VASS—A VLSI array system synthesizer

  • Jinn-Wang Yeh
  • Wen-Jiunn Cheng
  • Chein-Wei Jen
Article

Abstract

This paper presents a computer-aided design environment called VASS, which assists the VLSI array design. It applies a systematic methodology to synthesize a competitive array system from a behavioral description. Special features include the multiple projection and the two level pipeline techniques. Several crucial issues are considered and some practical solutions are incorporated into VASS. For example, an effective approach is used to transport all the interior I/O to the boundaries of the array. Besides, VASS can generate a kind of control signals, called tags, which propagate with data through the whole array to specify the appropriate functions of each processing element at the appropriate time step. Also, based on the inherent characteristics of the systolic algorithms, a high level synthesis method is proposed to facilitate the datapath generation of processing elements in the resultant array. The automatic specification of control signals and datapath generation of the processing elements render VASS a complete VLSI array system synthesizer. With VASS, one can quickly inspect various array implementations for an algorthm and iteratively improve them to meet the demands of an application-specific VLSI array system.

Keywords

Functional Unit Processing Element Dependence Graph Systolic Array Array Processor 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    H.T. Kung and C.E. Leiserson, “Systolic Arrays (for VLSI),”Sparse Matrix Proceedings, Philadelphia: Society of Industrial and Applied Mathematics, pp. 256–282, 1978.Google Scholar
  2. 2.
    H.T. Kung, “Why Systolic Architectures?”IEEE Computer, Vol. 15, No. 1, pp. 37–45, 1982.CrossRefMATHGoogle Scholar
  3. 3.
    D.I. Moldovan, “On the Design of Algorithms for VLSI Systolic Arrays,”Proceedings of the IEEE, Vol. 71, No. 1, pp. 113–120, 1983.CrossRefGoogle Scholar
  4. 4.
    S.-Y. Kung, “On Supercomputing with Systolic/Wavefront Array Processors,”Proceedings of the IEEE, Vol. 72, No. 7, pp. 867–884, 1984.CrossRefGoogle Scholar
  5. 5.
    H.T. Kung and W.T. Lin, “An Algebra for Systolic Computation,” inElliptic Problem Solvers II, G. Birkhoff and A. Schoenstadt (Eds.), Orlando, Florida: Academic Press, Inc., pp. 141–160, 1984.Google Scholar
  6. 6.
    P.R. Cappelo and K. Steiglitz, “Unifying VLSI Array Design with Linear Transformations of Space-Time,” inAdvances in Computing Research, F.P. Preparata (Ed.), London, England: JAI Press Inc., pp. 23–65, 1984.Google Scholar
  7. 7.
    P. Quiton, “Automatic Synthesis of Systolic Arrays from Uniform Recurrent Equations,”Proc. 11th Intl. Annual Symp. Computer Architecture, pp. 208–214, 1984.Google Scholar
  8. 8.
    S.K. Rao and T. Kailath, “Regular Iterative Algorithms and their Implementation on Processor Arrays,”Proceedings of the IEEE, Vol. 76, No. 3, pp. 259–269, 1988.CrossRefGoogle Scholar
  9. 9.
    W. Luk, G. Jones, and M. Sheeran, “Computer-Based Tools for Regular Array Design,” inSystolic Array Processors. Contributions by Speakers at the International Conference on Systolic Arrays, J. McCanny, J. McWhirter, and E. Swartzlander Jr. (Eds.), UK: Prentice Hall Intl. Ltd., 1989, pp. 589–598.Google Scholar
  10. 10.
    N. Ling and M.A. Bayoumi, “Formal Specification and Verification Strategies for Systolic Arrays,”International Journal of Computer Aided VLSI Design, Vol. 3, No. 1, pp. 91–112, 1991.Google Scholar
  11. 11.
    P. Frison, P. Gachet, and P. Quinton, “Designing Systolic Arrays with DIASTOL,” inVLSI Signal Processing II, S.-Y. Kung, R.E. Owen, and J.G. Nash (Eds.), New York: IEEE Press, 1986, pp. 93–105.Google Scholar
  12. 12.
    D.I. Moldovan, “ADVIS: A Software Package for the Design of Systolic Arrays,”IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Vol. CAD-6, No. 1, pp. 33–40, 1987.MathSciNetCrossRefGoogle Scholar
  13. 13.
