Abstract
The increasing pervasiveness of multicore processors in today’s computing systems will increase the demand for techniques to adapt application level parallelism. In this paper we demonstrate the impact of oversubscription in the context of a desktop scenario and show that using too many threads in one application can lead to significant performance loss for other applications within the system environment (in our example more than 30%). We examine how common parallelization tools are trying to exploit parallelism while not causing oversubscription and find that common tools do not offer a mechanism which sufficiently takes into account the computational load of the system. Oversubscription is not easy to detect from an application perspective due to the fair scheduling of common operating systems. Nonetheless, we do present an approach for detecting oversubscription by exploiting a scheduling artifact in the average execution time of a parallel code section.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Intel: Intel threading building blocks. Intel Tutorial (2007)
Board, O.A.R.: Openmp application program interface (2008)
Fuentes, E.: Throttling concurrency in the clr 4.0 threadpool. MSDN Magazine (2010)
Russinovich, M.E., Solomon, D., Ionescu, A.: Windows Internals: Book and Online Course Bundle. C.B.Learning, United Kingdom (2010)
Tabatabaee, V., Tiwari, A., Hollingsworth, J.K.: Parallel parameter tuning for applications with performance variability. In: Proceedings of the 2005 ACM/IEEE Conference on Supercomputing, SC 2005, p. 57. IEEE Computer Society, Washington, DC (2005)
Qasem, A., Kennedy, K., Mellor-Crummey, J.: Automatic tuning of whole applications using direct search and a performance-based transformation system, vol. 36, pp. 183–196. Kluwer Academic Publishers, Hingham (2006)
Ganapathi, A., Datta, K., Fox, A., Patterson, D.: A case for machine learning to optimize multicore performance. In: Proceedings of the First USENIX Conference on Hot Topics in Parallelism, HotPar 2009, p. 1. USENIX Association, Berkeley, CA (2009)
Reimer, N.: Dynamically Adapting the Degree of Parallelism With Reflexive Programs. In: Saad, Y., Yang, T., Ferreira, A., Rolim, J.D.P. (eds.) IRREGULAR 1996. LNCS, vol. 1117, pp. 313–318. Springer, Heidelberg (1996)
Hall, M.W., Martonosi, M.: Adaptive parallelism in compiler-parallelized code. In: Proc. of the 2nd SUIF Compiler Workshop (1997)
Karcher, T., Schaefer, C., Pankratius, V.: Auto-tuning support for manycore applications: perspectives for operating systems and compilers. SIGOPS Oper. Syst. Rev. 43(2), 96–97 (2009)
Corbet, J.: TTY-based group scheduling (November 2010), http://lwn.net/Articles/415740/ (retrieved on: January 13, 2011)
Iancu, C., Hofmeyr, S., Blagojevic, F., Zheng, Y.: Oversubscription on multicore processors. In: 2010 IEEE International Symposium on Parallel Distributed Processing (IPDPS), pp. 1–11 (2010)
Mattson, T., Sanders, B., Massingill, B.: Patterns for parallel programming, 1st edn. Addison-Wesley Professional (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Christmann, C., Hebisch, E., Weisbecker, A. (2012). Oversubscription of Computational Resources on Multicore Desktop Systems. In: Pankratius, V., Philippsen, M. (eds) Multicore Software Engineering, Performance, and Tools. MSEPT 2012. Lecture Notes in Computer Science, vol 7303. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-31202-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-31202-1_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-31201-4
Online ISBN: 978-3-642-31202-1
eBook Packages: Computer ScienceComputer Science (R0)