KIT | KIT-Bibliothek | Impressum | Datenschutz

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

Eichinger, Frank; Kramer, David; Böhm, Klemens; Karl, Wolfgang

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.


Volltext §
DOI: 10.5445/IR/1000012935
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Programmstrukturen und Datenorganisation (IPD)
Institut für Technische Informatik (ITEC)
Publikationstyp Buchaufsatz
Publikationsjahr 2010
Sprache Englisch
Identifikator ISBN: 978-1-84882-982-4
urn:nbn:de:swb:90-129351
KITopen-ID: 1000012935
Erschienen in Research and Development in Intelligent Systems XXVI. Incorporating Applications and Innovations in Intelligent Systems XVII. Ed.: M. Bramer
Verlag Springer
Seiten 363-376
Bemerkung zur Veröffentlichung Proceedings of the 29th SGAI International Conference on Artificial Intelligence (AI), Cambridge, UK, December 2009
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page