    S.Y. Kung and S.N. Jean, “A VLSI Array Compiler System (VACS) for Array Design,” inVLSI Signal Processing III, R.W. Brodersen and H.S. Moscovitz (Eds.), New York: IEEE Press, pp. 495–508, 1988.Google Scholar
  14. 14.
    P.-P. Hou, R.M. Owens, and M.J. Irwin, “DECOMPOSER: A Synthesizer for Systolic Systems,”Proc. 25th Design Automation Conference, Anaheim, CA, USA, 1988, pp. 650–653.Google Scholar
  15. 15.
    E.T.L. Omtzigt, “SYSTARS: A CAD Tool for the Synthesis and Analysis of VLSI Systolic/Wavefront Arrays,”Proc. Int. Conf. on Systolic Arrays, San Diego, CA, USA, 1988, pp. 383–391.Google Scholar
  16. 16.
    M.T. O'Keefe and J.A.B. Fortes, “Bit Level Processor Arrays: Current Architectures and a Design and Programming Tool,”Proc. IEEE International Symposium on Circuits and Systems, Espoo, Finland, 1988, pp. 2751–2755Google Scholar
  17. 17.
    B.R. Engstrom and P.R. Cappello, “The SDEF Programming System,”Journal of Parallel and Distributed Computing, Vol. 7, No. 2, pp. 201–231, 1989.CrossRefGoogle Scholar
  18. 18.
    A.A.J. de Lange, A.J. van der Hoeven, E.F. Deprettere, and P.M. Dewilde, “HiFi: An Object Oriented System for the Structural Synthesis of Signal Processing Algorithms and the VLSI Compilation of Signal Flow Graphs,” inFormal VLSI Specification and Synthesis, VLSI Design Methods-I, L.J.M. Claesen (Ed.), North-Holland: IFIP, 1990, pp. 321–340.Google Scholar
  19. 19.
    H. Leverge, C. Mauras, and P. Quinton, “A Language-Oriented Approach to the Design of Systolic Chips,” inAlgorthms and Parallel VLSI Architectures. Lectures and Tutorials Presented at the International Workshop Vol. A,, E.F. Deprettere and A.-J. van der Veen (Eds.), Amsterdam, Netherlands: Elsevier Science Publishers B.V., pp. 309–327, 1991.Google Scholar
  20. 20.
    F. Catthoor, “Microcoded Processor Architectures and Synthesis Methodologies for Real-Time Signal Processing,” inAlgorithms and Parallel VLSI Architectures. Lectures and Tutorials Presented at the International Workshop Vol. A,, E.F. Deprettere and A.-J. van der Veen (Eds.), Amsterdam, Netherlands: Elsevier Science Publishers B.V., pp. 403–429, 1991.Google Scholar
  21. 21.
    Y.-T. Hwang and Y.H. Hu, “MSSM—A Design Aid for Multi-Stage Systolic Mapping,”Journal of VLSI Signal Processing, Vol. 4, No. 2–3, pp. 125–145, 1992.CrossRefGoogle Scholar
  22. 22.
    V. van Dongen, “From Systolic to Periodic Array Design,” inAlgorithms and Parallel VLSI Architectures II, P. Quinton and Y. Robert (Eds.), Amsterdam, Netherlands: Elsevier Science Publishers B.V., pp. 151–162, 1992.Google Scholar
  23. 23.
    L. Thiele and U. Arzt, “On the Synthesis of Massively Parallel Architectures,”International Journal of High Speed Electronics and Systems, Vol. 4, No. 2, pp. 99–131, 1993.CrossRefGoogle Scholar
  24. 24.
    U. Vehlies, “DECOMP—A Program for Mapping DSP Algorithms onto Systolic Arrays,” inTransformational Approaches to Systolic Design, G.M. Megson (Ed.), London, UK: Chapman & Hall, 1994, pp. 159–178.Google Scholar
  25. 25.
    W. Burleson, “Using Regular Array Methods for DSP Module Synthesis,”Proc. 27th Hawaii Intl. Conf. System Sciences Vol. I: Architecture, Wailea, HI, USA, 1994, pp. 58–67.Google Scholar
  26. 26.
    J. Buck, S. Ha, E.A. Lee, and D.G. Messerschmitt, “Ptolemy: A Framework for Simulating and Prototyping Heterogeneous Systems,”International Journal of Computer Simulation, Vol. 4, pp. 155–182, 1994.Google Scholar
  27. 27.
    G.M. Megson,An Introduction to Systolic Algorithm Design, Oxford: Clarendon Press, 1992.MATHGoogle Scholar
  28. 28.
    S.-W. Hwang, C.-M. Liu, and C.-W. Jen, “A Workbench for VLSI Array Design,”Proc. Electron Devices, and Material Circuit Technology Symposium, Hsinchu, Taiwan, R.O.C., 1989, pp. 91–97.Google Scholar
  29. 29.
    T.-H. Huang, C.-M. Liu, and C.-W. Jen, “A High-Level Synthesizer for VLSI Array Architectures Dedicated to Digital Signal Processing,”Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, Ontario, Canada, 1991, Vol. 2, pp. 1221–1224.Google Scholar
