Total views : 102

A Comparative Study of Multithreading APIs for Software of ICT Equipment

Affiliations

  • Department of Computer Science and Engineering,Hanyang University ERICA, Ansan, South Korea, Korea, Republic of

Abstract


In the infrastructure of Information and Communication Technology (ICT), the design and architecture of software deployed over equipment plays a vital role in system’s concurrent efficiency. The high performance computing nexus with fine-grain parallel processing environment calls for optimized and effective multithreading strategies for ICT’s software implementations. This paper briefly identifies different state-of-art multithreading APIs used in multi-core coherent processors. The paper investigates various APIs based on main categorization of operating system level and lightweight thread level. Operating system level multithreading relies on operating system kernel architecture as numerous threads or tasks achieve concurrency provided by the underlying hardware, thus considered effective for high core programming. On the other hand, various application level lightweight thread models are been offers with lighter mechanism for high parallelism and massive concurrency. Lightweight models are optimized to combine low-latency thread and task scheduling with optimized functionality for data-movement. This comparative study aims to demonstrate major working models and principal differences among well-established libraries in each category. This paper projects an early investigation for the identification of most efficient thread library for ICT equipment.

Keywords

ICT Software, Parallelism, Multithreading Models.

Full Text:

 |  (PDF views: 89)

References


  • Döbel B, Härtig H, Engel M. Operating system support for redundant multithreading. Proceedings of the tenth ACM International Conference on Embedded Software; 2012Oct. p. 83–92.
  • Grochowski E, Wang H, Shen JP, Wang PH, Collins JD, Held J, Kundu P, Leviathan R, Ngai T-F. Method and system to provide user-level multithreading. U.S. Patent Application 15/088,043; 2016 Mar 31.
  • Kundu P, Das D, Banerjee A. Plug-in instrumentation: A futuristic ICT approach for teaching the runtime behaviour of software. UGC Sponsored Seminar on ICT in Higher Education: Opportunities and Challenges in the 21st Century Proceedings, SPS Education India Pvt. Ltd., Kolkata; 2012 Mar. p. 24–7.
  • Mahmoud SS, Ahmad I. A green model for sustainable software engineering. International Journal of Software Engineering and its Applications. 2013; 7(4):55–74.
  • Yull S, Lawson J. AQA AS GCE applied ICT single award (Paperback); 2005.
  • Kerrison S, Eder K. Modeling and visualizing networked multi-core embedded software energy consumption[Internet]. 2015. Available from: https://arxiv.org/abs/1509.02830.
  • Kerrison SP. Energy modelling of multi-threaded, multi-core software for embedded systems. Ph.D diss., University of Bristol; 2015.
  • Fei Y, Zhu H, Wu X, Fang H. Comparative modeling and verification of Pthreads and Dthreads. 2016 IEEE 17th International Symposium on High Assurance Systems Engineering (HASE);2016 Jan. p. 132–40.
  • Baccelli E, Hahm O, Gunes M, Wahlisch M, Schmidt TC. RIOT OS: Towards an OS for the Internet of Things. 2013 IEEE Conference onComputer Communications Workshops (INFOCOM WKSHPS); 2013 Apr. p. 79–80.
  • Danjean V, Namyst R, Russell RD. Linux kernel activations to support multithreading. 18th IASTED International Conference on Applied Informatics (AI 2000);2000.
  • Barney B. POSIX threads programming. National Laboratory. [Internet]. 2009. Available from:https://computing.llnl.gov/tutorials/Pthreads/.
  • Liu T, Curtsinger C, Berger ED. Dthreads: Efficient deterministic multithreading. Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles; 2011 Oct.p. 327–36.
  • Anderson TE, Bershad BN, Lazowska ED, Levy HM. Scheduler activations: Effective kernel support for the user-level management of parallelism. ACM Transactions on Computer Systems. 1992;10(1):53–79.
  • Wheeler KB, Murphy RC, Thain D. Qthreads: An API for programming with millions of lightweight threads. IEEE International Symposium on Parallel and Distributed Processing. IPDPS 2008; 2008 Apr. p. 1–8.
  • Nakashima J, Taura K. MassiveThreads: A thread library for high productivity languages. Concurrent Objects and Beyond, Springer Berlin Heidelberg; 2014.p. 222–38.
  • Seo S, Amer A, Balaji P, Beckman P, Bordage C, Bosilca G, Brooks A, Castelló A. Argobots: A Lightweight Low-level threading/tasking framework [Internet]. 2015. Available from: https://collab.cels.anl.gov/display/ARGOBOTSS/.
  • Castelló A, Pena, AJ, Seo S, Mayo R, Balaji P, Quintana-Orti ES. A review of lightweight thread approaches for high performance computing. IEEE Cluster 2016; 2016.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.