SAT-based analysis of feature models is easy

  • Authors:

  • Marcilio Mendonca;Andrzej Wąsowski;Krzysztof Czarnecki

  • Affiliations:

  • University of Waterloo, Canada;IT University of Copenhagen, Denmark;University of Waterloo, Canada

  • Venue:
  • Proceedings of the 13th International Software Product Line Conference
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Feature models are a popular variability modeling notation used in product line engineering. Automated analyses of feature models, such as consistency checking and interactive or offline product selection, often rely on translating models to propositional logic and using satisfiability (SAT) solvers. Efficiency of individual satisfiability-based analyses has been reported previously. We generalize and quantify these studies with a series of independent experiments. We show that previously reported efficiency is not incidental. Unlike with the general SAT instances, which fall into easy and hard classes, the instances induced by feature modeling are easy throughout the spectrum of realistic models. In particular, the phenomenon of phase transition is not observed for realistic feature models. Our main practical conclusion is a general encouragement for researchers to continued development of SAT-based methods to further exploit this efficiency in future.