Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

Fast and low overhead architectural transaction level modelling for large-scale network-on-chip simulation

Fast and low overhead architectural transaction level modelling for large-scale network-on-chip simulation

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computers & Digital Techniques — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Early system modelling is an essential tool to accelerate software development, architectural analysis and hardware verification in complex many-core system-on-chips (SoCs). Transaction level modelling (TLM) offers a higher level of abstraction than register transfer level (RTL) and can be used for early system modelling. Maintaining simulation speed with the right accuracy is a major challenge and this paper proposes SystemC-based architectural modelling techniques that extend TLM to deliver faster simulation models for many-core system. The proposed approach considers a micro-scheduler for large modules (in the sense of SystemC modules) to locally manage all events in the module. Exploiting this micro-scheduler along with function object and coroutine concepts, the authors propose a lightweight thread process that significantly reduces the context switching overhead among the different processes. Additionally the micro-scheduler allows some processes to be run ahead of simulation time. The proposed techniques are applied to the model of a very large networks-on-chip (NoC) formed by thousands of cores stressing the simulation capabilities of the host computer and operating system. The experimental results demonstrate that the model can run successfully and exhibits up to 93% improvement in simulation speed compared to traditional SystemC-based modelling.

References

    1. 1)
      • Lis, M., Shim, K.S., Cho, M.H., Ren, P., Khan, O., Devadas, S.: `DARSIM: a parallel cycle-level NoC simulator', Sixth Workshop on Modeling, Benchmarking, and Simulation (MoBS), June 2010.
    2. 2)
      • Mello, A., Maia, I., Greiner, A., Pecheux, F.: `Parallel simulation of systemC TLM 2.0 compliant MPSoC on SMP workstations', Design, Automation and Test in Europe Conf. and Exhibition (DATE), 2010, 8–12 March 2010, p. 606–609.
    3. 3)
      • Nanjundappa, M., Patel, H.D., Jose, B.A., Shukla, S.K.: `SCGPsim a fast SystemC simulator on GPUs', Fifteenth Asia and South Pacific Design Automation Conf. (ASP-DAC), 2010, p. 149–154.
    4. 4)
    5. 5)
      • Vandevoorde D., Josuttis N.M.: C++ templates: the complete guide, ISBN-13: 978-0-201-73484-3, Published November 12, 2002 by Addison-Wesley Professional.
    6. 6)
      • Borkae, S.: `Thousand core chips-a technology perspective', Proc. Design Automation Conf., 2007, p. 746–749.
    7. 7)
      • IEEE Computer Society: IEEE Standard SystemC® Language Reference Manual, IEEE Std 1666™, 2005.
    8. 8)
      • R. Fujimoto . (2000) Parallel and distributed simulation systems.
    9. 9)
      • OSCI: TLM-2.0 language reference manual [online], available at http://www.systemc.org/download.
    10. 10)
    11. 11)
    12. 12)
      • M. Hosseinabady , J.L. Nunez-Yanez . SystemC architectural transaction level modelling for large NoCs, Forum on Specification and Design Languages (FDL’10).
    13. 13)
      • Cai, L., Gajski, D.: `Transaction level modelling: an overview', Proc. IEEE/ACM/IFIP Int. Conf. on Hardware/Software Codesign and System Synthesis, 2003, p. 19–24.
    14. 14)
      • http://noxim.sourceforge.net/.
    15. 15)
      • Nunez-Yanez, J., Beldachi, A., Nabina, A., Hosseinabady, M.: `Exploring dynamically reconfigurable multicore designs with NORC designer', Int. Conf. on High Performance Computing and Simulation (HPCS), 2012, p. 254–260.
    16. 16)
      • T. Duff . Tom Duff on Duff's Device.
    17. 17)
      • Hosseinabady, M., Nunez-Yanez, J.L.: `Effective modelling of large NoCs using SystemC', Proc. IEEE Int. Symp. on Circuits and Systems (ISCAS'10), 2010, p. 161–164.
    18. 18)
      • http://code.google.com/a/eclipselabs.org/p/network-on-chip-designer/.
    19. 19)
      • Agarwal, N., Krishna, T., Peh, L., Jha, N.K.: `GARNET: a detailed on-chip network model inside a full-system simulator', Proc. Int. Symp. on Performance Analysis of Systems and Software, 2009, p. 33–42.
    20. 20)
      • http://webee.technion.ac.il/matrics/software.html.
    21. 21)
    22. 22)
      • http://www.omnetpp.org/.
    23. 23)
    24. 24)
      • http://www.ict.kth.se/nostrum/.
    25. 25)
      • Dunkels, A., Schmidt, O., Voigt, T., Ali, M.: `Protothreads: simplifying event-driven programming of memory-constrained embedded systems', Proc. Int. Conf. on Embedded Networked Sensor Systems (SENSYS), 2006, p. 29–42.
    26. 26)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cdt.2012.0001
Loading

Related content

content/journals/10.1049/iet-cdt.2012.0001
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address