Advertisement

Efficient Realization of Data Dependencies in Algorithm Partitioning Under Resource Constraints

  • Sebastian Siegel
  • Renate Merker
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4128)

Abstract

Mapping algorithms to parallel architectures efficiently is very important for a cost-effective design of many modern technical products. In this paper, we present a solution to the problem of efficiently realizing uniform data dependencies on processor arrays. In contrary to existing approaches, we formulate an optimization problem to consider the cost of both: channels and registers. Further, a solution to the optimization problem assigns which channels shall be implemented and it specifies the control for the realization of the uniform data dependencies. We illustrate our method on the edge detection algorithm.

Keywords

Integer Linear Programming Data Dependency Communication Problem Iteration Space Data Path 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Motomura, M.: A Dynamically Reconfigurable Processor Architecture. In: Microprocessor Forum (2002)Google Scholar
  2. 2.
    Duller, A., Towner, D., Panesar, G., Gray, A., Robbins, W.: picoArray Technology: The Tool’s Story. In: Design, Automation and Test in Europe (DATE 2005), vol. 3, pp. 106–111 (2005)Google Scholar
  3. 3.
    Siegel, S., Merker, R.: Optimized Data-Reuse in Processor Arrays. In: Proc. IEEE Int. Conf. on Application-Specific Systems, Architectures, and Processors (ASAP 2004), pp. 315–325 (2004)Google Scholar
  4. 4.
    Karp, R.M., Miller, R.E., Winograd, S.: The organisation of computations for uniform recurrence equations. JACM 14(3), 563–590 (1967)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Siegel, S., Merker, R.: Algorithm Partitioning including Optimized Data-Reuse for Processor Arrays. In: Proc. IEEE International Conference on Parallel Computing in Electrical Engineering (PARELEC 2004) pp. 85–90 (2004)Google Scholar
  6. 6.
    Derrien, S., Rajopadhye, S., Sur-Kolay, S.: Combining Instruction and Loop Level Parallelism for Array Synthesis on FPGAs. In: International Symposium on System Synthesis (2001)Google Scholar
  7. 7.
    Feautrier, P.: Fine-grain Scheduling under Resource Constraints. In: Pingali, K.K., Gelernter, D., Padua, D.A., Banerjee, U., Nicolau, A. (eds.) LCPC 1994. LNCS, vol. 892, pp. 1–15. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  8. 8.
    Thiele, L.: Resource constraint scheduling of uniform algorithms. Journal of VLSI Signal Processing 10, 295–310 (1995)CrossRefGoogle Scholar
  9. 9.
    Teich, J., Thiele, L.: A New Approach to Solving Resource-Constrained Scheduling Problems based on a Flow-Model. Technical Report 17, TIK, Swiss Federal Institute of Technology (ETH) Zürich (1996)Google Scholar
  10. 10.
    Dion, M., Risset, T., Robert, Y.: Resource-constrained scheduling of partitioned algorithms on processor arrays. Integration, the VLSI Journal 20, 139–159 (1996)MATHCrossRefGoogle Scholar
  11. 11.
    Fimmel, D., Merker, R.: Localization of Data Transfer in Processor Arrays. In: Amestoy, P.R., Berger, P., Daydé, M., Duff, I.S., Frayssé, V., Giraud, L., Ruiz, D. (eds.) Euro-Par 1999. LNCS, vol. 1685, pp. 401–408. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  12. 12.
    Eisenbeis, C., Sawaya, A.: Optimal loop parallelization under register constraints. Technical Report 2781, INRIA (1996)Google Scholar
  13. 13.
    Müller, J., Fimmel, D., Merker, R.: Optimal Loop Scheduling with Register Constraints Using Flow Graphs. In: Proc. of the 7th Int. Symposium on Parallel Architectures, Algorithms, and Networks (I-SPAN), Hong Kong, China (2004)Google Scholar
  14. 14.
    Fimmel, D.: Optimaler Entwurf paralleler Rechenfelder unter Verwendung ganzzahliger linearer Optimierung. PhD thesis, Dresden University of Technology, Institute of Circuits and Systems (2002)Google Scholar
  15. 15.
    Siegel, S., Merker, R.: Minimum Cost for Channels and Registers in Processor Arrays by Avoiding Redundancy. In: IEEE 17th Int. Conf. on Application-Specific Systems, Architectures, and Processors (ASAP 2006) (2006)Google Scholar
  16. 16.
    Siegel, S., Merker, R.: Optimal Realization of Uniform Data Dependencies in Algorithm Partitioning Under Resource Constraints. Technical report, Dresden University of Technology, Institute of Circuits and Systems (2006), http://www.iee.et.tu-dresden.de/~siegel/paper/SM06a.pdf

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sebastian Siegel
    • 1
  • Renate Merker
    • 1
  1. 1.Institute of Circuits and SystemsDresden University of TechnologyDresdenGermany

Personalised recommendations