Skip to main content
SpringerLink
Log in

A New Approach to Detecting Execution Phases Using Performance Monitoring Counters

  • Conference paper
  • First Online:
Architecture of Computing Systems - ARCS 2017 (ARCS 2017)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 10172))

Included in the following conference series:

Abstract

In this paper, a new hierarchical view of the workload phase classification problem is introduced. Execution phases are the continuous pieces of execution that show consistent behaviour in terms of performance and power. To the best of our knowledge, this is the first work which uses a hierarchical approach to collect and cluster the performance monitoring counters in order to detect macroscopic phases in an application. Our results show the ability of our model to differentiate between execution phases according to the processor power behaviour. Furthermore, we investigate the power consistency inside each phase. The results show the effectiveness of our proposed methodology in classifying phases with similar power behaviour. This information can be used by the system to control and maintain power bursts, increasing the data centre’s power efficiency by reducing the maximum-to-average power ratio.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Srinivasan, S., Kumar, R., Kundu, S.: Program phase duration prediction and its application to fine-grain power management. In: 2013 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), pp. 127–132, August 2013

    Google Scholar 

  2. Benomar, O., Sahraoui, H., Poulin, P.: Detecting program execution phases using heuristic search. In: Goues, C., Yoo, S. (eds.) SSBSE 2014. LNCS, vol. 8636, pp. 16–30. Springer, Cham (2014). doi:10.1007/978-3-319-09940-8_2

    Google Scholar 

  3. Fan, X., Weber, W.-D., Barroso, L.A.: Power provisioning for a warehouse-sized computer. In: Proceedings of the 34th Annual International Symposium on Computer Architecture. ISCA 2007, pp. 13–23. ACM (2007)

    Google Scholar 

  4. Henning, J.L.: SPEC CPU2006 benchmark descriptions. ACM SIGARCH Comput. Archit. News 34(4), 1–17 (2006)

    Article  Google Scholar 

  5. Reiss, S.P.: Dynamic detection and visualization of software phases. ACM SIGSOFT Softw. Eng. Notes 30(4), 1–6 (2005)

    Article  Google Scholar 

  6. Ishio, T., Watanabe, Y., Inoue, K.: AMIDA: A sequence diagram extraction toolkit supporting automatic phase detection. In: Companion of the 30th International Conference on Software Engineering, pp. 969–970. ACM (2008)

    Google Scholar 

  7. Isci, C., Martonosi, M.: Phase characterization for power: evaluating control-flow-based and event-counter-based techniques. In: HPCA 2006, pp. 121–132 (2006)

    Google Scholar 

  8. Zhang, Z., Chang, J.M.: A cool scheduler for multi-core systems exploiting program phases. IEEE Trans. Comput. 63(5), 1061–1073 (2014)

    Article  MathSciNet  Google Scholar 

  9. Cochran, R., Reda, S.: Thermal prediction and adaptive control through workload phase detection. ACM Trans. Des. Autom. Electron. Syst. (TODAES) 18(1), 7 (2013)

    Google Scholar 

  10. Mucci, P.J., Browne, S., Deane, C., Ho, G.: PAPI: A portable interface to hardware performance counters. In: Proceedings of the Department of Defense HPCMP Users Group Conference, pp. 7–10 (1999)

    Google Scholar 

  11. Sun, Y., Wanner, L., Srivastava, M.: Low-cost estimation of sub-system power. In: International Green Computing Conference (IGCC), pp. 1–10. IEEE (2012)

    Google Scholar 

  12. Kim, Y., Park, S., Cho, Y., Chang, N.: System-level online power estimation using an on-chip bus performance monitoring unit. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 30(11), 1585–1598 (2011)

    Article  Google Scholar 

  13. Bartalos, P., Blake, M.B.: Green web services: modeling and estimating power consumption of web services. In: 2012 IEEE 19th International Conference on Web Services (ICWS), pp. 178–185. IEEE (2012)

    Google Scholar 

  14. Khoshbakht, S., Dimopoulos, N.: SAPPP: the software-aware power and performance profiler (under Review)

    Google Scholar 

  15. Hardy, A.: An examination of procedures for determining the number of clusters in a data set. In: Diday, E., Lechevallier, Y., Schader, M., Bertrand, P., Burtschy, B. (eds.) New Approaches in Classification and Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization, pp. 178–185. Springer, Heidelberg (1994). doi:10.1007/978-3-642-51175-2_20

    Chapter  Google Scholar 

  16. Bircher, W.L., John, L.K.: Complete system power estimation using processor performance events. IEEE Trans. Comput. 61(4), 563–577 (2012)

    Article  MathSciNet  Google Scholar 

  17. Rodrigues, R., Annamalai, A., Koren, I., Kundu, S.: Scalable thread scheduling in asymmetric multicores for power efficiency. In: 2012 IEEE 24th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), pp. 59–66. IEEE (2012)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, University of Victoria, Victoria, British Columbia, Canada

    Saman Khoshbakht & Nikitas Dimopoulos

Authors
  1. Saman Khoshbakht
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nikitas Dimopoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Saman Khoshbakht .

Editor information

Editors and Affiliations

  1. Vienna University of Technology, Vienna, Austria

    Jens Knoop

  2. Karlsruhe Institute of Technology, Karlsruhe, Germany

    Wolfgang Karl

  3. Lawrence Livermore National Laboratory, Livermore, USA

    Martin Schulz

  4. Kyushu University, Fukuoka, Japan

    Koji Inoue

  5. Otto-von-Guericke Universität Magdeburg, Magdeburg, Germany

    Thilo Pionteck

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Khoshbakht, S., Dimopoulos, N. (2017). A New Approach to Detecting Execution Phases Using Performance Monitoring Counters. In: Knoop, J., Karl, W., Schulz, M., Inoue, K., Pionteck, T. (eds) Architecture of Computing Systems - ARCS 2017. ARCS 2017. Lecture Notes in Computer Science(), vol 10172. Springer, Cham. https://doi.org/10.1007/978-3-319-54999-6_7

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-54999-6_7

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-54998-9

  • Online ISBN: 978-3-319-54999-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation