Advertisement

A Novel Data-Path for Accelerating DSP Kernels

  • Michalis D. Galanis
  • G. Theodoridis
  • Spyros Tragoudas
  • Dimitrios Soudris
  • Costas E. Goutis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3133)

Abstract

A high-performance data-path to implement DSP kernels is proposed in this paper. The data-path is based on a flexible, universal, and regular component to optimally exploiting both inter- and intra-component chaining of operations. The introduced component is a combinational circuit with steering logic that allows in easily realizing any desirable complex hardware unit, called template; so that the data-path’s performance benefits by the intra-component chaining of operations. Due to the component’s flexible and universal structure, the Data Flow Graph is realized by a small number of such components. The small numbers of the used components coupled with a configurable interconnection network allow adopting direct inter-component connections and optimally exploiting any inter-component chaining possibility over to the existing template- based methods. Also, due to universal and flexible structure of the component, scheduling and binding are accomplished by simple, yet efficient, algorithms achieving minimum latency at the expense of an area penalty and a small overhead at the control circuit and clock period. Results on DSP benchmarks show an average latency reduction of 20 path.

Keywords

Clock Cycle Digital Signal Processing Register Bank Clock Period Combinational Circuit 
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.
    Corazao, M.R., et al.: Performance Optimization Using Template Mapping for Datapath- Intensive High-Level Synthesis. IEEE Trans. on CAD 15(2), 877–888 (1996)Google Scholar
  2. 2.
    Kastner, R., et al.: Instruction Generation for Hybrid Reconfigurable Systems. ACM TODAES 7(4), 605–627 (2002)CrossRefGoogle Scholar
  3. 3.
    Geurts, W., Catthoor, F., Vernalde, S., DeMan, H.: Accelerator Data-Path Synthesis for High-Throughput Signal Processing Applications. Kluwer, Boston (1996)Google Scholar
  4. 4.
    Rao, D., Kurdahi, F.: On Clustering for Maximal Regularity Extraction. IEEE Trans. on CAD 12(8), 1198–1208 (1993)Google Scholar
  5. 5.
    De Micheli, G.: Synthesis and Optimization of Digital Circuits. International edn.McGraw-Hill, New York (1994)Google Scholar
  6. 6.
    Gajski, D., et al.: High-Level Synthesis: Introduction to Chip and System design. Kluwer Academic Publishers, Dordrecht (1997)Google Scholar
  7. 7.
    Jain, M., et al.: ASIP Design Methodologies: Survey and Issues. In: Proc of Int. Conf. on VLSI Design, pp. 76–81 (2001)Google Scholar
  8. 8.
    Cadambi, S., Goldstein, S.C.: CPR: a configuration profiling tool. In:Symp. on Field- Programmable Custom Computing Machines, FCCM (1999)Google Scholar
  9. 9.
    Cong, J., et al.: Application-Specific Instruction Generation for Configurable Processor Architectures.In: Proc. of Int. Symp. on FPGA 2004 (2004)Google Scholar
  10. 10.
    Leiserson, C.E.: Fat-Trees: Universal Networks for Hardware Efficient Supercomputing. IEEE Trans. on Computers 43(10), 892–901 (1985)Google Scholar
  11. 11.
    Lai, Y.: Hierarchical Interconnection Structures for Field Programmable Gate Arrays. IEEE Trans. on VLSI 5(2), 186–196 (1997)CrossRefGoogle Scholar
  12. 12.
    Cadence BuildGates, http://www.cadence.com
  13. 13.
    Lee, C., et al.: MediaBench: a tool for evaluating and synthesizing multimedia and communications systems., in Int. Symposium on Microarchitecture (1997)Google Scholar
  14. 14.
  15. 15.
    Hall, M.W., et al.: Maximizing multiprocessor performance with the SUIF compiler.Computer  29, 84-89 (1996), http://suif.standford.edu

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Michalis D. Galanis
    • 1
  • G. Theodoridis
    • 2
  • Spyros Tragoudas
    • 3
  • Dimitrios Soudris
    • 4
  • Costas E. Goutis
    • 1
  1. 1.University of PatrasPatrasGreece
  2. 2.Aristotle UniversityThessalonicaGreece
  3. 3.Southern Illinois UniversityCarbondaleUSA
  4. 4.Democriteus UniversityXanthiGreece

Personalised recommendations