This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Static Rate-Optimal Scheduling of Iterative Data-Flow Programs Via Optimum Unfolding
February 1991 (vol. 40 no. 2)
pp. 178-195

Rate-optimal compile-time multiprocessor scheduling of iterative dataflow programs suitable for real-time signal processing applications is discussed. It is shown that recursions or loops in the programs lead to an inherent lower bound on the achievable iteration period, referred to as the iteration bound. A multiprocessor schedule is rate-optimal if the iteration period equals the iteration bound. Systematic unfolding of iterative dataflow programs is proposed, and properties of unfolded dataflow programs are studied. Unfolding increases the number of tasks in a program, unravels the hidden concurrently in iterative dataflow programs, and can reduce the iteration period. A special class of iterative dataflow programs, referred to as perfect-rate programs, is introduced. Each loop in these programs has a single register. Perfect-rate programs can always be scheduled rate optimally (requiring no retiming or unfolding transformation). It is also shown that unfolding any program by an optimum unfolding factor transforms any arbitrary program to an equivalent perfect-rate program, which can then be scheduled rate optimally. This optimum unfolding factor for any arbitrary program is the least common multiple of the number of registers (or delays) in all loops and is independent of the node execution times. An upper bound on the number of processors for rate-optimal scheduling is given.

[1] R.E. Karp and R.E. Miller, "Properties of a model for parallel computations: Determinacy, termination, and queueing,"SIAM J. Appl. Math., vol. 14, no. 6, pp. 1390-1411, Nov. 1966.
[2] R. Reiter, "Scheduling parallel computations,"J. ACM, vol. 15, no. 4, pp. 590-599, Oct. 1968.
[3] R. E. Crochiere and A. V. Oppenheim, "Analysis of linear digital networks,"Proc. IEEE, vol. 63, no. 4, pp. 581-595, Apr. 1975.
[4] J.B. Dennis, "Data flow supercomputers,"IEEE Comput. Mag., pp. 48-56, Nov. 1980.
[5] A. L. Davis and R. M. Keller, "Data flow program graphs,"IEEE Comput. Mag., vol. 15, no. 2, pp. 26-41, Feb. 1982.
[6] W. B. Ackerman, "Data flow languages,"IEEE Comput. Mag., vol. 15, no. 2, pp. 15-25, Feb. 1982.
[7] E. A. Lee and D. G. Messerschmitt, "Static scheduling of synchronous data flow programs for digital signal processing,"IEEE Trans. Comput., vol. C-36, no. 1, pp. 24-35, Jan. 1987.
[8] S. Y. Kung, P. S. Lewis, and S. C. Lo, "Performance analysis and optimization of VLSI data flow arrays,"J. Parallel Distributed Comput., vol. 4, pp. 592-618, 1987.
[9] K.K. Parhi and D.G. Messerschmitt, "Rate-optimal fully-static multiprocessor scheduling of data-flow signal processing programs," inProc. 1989 IEEE Int. Symp. Circuits Syst., Portland, OR, May 1989
[10] K.K. Parhi and D.G. Messerschmitt, "Fully-static rate-optimal scheduling of iterative data-flow programs via optimum unfolding," inProc. 1989 Int. Conf. Parallel processing, St. Charles, IL, Aug. 1989
[11] S. C. Cheng, J. A. Stankovic, and K. Ramamritham, "Scheduling algorithms for hard real-timd systems-A brief survey," inHard Real-Time Systems Tutorial, J. A. Stankovic, Ed. New York: IEEE Computer Society Press, 1988, pp. 150-173.
[12] C. L. Liu and J. W. Layland, "Scheduling algorithms for multiprogramming in a hard real-time environment,"J. ACM, vol. 20, no. 1, pp. 46-61, Jan. 1973.
[13] E. L. Lawler and C. U. Martel, "Scheduling periodically occurring tasks on multiple processsors,"Inform. Processing Lett., vol. 12, pp. 9-12, 1981.
[14] W. Zhao, K. Ramamritham, and J. A. Stankovic, "Preemptive scheduling under time and resource constraints,"IEEE Trans. Comput., Aug. 1987.
[15] J. W.S. Liuet al., "Scheduling real-time, periodic jobs using imprecise results," inProc. IEEE Real-Time Syst. Symp., San Jose, CA, Dec. 1987, pp. 252-260.
[16] E.G. Coffman, Jr., Ed.,Computer and Job Scheduling Theory. New York: Wiley, 1976.
