Early Design Phase Cross-Platform Throughput Prediction for Industrial Stream-Processing Applications

Authors Tjerk Bijlsma, Alexander Lint, Jacques Verriet



PDF
Thumbnail PDF

File

LIPIcs.ECRTS.2018.18.pdf
  • Filesize: 1.73 MB
  • 20 pages

Document Identifiers

Author Details

Tjerk Bijlsma
  • ESI, High Tech Campus 25, 5600 HE, Eindhoven, The Netherlands
Alexander Lint
  • Océ Technologies, P.O. Box 101, 5900 MA, Venlo, The Netherlands
Jacques Verriet
  • ESI, High Tech Campus 25, 5600 HE, Eindhoven, The Netherlands

Cite AsGet BibTex

Tjerk Bijlsma, Alexander Lint, and Jacques Verriet. Early Design Phase Cross-Platform Throughput Prediction for Industrial Stream-Processing Applications. In 30th Euromicro Conference on Real-Time Systems (ECRTS 2018). Leibniz International Proceedings in Informatics (LIPIcs), Volume 106, pp. 18:1-18:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)
https://doi.org/10.4230/LIPIcs.ECRTS.2018.18

Abstract

Industrial embedded platforms are often used to execute stream-processing applications, from which the results are used by actuators. On average, these stream-processing applications should at least meet the required throughput of their actuators, which poses a real-time requirement on the system. To avoid extra costs and delays, it is desired to estimate during the early design phase if a combination of an embedded platform and a stream-processing application can achieve the required throughput. The throughput of a stream-processing application executed on different embedded platforms can be predicted by modeling them using static or measurement based analysis. However, during the early design phase it can be desirable to have a model that allows a large set of embedded platforms to be considered, where embedded platforms with predictive instructions are supported. This paper presents a gray-box approach applicable during the early design phase to perform cross-platform throughput predictions for industrial stream-processing applications and their embedded platforms. A three step regression-based approach is presented, which uses an expression based on Amdahl's law for the discrete scaling of workload over cores and a large database with CPU performance scores to perform cross-platform throughput predictions. Validation, with a limited set of platforms, showed the usability of the approach. The pragmatic approach is based on a prototype industrial digital image processing application for a printer from Océ, which is also used to present the approach.

Subject Classification

ACM Subject Classification
  • General and reference → Estimation
  • General and reference → Performance
  • Computer systems organization → Real-time systems
Keywords
  • throughput prediction
  • stream-processing application
  • early design phase
  • regression model
  • cross-platform

