
This Article  
 
Share  
Bibliographic References  
Add to:  
Digg Furl Spurl Blink Simpy Del.icio.us Y!MyWeb  
Search  
 
ASCII Text  x  
K.K. Parhi, D.G. Messerschmitt, "Static RateOptimal Scheduling of Iterative DataFlow Programs Via Optimum Unfolding," IEEE Transactions on Computers, vol. 40, no. 2, pp. 178195, February, 1991.  
BibTex  x  
@article{ 10.1109/12.73588, author = {K.K. Parhi and D.G. Messerschmitt}, title = {Static RateOptimal Scheduling of Iterative DataFlow Programs Via Optimum Unfolding}, journal ={IEEE Transactions on Computers}, volume = {40}, number = {2}, issn = {00189340}, year = {1991}, pages = {178195}, doi = {http://doi.ieeecomputersociety.org/10.1109/12.73588}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }  
RefWorks Procite/RefMan/Endnote  x  
TY  JOUR JO  IEEE Transactions on Computers TI  Static RateOptimal Scheduling of Iterative DataFlow Programs Via Optimum Unfolding IS  2 SN  00189340 SP178 EP195 EPD  178195 A1  K.K. Parhi, A1  D.G. Messerschmitt, PY  1991 KW  static rate optimal scheduling; iterative dataflow programs; optimum unfolding; realtime signal processing; iteration period; perfectrate programs; perfectrate program; upper bound; parallel programming; scheduling. VL  40 JA  IEEE Transactions on Computers ER   
Rateoptimal compiletime multiprocessor scheduling of iterative dataflow programs suitable for realtime 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 rateoptimal 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 perfectrate programs, is introduced. Each loop in these programs has a single register. Perfectrate 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 perfectrate 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 rateoptimal 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. 13901411, Nov. 1966.
[2] R. Reiter, "Scheduling parallel computations,"J. ACM, vol. 15, no. 4, pp. 590599, Oct. 1968.
[3] R. E. Crochiere and A. V. Oppenheim, "Analysis of linear digital networks,"Proc. IEEE, vol. 63, no. 4, pp. 581595, Apr. 1975.
[4] J.B. Dennis, "Data flow supercomputers,"IEEE Comput. Mag., pp. 4856, Nov. 1980.
[5] A. L. Davis and R. M. Keller, "Data flow program graphs,"IEEE Comput. Mag., vol. 15, no. 2, pp. 2641, Feb. 1982.
[6] W. B. Ackerman, "Data flow languages,"IEEE Comput. Mag., vol. 15, no. 2, pp. 1525, 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. C36, no. 1, pp. 2435, 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. 592618, 1987.
[9] K.K. Parhi and D.G. Messerschmitt, "Rateoptimal fullystatic multiprocessor scheduling of dataflow signal processing programs," inProc. 1989 IEEE Int. Symp. Circuits Syst., Portland, OR, May 1989
[10] K.K. Parhi and D.G. Messerschmitt, "Fullystatic rateoptimal scheduling of iterative dataflow 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 realtimd systemsA brief survey," inHard RealTime Systems Tutorial, J. A. Stankovic, Ed. New York: IEEE Computer Society Press, 1988, pp. 150173.
[12] C. L. Liu and J. W. Layland, "Scheduling algorithms for multiprogramming in a hard realtime environment,"J. ACM, vol. 20, no. 1, pp. 4661, Jan. 1973.
[13] E. L. Lawler and C. U. Martel, "Scheduling periodically occurring tasks on multiple processsors,"Inform. Processing Lett., vol. 12, pp. 912, 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 realtime, periodic jobs using imprecise results," inProc. IEEE RealTime Syst. Symp., San Jose, CA, Dec. 1987, pp. 252260.
[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. ICASSP84, 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. DSPL852, July 1985.
[19] D. A. Schwartz and T. P. Barnwell, III, "Cyclostatic multiprocessor scheduling for the optimal implementation of shift invariant flow graphs," inProc. ICASSP85, Tampa, FL, Mar. 1985.
[20] D.A. Schwartz, "Cyclostatic realizations: Loop unrolling and CPM, optimal multiprocessor scheduling," inProc. 1987 Princeton Workshop Algorithms, Architecture, and Technology Issues in Models of Concurrent Computations, Sept. 30Oct. 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. 16941697.
[22] H. Forren and D. A. Schwartz, "Transforming periodic synchronous multiprocessor programs," inProc. ICASSP87, Dallas, TX, Apr. 1987, pp. 14061409.
[23] M. Renfors and Y. Neuvo, "The maximum sampling rate of digital filters under hardware speed constraints,"IEEE Trans Circuits Syst., vol. CAS28, no. 3, pp. 196202, 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. SE6, no. 5, pp. 440449, 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. 442446, 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. 15361549, 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. 87116.
[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. 11411151, 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. 11181135. July 1989.
[32] M. R. Garey and D. S. Johnson,Computers and Intractability: A Guide to Theory of NPCompleteness. San Francisco, CA: Freeman, 1979.
[33] K. K. Parhi, "Algorithm transformations for concurrent processors,"Proc. IEEE, vol. 77, no. 12, pp. 18791895, Dec. 1989.
[34] T. C. Hu, "Parallel sequencing and assembly line problems,"Oper. Res., vol. 9, pp. 841848, 1961.
[35] M. C. McFarlandet al., "High level synthesis of digital systems,"Proc. IEEE, Feb. 1990.
[36] K. K. Parhi, "Nibbleserial arithmetic processor designs via unfolding," inProc. IEEE Int. Symp. Circuits Syst., May 1989, OR, pp. 635640.
[37] C.Y. Wang and K. K. Parhi, "Digitserial DSP architectures," inProc. IEEE Conf. Application Specific Array Processors, Princeton, NJ, Sept. 1990.
[38] K. K. Parhi, "A systematic approach for design of digitserial signal processing architectures,"IEEE Trans. Circuits Syst., to be published.