative study of various sorting algorithms. Int J Adv Stud Sci Res 4(1):405–416

    Google Scholar 

  6. He L, Li J et al (2019) Dynamic scheduling of hybrid tasks with time windows in data relay satellite networks. IEEE Trans Veh Technol 68(5):4989–5004. https://doi.org/10.1109/TVT.2019.2903737

    Article  Google Scholar 

  7. Hussain SB, Hu W (2017) Low-latency dynamic wavelength and bandwidth allocation algorithm for NG-EPON. IEEE/OSA J Opt Commun Netw 9(12):1108–1115. https://doi.org/10.1364/JOCN.9.001108

    Article  Google Scholar 

  8. Kiran N, Pan C (2019) Joint resource allocation and computation offloading in mobile edge computing for SDN based wireless networks. J Commun Netw 22(1):1–11. https://doi.org/10.1109/JCN.2019.000046

    Article  Google Scholar 

  9. Kong Y, Zhang M et al (2019) An auction-based approach for group task allocation in an open network environment. Comput J 59(3):403–422. https://doi.org/10.1093/comjnl/bxv061

    MathSciNet  Article  Google Scholar 

  10. Lee H, Faruque MAA (2018) GPU architecture aware instruction scheduling for improving soft-error reliability. IEEE Trans Multi-Scale Comput Syst 3(2):86–99. https://doi.org/10.1109/TMSCS.2017.2667661

    Article  Google Scholar 

  11. Li H, Qi Q et al (2020) Mobile wireless multimedia sensor networks image compression task collaboration based on dynamic alliance. IEEE Access. 8:86024–86037. https://doi.org/10.1109/ACCESS.2020.2992795

    Article  Google Scholar 

  12. Najam S, Ahmed J et al (2019) Run-time resource management controller for power efficiency of GP-GPU architecture. IEEE Access. 7:25493–25505. https://doi.org/10.1109/ACCESS.2019.2901010

    Article  Google Scholar 

  13. Neamatollahi P, Naghibzadeh M et al (2018) Distributed clustering-task scheduling for wireless sensor networks using dynamic hyper round policy. IEEE Trans Mob Comput 17(2):334–347. https://doi.org/10.1109/TMC.2017.2710050

    Article  Google Scholar 

  14. Singh SK, Vidyarthi DP (2015) Independent tasks scheduling using parallel PSO in multiprocessor systems. Int J Grid High-Perform Comput 7(2):1–17. https://doi.org/10.4018/ijghpc.2015040101

    Article  Google Scholar 

  15. Topa T (2016) Load-balanced fortran-based out-of-GPU memory implementation of the method of moments. IEEE Antennas Wirel Propag Lett 16:813–816. https://doi.org/10.1109/LAWP.2016.2605042

    Article  Google Scholar 

  16. Vilches A, Navarro A et al (2015) Mapping streaming applications on commodity multi-CPU and GPU on-chip processors. IEEE Trans Parallel Distrib Syst 27(4):1099–1115. https://doi.org/10.1109/TPDS.2015.2432809

    Article  Google Scholar 

  17. Vyas U (2016) Designing your first cloud with OpenStack. Appl OpenStack Des Patterns. https://doi.org/10.1007/978-1-4842-2454-0_1

    Article  Google Scholar 

  18. Wachowiak MP, Timson MC et al (2017) Adaptive particle swarm optimization with heterogeneous multicore parallelism and GPU acceleration. IEEE Trans Parallel Distrib Syst 28(10):2784–2793. https://doi.org/10.1109/TPDS.2017.2687461

    Article  Google Scholar 

  19. Wang F, Jie Xu et al (2020) Optimal energy allocation and task offloading policy for wireless powered mobile edge computing systems. IEEE Trans Wirel Commun 19(4):2443–2459. https://doi.org/10.1109/TWC.2020.2964765

    MathSciNet  Article  Google Scholar 

  20. Wu M, Chen Q et al (2020) BPCM: a flexible high-speed bypass parallel communication mechanism for GPU cluster. IEEE Access. 8:103256–103272. https://doi.org/10.1109/ACCESS.2020.2999096

    Article  Google Scholar 

  21. Zhang Q, Liu L (2016) Workload adaptive shared memory management for high performance network I/O in virtualized cloud. IEEE Trans Comput 65(11):3480–3494. https://doi.org/10.1109/TC.2016.2532865

    MathSciNet  Article  MATH  Google Scholar 

  22. Zhang Q, Liu L et al (2017) MemFlex: a shared memory swapper for high performance VM execution. IEEE Trans Comput 66(9):1645–1652. https://doi.org/10.1109/TC.2017.2686850

    MathSciNet  Article  Google Scholar 

  23. Zhang Q, Gui L et al (2020) Dynamic task offloading and resource allocation for mobile-edge computing in dense cloud RAN. IEEE Internet Things J 7(4):3282–3299. https://doi.org/10.1109/JIOT.2020.2967502

    Article  Google Scholar 

  24. Zhou A, Wang S, Hsu C, Sun Q, Yang F (2015) Task rescheduling optimization to minimize network resource consumption. Multimed Tools Appl 75(20):12901–12917. https://doi.org/10.1007/s11042-015-2549-x

    Article  Google Scholar 

  25. Zhou Q, Yang L et al (2018) Reconfigurable instruction-based multicore parallel convolution and its application in real-time template matching. IEEE Trans Comput 67(12):1780–1793. https://doi.org/10.1109/TC.2018.2844351

    MathSciNet  Article  MATH  Google Scholar 

  26. Zouaneb I, Belarbi M, Chouarfia A (2016) Multi approach for real-time systems specification: a case study of GPU parallel systems. Int J Big Data Intell 3(2):122. https://doi.org/10.1504/ijbdi.2016.077385

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to K. Ramesh.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ramesh, K., Thilagavathy, A. Reinforcement learning-based spatial sorting based dynamic task allocation on networked multicore GPU processors. J Ambient Intell Human Comput (2021). https://doi.org/10.1007/s12652-020-02716-2

Download citation

Keywords

  • Cloud computing
  • Reinforcement algorithm
  • Data stockpiling
  • GPU processor
  • Task allocation