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. Abdulrahman Alenezi, Scott A. Moses, and Theodore B. Trafalis. Real-time prediction of order flowtimes using support vector regression. Elsevier Computers and Operations Research, 35(11):3489-3503, 2008. Google Scholar
  2. Gene M. Amdahl. Validity of the single processor approach to achieving large scale computing capabilities. In Proc. Spring Joint Computer Conference, pages 483-485. ACM, apr 1967. Google Scholar
  3. Simonetta Balsamo, Antinisca Di Marco, Paola Inverardi, and Marta Simeoni. Model-based performance prediction in software development: a survey. IEEE Transactions on Software Engineering, 30(5):295-310, 2004. Google Scholar
  4. Frank Buschmann, Regine Meunier, Hans Rohnert, Peter Sommerlad, and Michael Stal. Pattern-Oriented Software Architecture - Volume 1: A System of Patterns. Wiley Publishing, 1996. Google Scholar
  5. Giorgio C. Buttazzo. Hard Real-Time Computing Systems: Predictable Scheduling Algorithms and Applications. Springer Publishing Company, Incorporated, 3rd edition, 2011. Google Scholar
  6. Abraham Charnes, Edward L. Frome, and Po-Lung Yu. The equivalence of generalized least squares and maximum likelihood estimates in the exponential family. journal of the American Statistical Association, 71(353):169-171, 1976. Google Scholar
  7. Jeffrey Dean and Sanjay Ghemawat. Mapreduce: Simplified data processing on large clusters. Commununications of the ACM, 51(1):107-113, 2008. Google Scholar
  8. Fernando Diaz-del Rio, Javier Salmeron-Garcia, and Jose Luis Sevillano. Extending amdahl’s law for the cloud computing era. IEEE Computer, 49(2):14-22, feb 2016. Google Scholar
  9. Futuremark Corporationsuperscriptcopyright 2016. Best CPUs - July 2017, 2017. https://www.futuremark.com/hardware/cpu/. Google Scholar
  10. Chetan Gupta, Abhay Mehta, and Umeshwar Dayal. PQR: Predicting query execution times for autonomous workload management. In Proc. Int. Conf. on Autonomic Computing (ICAC), ICAC '08, pages 13-22, Washington, DC, USA, 2008. IEEE Computer Society. Google Scholar
  11. Wolfgang Haid, Matthias Keller, Kai Huang, Iuliana Bacivarov, and Lothar Thiele. Generation and calibration of compositional performance analysis models for multi-processor systems. In Proc. Int. symposium on Systems, Architectures, Modeling, and Simulation (SAMOS), pages 92-99, jul 2009. Google Scholar
  12. Martijn Hendriks, Twan Basten, Jacques Verriet, Marco Brassé, and Lou Somers. A blueprint for system-level performance modeling of software-intensive embedded systems. Springer Software Tools for Technology Transfer, 18(1):21-40, feb 2016. Google Scholar
  13. Martijn Hendriks, Jacques Verriet, Twan Basten, Marco Brassé, Reinier Dankers, René Laan, Alexander Lint, Hristina Moneva, Lou Somers, and Marc Willekens. Performance engineering for industrial embedded data-processing systems. In Proc. Int. Conf. Product-Focused Software Process Improvement (PROFES), pages 399-414, Cham, 2015. Springer International Publishing. Google Scholar
  14. Mark D. Hill and Michael R. Marty. Amdahl’s law in the multicore era. IEEE Computer, 41(7), 2008. Google Scholar
  15. Ling Huang, Jinzhu Jia, Bin Yu, Byung-Gon Chun, Petros Maniatis, and Mayur Naik. Predicting execution time of computer programs using sparse polynomial regression. In Proc. Int. Conf. on Neural Information Processing Systems, NIPS'10, pages 883-891, USA, 2010. Curran Associates Inc. Google Scholar
  16. Intel Corporationsuperscriptcopyright. Product specifications, 2016. https://ark.intel.com/. Google Scholar
  17. Bart Kienhuis, Ed F. Deprettere, Pieter van der Wolf, and Kees Vissers. A methodology to design programmable embedded systems. In Proc. Embedded Processor Design Challenges, pages 18-37. Springer, 2002. Google Scholar
  18. Sumit Mohanty, Viktor K. Prasanna, Sandeep K. Neema, and James R. Davis. Rapid design space exploration of heterogeneous embedded systems using symbolic search and multi-granular simulation. ACM SIGPLAN Notices, 37(7):18-27, 2002. Google Scholar
  19. Douglas C. Montgomery, Elizabeth A. Peck, and Geoffrey G. Vining. Introduction to Linear Regression Analysis. Wiley &Sons, New York, third edition, 2006. Google Scholar
  20. Ayoub Nouri, Marius Bozga, Anca Molnos, Axel Legay, and Saddek Bensalem. Astrolabe: A rigorous approach for system-level performance modeling and analysis. ACM Transactions on Embedded Computing Systems (TECS), 15(2):31:1-31:26, 2016. Google Scholar
  21. PassMarksuperscriptcopyright Software. CPU benchmarks, may 2017. https://www.cpubenchmark.net/. Google Scholar
  22. Skipper Seabold and Josef Perktold. Statsmodels: Econometric and statistical modeling with python. In Proc. 9th Python in Science Conference, 2010. Google Scholar
  23. Xian He Sun and Yong Chen. Reevaluating amdahl’s law in the multicore era. Academic Press Parallel Distributed Computing, 70(2):183-188, 2010. Google Scholar
  24. David Trilla, Javier Jalle, Mikel Fernandez, Jaume Abella, and Francisco J. Cazorla. Improving early design stage timing modeling in multicore based real-time systems. In Proc. IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), pages 1-12, 2016. Google Scholar
  25. Maarten H. Wiggers. Aperiodic Multiprocessor Scheduling for Real-Time Stream Processing Applications. PhD thesis, University of Twente, 2009. Google Scholar
  26. Reinhard Wilhelm et al. The worst-case execution-time problem - overview of methods and survey of tools. ACM Transactions on Embedded Computing Systems (TECS), 7(3):36:1-36:53, 2008. Google Scholar
  27. Murray Woodside, Greg Franks, and Dorina C. Petriu. The future of software performance engineering. In Proc. Future of Software Engineering (FOSE), pages 171-187. IEEE, 2007. Google Scholar
  28. Leonid Yavits, Amir Morad, and Ran Ginosar. The effect of communication and synchronization on Amdahl’s law in multicore systems. Elsevier Parallel Computing, 40(1):1-16, jan 2014. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail