From Source Code to Runtime Behaviour: Software Metrics Help to Select the Computer Architecture.

  • Frank Eichinger
  • David Kramer
  • Klemens Böhm
  • Wolfgang Karl
Conference paper

DOI: 10.1007/978-1-84882-983-1_29

Cite this paper as:
Eichinger F., Kramer D., Böhm K., Karl W. (2010) From Source Code to Runtime Behaviour: Software Metrics Help to Select the Computer Architecture.. In: Bramer M., Ellis R., Petridis M. (eds) Research and Development in Intelligent Systems XXVI. Springer, London

Abstract

The decision which hardware platform to use for a certain application is an important problem in computer architecture. This paper reports on a study where a data-mining approach is used for this decision. It relies purely on source-code characteristics, to avoid potentially expensive program executions. One challenge in this context is that one cannot infer how often functions that are part of the application are typically executed. The main insight of this study is twofold: (a) Source-code characteristics are sufficient nevertheless. (b) Linking individual functions with the runtime behaviour of the program as a whole yields good predictions. In other words, while individual data objects from the training set may be quite inaccurate, the resulting model is not.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag London 2010

Authors and Affiliations

  • Frank Eichinger
    • 1
  • David Kramer
    • 2
  • Klemens Böhm
    • 1
  • Wolfgang Karl
    • 2
  1. 1.Institute for Program Structures and Data Organisation (IPD)Universität Karlsruhe (TH)KarlsruheGermany
  2. 2.Institute for Computer Science and Engineering (ITEC)Universität Karlsruhe (TH)KarlsruheGermany

Personalised recommendations