The Datapath Merging Problem in Reconfigurable Systems: Lower Bounds and Heuristic Evaluation

  • Cid C. de Souza
  • André M. Lima
  • Nahri Moreano
  • Guido Araujo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3059)

Abstract

In this paper we investigate the datapath merging problem (DPM) in reconfigurable systems. DPM is in \(\mathcal{NP}\)-hard and it is described here in terms of a graph optimization problem. We present an Integer Programming (IP) formulation of DPM and introduce some valid inequalities for the convex hull of integer solutions. These inequalities form the basis of a branch-and-cut algorithm that we implemented. This algorithm was used to compute lower bounds for a set of DPM instances, allowing us to assess the performance of the heuristic proposed by Moreano et al. [1] which is among the best ones available for the problem. Our computational experiments confirmed the efficiency of Moreano’s heuristic. Moreover, the branch-and-cut algorithm also was proved to be a valuable tool to solve small-sized DPM instances to optimality.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Moreano, N., Araujo, G., Huang, Z., Malik, S.: Datapath merging and interconnection sharing for reconfigurable architectures. In: Proceedings of the 15th International Symposium on System Synthesis, pp. 38–43 (2002)Google Scholar
  2. 2.
    Wolf, W.: Computers as Components – Principles of Embedded Computing System Design. Morgan Kaufmann Publishers, San Francisco (2001)Google Scholar
  3. 3.
    DeHon, A., Wawrzynek, J.: Reconfigurable computing: What, why, and implications for design automation. In: Proceedings of the Design Automation Conference (DAC), pp. 610–615 (1999)Google Scholar
  4. 4.
    Schaumont, P., Verbauwhede, I., Keutzer, K., Sarrafzadeh, M.: A quick safari through the reconfiguration jungle. In: Proceedings of the Design Automation Conference (DAC), pp. 172–177 (2001)Google Scholar
  5. 5.
    Compton, K., Hauck, S.: Reconfigurable computing: A survey of systems and software. ACM Computing Surveys 34, 171–210 (2002)CrossRefGoogle Scholar
  6. 6.
    Bondalapati, K., Prasanna, V.: Reconfigurable computing systems. Proceedings of the IEEE (2002)Google Scholar
  7. 7.
    Callahan, T., Hauser, J., Wawrzynek, J.: The Garp architecture and C compiler. IEEE Computer, 62–69 (2000)Google Scholar
  8. 8.
    Singh, H., Lee, M., Lu, G., Kurdahi, F., Bagherzadeh, N., Filho, E.: MorphoSys: An integrated reconfigurable system for data-parallel and computation-intensive applications. IEEE Transactions on Computers 49, 465–481 (2000)CrossRefGoogle Scholar
  9. 9.
    Schmit, H., et al.: PipeRench: A virtualized programmable datapath in 0.18 micron technology. In: Proceedings of the IEEE Custom Integrated Circuits Conference (CICC), pp. 63–66 (2002)Google Scholar
  10. 10.
    Moreano, N., Araujo, G., de Souza, C.C.: CDFG merging for reconfigurable architectures. Technical Report IC-03-18, Institute of Computing, University of Campinas SP, Brazil (2003)Google Scholar
  11. 11.
    Nemhauser, G.L., Wolsey, L.: Integer and Combinatorial Optimization. Wiley & Sons, Chichester (1988)MATHGoogle Scholar
  12. 12.
    Grötschel, M., Lovász, L., Schrijver, A.: The ellipsoid method and its consequences in combinatorial optimization. Combinatorica 1, 169–197 (1981)MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
  14. 14.
    Battiti, R., Protasi, M.: Reactive local search for the maximum clique problem. Algorithmica 29, 610–637 (2001)MATHCrossRefMathSciNetGoogle Scholar
  15. 15.

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Cid C. de Souza
    • 1
  • André M. Lima
    • 1
  • Nahri Moreano
    • 2
  • Guido Araujo
    • 1
  1. 1.Institute of ComputingState University of CampinasCampinasBrazil
  2. 2.Department of Computing and StatisticsFederal University of Mato Grosso do SulCampo GrandeBrazil

Personalised recommendations