This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Multirate VLSI Arrays and Their Synthesis
May 1997 (vol. 46 no. 5)
pp. 515-529

Abstract—Many applications in signal and image processing can be efficiently implemented on regular VLSI architectures such as systolic arrays. Multirate arrays (MRAs) are an extension of systolic arrays where different data streams are propagated with different clocks. We address the analysis and synthesis problem for this class of architectures. We present a formal definition of MRAs, as systems of recurrence equations defined over sparse polyhedral domains. We also give transformation rules for this class of recurrences, and use them to show that MRAs constitute a particular subset of systems of affine recurrence equations (SoAREs). We then address the synthesis problem, and show how an MRA can be systematically derived from an initial specification in the form of a mathematical equation. The main transformations that we use are domain rescalings and dependency decomposition, and we illustrate our method by deriving a hitherto unknown decimation filter array.

[1] D.G. Baltus and J. Allen, "Optimal Systolic Array Synthesis," Proc. Int'l Conf. Application Specific Array Processors, pp. 428-441,Venice, 1993.
[2] M. Chen, "A Parallel Language and Its Compilation to Multiprocessors Machines or VLSI," Conf. Record 13th Ann. ACM Conf. Principles of Programming Languages, pp. 131-139. ACM, Jan. 1986.
[3] R. Karp, R. Miller, and S. Winograd, "The Organization of Computations for Uniform Recurrence Equations," J. ACM, vol. 14, July 1967.
[4] C. Mead and L. Conway, "Introduction to VLSI Systems," Algorithms for VLSI Processor Arrays, H.T. Kung and C.E. Leiserson, eds., chapter 8.3, pp. 271-292.Reading, Mass.: Addison-Wesley, 1980.
[5] S.Y. Kung, K.S. Arun, R.J. Gal-Ezer, and D.V.B. Rao, "Wavefront Array Processor: Language, Architecture, and Applications," IEEE Trans. Computers, vol. 31, pp. 1,054-1,066, 1982.
[6] H. Le Verge, "Un environment de transformations de programmes pour la synthèse d'architectures régulières," PhD thesis, L'Universitéde Rennes I, IRISA, Campus de Beaulieu, Rennes, France, Oct. 1992.
[7] H. Le Verge, C. Mauraas, and P. Quinton, "The ALPHA Language and Its Use for the Design of Systolic Arrays," J. VLSI Signal Processing, vol. 3, no. 3, pp. 173-182, Sept. 1991.
[8] H. Le Verge and P. Quinton, "Recurrences on Lattice Polyhedra and Their Applications to the Synthesis of Systolic Arrays," updated version to appear as IRISA research report, Jan. 1994.
[9] P. Lenders, "Synthesis and Design of Multidimensional Multirate VLSI Arrays," Proc. Pacific Rim Conf. Comm., Computers, and Signal Processing,Victoria, B.C., Canada, May 1991.
[10] A. Li and S. Kiaei, "VLSI Design of Multi-Rate Arrays for DSP Algorithms," Proc. ICASSP 90: Int'l Conf. Acoustics, Speech, and Signal Processing,Albuquerque, N.M., 1990.
[11] A. Li, "Synthesis of Multi-Rate Arrays from Directional Uniform Recurrence Equations," master's thesis, Oregon State Univ., Electrical and Computer Eng. Dept., Corvallis, Ore., Mar. 1990.
[12] J. Li and M. Chen, "The Data Alignment Phase in Compiling Programs for Distributed-Memory Machines," J. Parallel and Distributed Computing, vol. 13, pp. 213-221, 1991.
[13] C. Mauras, "ALPHA: un langageéquationnel pour la conception et la programmation d'architectures parallèles synchrones," PhD thesis, L'Universitéde Rennes I, IRISA, Campus de Beaulieu, Rennes, France, Dec. 1989.
[14] C. Maruas, P. Quinton, S.V. Rajopadhye, and Y. Saouter, "Scheduling Affine Paramterized Recurrences by Means of Variable Dependent Timing Functions," Proc. Int'l Conf. Application Specific Array Processing, S.Y. Kung, E. Swartzlander, eds., pp. 100-110,Princeton, N.J., Sept. 1990.
[15] P. Quinton, "Automata Networks in Computer Science," The Systematic Design of Systolic Arrays, chapter 9, pp. 229-260. Princeton Univ. Press, 1987. Preliminary versions appeared as IRISA Technical Reports 193 and 216, 1983.
[16] P. Quinton and V. Van Dongen, "The Mapping of Linear Recurrence Equations on Regular Arrays," J. VLSI Signal Processing, vol. 1, no. 2, pp. 95-113, 1989.
[17] S.V. Rajopadhye, "Synthesis, Optimization, and Verification of Systolic Architectures," PhD thesis, Univ. of Utah, Salt Lake City, Dec. 1986.
[18] S.V. Rajopadhye and R.M. Fujimoto, "Synthesizing Systolic Arrays from Recurrence Equations," Parallel Computing, vol. 14, pp. 163-189, June 1990.
[19] S.K. Rao,“Regular iterative algorithms and their implementations on processor arrays,” PhD thesis, Stanford Univ., 1985.
[20] S. Rao and T. Kailath, "What Is a Systolic Algorithm?" Proc. Highly Parallel Signal Processing Architectures, pp. 34-48,Los Angeles, 1986.
[21] V. Roychowdhury, L. Thiele, S.K. Rao, and T. Kailath, "On the Loacalization of Algorithms for VLSI Processor Arrays," VLSI Signal Processing, III, R.W. Brodersen and H.S. Moscovitz, eds., pp. 459-470,Monterey, Calif., Nov. 1988. A detailed version submitted to IEEE Trans. on Computers.
[22] J. Teich and L. Thiele, "Partitioning of Processor Arrays: A Piecewise Regular Approach," INTEGRATION: The VLSI J., vol. 14, no. 3, pp. 297-332, Feb. 1993.
[23] Y.W. Wong and J.M. Delosme,“Broadcast removal in systolic algorithms,” Proc. Int’l Conf. Systolic Arrays, pp. 403-412, 1988.
[24] Y. Yaacoby and P.R. Cappello, "Converting Affine Recurrence Equations to Quasi-Uniform Recurrence Equations," Proc. AWOC 1988: Third Int'l Workshop Parallel Computation and VLSI Theory, June 1988. See also Univ. of California Santa Barbara Technical Report TRC87-18, Feb. 1988.
[25] Y. Yaacoby and P.R. Cappello, "Scheduling a System of Nonsingular Affine Recurrence Equations onto a Processor Array," J. VLSI Signal Processing, vol. 1, no. 2, pp. 115-125, 1989.
[26] Y. Zheng and S. Kiaei, "Multirate Transformation of Directional Affine Recurrence Equations," Proc. ASAP 93: Application Specific Array Processing Conf., L. Dadda and B. Wah, eds., pp. 392-403,Venice, Oct. 1993.

Index Terms:
Application specific processor arrays, space-time mappings, index transformations, systolic arrays, VLSI signal processing.
Citation:
Patrick Lenders, Sanjay Rajopadhye, "Multirate VLSI Arrays and Their Synthesis," IEEE Transactions on Computers, vol. 46, no. 5, pp. 515-529, May 1997, doi:10.1109/12.589218
Usage of this product signifies your acceptance of the Terms of Use.