Advertisement

Multi-GPU Approach for Development of Parallel and Scalable Pub-Sub System

  • Medha A. Shah
  • Dinesh Kulkarni
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 810)

Abstract

Event matching plays an important part in the overall attainment of the content-based Publish-Subscribe system. These systems demand guaranteed message delivery, high throughput and low matching time. Existing parallel content matching algorithms make use of multiple cores and off the shelf hardware easily available in today’s modern computers. For a large number of events and subscriptions, these algorithms suffer from performance degradation. In this paper, we propose high-performance Publish-Subscribe system designed to run efficiently on multiple GPUs. Performance comparison with existing CCM (CUDA Content Matching) algorithm clearly demonstrates 32% improvement in matching latency.

Keywords

High performance Parallel matching algorithm Multiple GPUs Matching latency 

References

  1. 1.
    Margara, A., Cugola, G.: High performance publish-subscribe matching using parallel hardware. In: IEEE Trans. Parallel Distrib. Syst. 25 (2014)CrossRefGoogle Scholar
  2. 2.
    Shah, M.A., Kulkarni, D.B.: Doctoral symposium: design and development of high performance, scalable content based publish subscribe system. In: Proceedings of the 10th ACM International Conference on Distributed and Event-based Systems (2016)Google Scholar
  3. 3.
    Farroukh, A., Ferzli, E., Tajuddin, N., Jacobsen, H.-A.: Parallel event processing for content-based publish/subscribe systems. In: DEBS vol. 09, pp. 8:1–8:4 (2009)Google Scholar
  4. 4.
    Tsoi, K., Papagiannis, I., Migliavacca, M., Luk, W., Pietzuch, P.: Accelerating publish/subscribe matching on reconfigurable supercomputing platforms. In: Proceedings of Many-Core and Reconfigurable Supercomputing ConferenceGoogle Scholar
  5. 5.
    Barazzutti, R., Felber, P.: Streamhub: A massively parallel architecture for high-performance content-based publish/subscribe. In: DEBS vol. 13Google Scholar
  6. 6.
    Wang, X.C.: Pub/sub on stream: a multi-core based message broker with qos support. In: DEBS (2012)Google Scholar
  7. 7.
    Shah, M.A., Kulkarni, D.B.: Design of high performance, scalable content-based publish-subscribe system using MPI-CUDA approach. In: Int. J. Comput. Sci. Eng. (IJCSE) UGC approved (2017). ISSN: 2347–2693 (E)Google Scholar
  8. 8.
    Carzaniga, A., Wolf, A.: Forwarding in a content-based network. In: Proceedings of SIG-COMM, pp. 163–174 (2003)Google Scholar
  9. 9.
    Carzaniga, A., Rosenblum, D., Wolf, A.: Achieving scalability and expressiveness in an internet-scale event notification service. In: Proceedings of the 19th Annual ACM Symposium, pp. 219–227 (2000)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of CSEWalchand College of EngineeringSangliIndia
  2. 2.Department of Information TechnologyWalchand College of EngineeringSangliIndia

Personalised recommendations