  30. 30.
    S.Y. Kung,VLSI Array Processors, Englewood Cliffs, NJ: Prentice-Hall International, Inc., 1988.Google Scholar
  31. 31.
    R.H. Kuhn, “Transforming Algorithms for Single-Stage and VLSI Architectures,” inPorc. Workshop on Interconnection Networks for Parallel and Distributed Processing, H.J. Siegel (Ed.), 1980, pp. 11–19.Google Scholar
  32. 32.
    C.-M. Liu and C.-W. Jen, “Design of Algorithm-Based Fault-Tolerant VLSI Array Processor,”IEEE Proc. Part E: Computers and Digital Techniques, Vol. 136, No. 6, pp. 539–547, 1989.Google Scholar
  33. 33.
    H.T. Kung and M.S. Lam, “Wafer-Scale Integration and Two-Level Pipelined Implementations,”Journal of Parallel and Distributed Processing, Vol. 1, No. 1, pp. 32–62, 1984.CrossRefGoogle Scholar
  34. 34.
    S.-J. Jou and C.-W. Jen, “Design of a Systolic Array System for Linear State Equations,”IEE Proc. Part G: Electronic Circuits and Systems, Vol. 135, No. 5, pp. 211–218, 1988.Google Scholar
  35. 35.
    S.K. Rao, “Regular Iterative Algorithms and Their Implementation on Processor Arrays,” Ph.D. Thesis, Stanford University, Stanford, California, 1985.Google Scholar
  36. 36.
    J. Teich and L. Thiele, “Control Generation in the Design of Processor Arrays,”Journal of VLSI Signal Processing, Vol. 3, No. 1–2, pp. 77–92, 1991.CrossRefGoogle Scholar
  37. 37.
    M. Huber, J. Teich, and L. Thiele, “Design of Configurable Processor Arrays,”Proc. IEEE Intl. Symp. Circuits and Systems, New Orleans, LA, USA, 1990, Vol. 2, pp. 970–973.Google Scholar
  38. 38.
    J. Xue and C. Lengauer, “The Synthesis of Control Signals for One-Dimensional Systolic Arrays,”Integration, The VLSI Journal, Vol. 14, No. 1, pp. 1–32, 1992.CrossRefMATHGoogle Scholar
  39. 39.
    U. Vehlies, “Mapping Different Node Types of Dependence Graphs into the Same Processing Element,”Proc. Intl. Conf. Application Specific Array Processors, Barcelona, Spain, 1991, pp. 72–86.Google Scholar
  40. 40.
    C.-W. Jen and H.-Y. Hsu, “Design of a Systolic Array with Tags Input,”Proc. IEEE Intl. Symp. Circuits and Systems, Espoo, Finland, 1988, pp. 2263–2266.Google Scholar
  41. 41.
    Michael Andrews,Principles of Firmware Engineering in Microprogram Control, Potomac, Md., Woodland Hills, California: Computer Science Press. 1980.MATHGoogle Scholar
  42. 42.
    J.-J. Wang and C.-W. Jen, “The Kalman Filter Design by Systolic Arrays with Tag Input,”IEEE Intl. Symp. Circuits and Systems, Portland, OR, USA, 1989, Vol. 2, pp. 1191–1194.Google Scholar
  43. 43.
    J.-I. Guo, C.-M. Liu, and C.-W. Jen, “A New Array Architecture for Prime-Length Discrete Cosine Transform,”IEEE Transactions on Signal Processing, Vol. 41, No. 1, pp. 436–442, 1993.CrossRefMATHGoogle Scholar
  44. 44.
    J.H. Wilkinson,The Algebraic Eigenvalue Problem, New York: Oxford University Press, 1965.MATHGoogle Scholar
  45. 45.
    M.C. McFarland, A.C. Parker, and R. Camposano, “High-Level Synthesis of Digital Systems,”Proceedings of the IEEE, Vol. 78, No. 2, pp. 301–318, 1990.CrossRefGoogle Scholar
  46. 46.
    W.-J. Cheng and C.-W. Jen, “A VLSI Array System Synthesizer,” Thesis, Institute of Electronics, National Chiao Tung University, Hsinchu, Taiwan, R.O.C., 1992.Google Scholar
  47. 47.
    D.I. Moldovan and J.A.B. Fortes, “Partitioning and Mapping Algorithms into Fixed Size Systolic Arrays,”IEEE Trans. Computers, Vol. C-35, No. 1, 1986.Google Scholar
  48. 48.
    J.G. Proakis and D.G. Manolakis,Introduction to Digital Signal Processing, New York: Macmillan Publishing Company, 1988.Google Scholar

Copyright information

© Kluwer Academic Publishers 1996

Authors and Affiliations

  • Jinn-Wang Yeh
    • 1
  • Wen-Jiunn Cheng
    • 1
  • Chein-Wei Jen
    • 1
  1. 1.Department of Electronics Engineering & Institute of ElectronicsNational Chiao Tung UniversityHsinchuTaiwan, R.O.C.

Personalised recommendations