[17] D. A. Schwartz and T. P. Barnwell, III, "A graph theoretic technique for the generation of systolic implementations for shift invariant flow graphs," inProc. ICASSP-84, San Diego, CA, Mar. 1984.
[18] D. A. Schwartz, "Synchronous multiprocessor realizations of shift invariant flow graphs," Ph.D. dissertation, Georgia lnstit. Technol., Tech. Rep. DSPL-85-2, July 1985.
[19] D. A. Schwartz and T. P. Barnwell, III, "Cyclostatic multiprocessor scheduling for the optimal implementation of shift invariant flow graphs," inProc. ICASSP-85, Tampa, FL, Mar. 1985.
[20] D.A. Schwartz, "Cyclo-static realizations: Loop unrolling and CPM, optimal multiprocessor scheduling," inProc. 1987 Princeton Workshop Algorithms, Architecture, and Technology Issues in Models of Concurrent Computations, Sept. 30-Oct. 1, 1987.
[21] S. H. Lee and T. P. Barnwell, III, "Optimal multiprocessor implementation from a serial algorithm specification," inProc. ICASSP- 88, NY, Apr. 1988, pp. 1694-1697.
[22] H. Forren and D. A. Schwartz, "Transforming periodic synchronous multiprocessor programs," inProc. ICASSP-87, Dallas, TX, Apr. 1987, pp. 1406-1409.
[23] M. Renfors and Y. Neuvo, "The maximum sampling rate of digital filters under hardware speed constraints,"IEEE Trans Circuits Syst., vol. CAS-28, no. 3, pp. 196-202, Mar. 1981.
[24] T. P. Barnwell, III and C. J. M. Hodges, "Optimal implementation of signal flow graphs on synchronous multiprocessors," inProc. 1982 Int. Conf. Parallel Processing, Belaire, MI, Aug. 1982.
[25] C. V. Ramamoorthy and G. S. Ho, "Performance evaluation of asynchronous concurrent systems using Petri nets,"IEEE Trans. Software Eng., vol. SE-6, no. 5, pp. 440-449, Sept. 1980.
[26] J. P. Brafman, J. Szczupak, and S. K. Mitra, "An approach to implementation of digital filters using microprocessors,"IEEE Trans. Acoust., Speech, Signal Processing, vol. 26, no. 5, pp. 442-446, Oct. 1978.
[27] J. Zeman and G. S. Moschytz, "Systematic design and programming of signal processors using project management techniques,"IEEE Trans. Acoust., Speech, Signal Processing, vol. 31, no. 6, pp. 1536-1549, Dec. 1983.
[28] C. E. Leiserson, F. Rose, and J. Saxe, "Optimizing synchronous circuitry by retiming," inProc. Third Caltech Conf. VLSI, Pasadena, CA, Mar. 1983, pp. 87-116.
[29] S. Y. Kung, "On supercomputing with systolic/wavefront array processors,"Proc. IEEE, vol. 72, no. 7, July 1984.
[30] K. K. Parhi and D. G. Messerschmitt, "Concurrent cellular VLSI adaptive filter architectures,"IEEE Trans. Circuits Syst., vol. 10, pp. 1141-1151, Oct. 1987.
[31] K. K. Parhi and D. G. Messerschmitt, "Pipelining and parallelism in recursive digital filters, Part II,"IEEE Trans. Acoust., Speech, Signal Processing, pp. 1118-1135. July 1989.
[32] M. R. Garey and D. S. Johnson,Computers and Intractability: A Guide to Theory of NP-Completeness. San Francisco, CA: Freeman, 1979.
[33] K. K. Parhi, "Algorithm transformations for concurrent processors,"Proc. IEEE, vol. 77, no. 12, pp. 1879-1895, Dec. 1989.
[34] T. C. Hu, "Parallel sequencing and assembly line problems,"Oper. Res., vol. 9, pp. 841-848, 1961.
[35] M. C. McFarlandet al., "High level synthesis of digital systems,"Proc. IEEE, Feb. 1990.
[36] K. K. Parhi, "Nibble-serial arithmetic processor designs via unfolding," inProc. IEEE Int. Symp. Circuits Syst., May 1989, OR, pp. 635-640.
[37] C.-Y. Wang and K. K. Parhi, "Digit-serial DSP architectures," inProc. IEEE Conf. Application Specific Array Processors, Princeton, NJ, Sept. 1990.
[38] K. K. Parhi, "A systematic approach for design of digit-serial signal processing architectures,"IEEE Trans. Circuits Syst., to be published.

Index Terms:
static rate optimal scheduling; iterative data-flow programs; optimum unfolding; real-time signal processing; iteration period; perfect-rate programs; perfect-rate program; upper bound; parallel programming; scheduling.
Citation:
K.K. Parhi, D.G. Messerschmitt, "Static Rate-Optimal Scheduling of Iterative Data-Flow Programs Via Optimum Unfolding," IEEE Transactions on Computers, vol. 40, no. 2, pp. 178-195, Feb. 1991, doi:10.1109/12.73588
Usage of this product signifies your acceptance of the Terms of Use.