Abstract
Vector supercomputers are designed with two levels of parallelism in order to achieved computational efficiency: low level parallelism through vector operations and high level parallelism with multiple independent processors. These innovations have a significant impact on the development of algorithms for network optimization.
In this paper a framework for the vectorization and multitasking of optimization software is developed. It is then applied on the primal truncated Newton algorithm for nonlinear generalized network problems. The vectorization and multitasking of the algorithm is discussed and illustrated with computational experiments with the software system NLPNETG on the CRAY series of vector multiprocessors.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
D.P. Ahlfeld, R.S. Dembo, J.M. Mulvey and S.A. Zenios, “Nonlinear programming on generalized networks,” to appear inACM Transactions on Mathematical Software 13 (4) (1987) 350–367.
G. Amdahl, “The validity of single processor approach to achieving large scale computing capabilities,” AFIPS Proceedings, vol. 30 (1967) pp. 783–785.
D.P. Bertsekas and D. El Baz, “Distributed asynchronous relaxation methods for convex network flow problems,”SIAM Journal of Control and Optimization 25 (1) (1987) 74–85.
G.G. Brown and R.D. McBride, “Solving generalized networks,”Management Science 30 (12) (1984) 1497–1523.
I.Y. Bucher, “The computational speed of supercomputers,”Proceedings of the ACM Sigmetrics Conference on Measurement and Modeling of Computer Systems, Aug 1983, pp. 151–165.
R.H. Byrd, C.L. Dert, A.H.G. Rinnooy Kan and R.B. Schnabel, “Concurrent stochastic methods for global optimization,” Report CU-CS-338-86, Department of Computer Science, University of Colorado (Boulder, CO, June 1986).
B.L. Buzbee and D.H. Sharp, “Perspectives on supercomputing,”Science 227 (4687) (1985) 591–597.
M.D. Chang, M. Engquist, R. Finkel and R.R. Meyer, “A parallel algorithm for generalized networks,”Annals of Operations Research 4, special volume onParallel Optimization on Novel Computer Architectures (R.R. Meyer and S.A. Zenios, eds., 1988).
S.S. Chen, “Large-scale and high-speed multiprocessor system for scientific applications,” in: J.S. Kowalik, eds.,High Speed Computation, NATO ASI Series F, vol. 7 (Springer-Verlag, Berlin, 1984).
CRAY Research Inc., “Multitasking user guide,” CRAY Computer Systems Technical Note SN-0222 (March 1986).
B. Dembart, “Vectorization using GATHER and SCATTER,” Mathematics and Modeling Technical Report ETA-TR-26, Boeing Computer Services (Seattle, WA, Apr. 1985).
R.S. Dembo, J.M. Mulvey and S.A. Zenios, “Large scale nonlinear models and their application,” Report EES-86-18, Civil Engineering Department, Princeton University (Princeton, NJ, 1987).
J.J. Dongarra and I.S. Duff, “Advanced architecture computers,” Mathematics and Computer Science Division, Argonne National Laboratory (Illinois, 1985).
J.J. Dongarra and A.R. Hinds, “Unrolling loops in FORTRAN,”Software—Practice and Experience (1979) 219–226.
F. Glover, J. Hultz, D. Klingman and J. Stutz, “Generalized networks: A fundamental computer-based planning tool,”Management Science 24 (12) (1978) 1209–1220.
R. Hockney and C. Jeeshope,Parallel Computers (Adam Hilger Ltd., Bristol, England, 1981).
K. Hwang,Supercomputers: Design and Applications (IEEE Computer Society, Maryland, 1984).
J.S. Kowalik,High Speed Computations, NATO ASI Series, Computer and System Sciences 7 (Springer-Verlag, Berlin 1984).
J.L. Larson, “Multitasking on the CRAY X-MP/2 multiprocessor,”Computer (July 1984).
F.A. Lootsma and K.M. Ragsdell, “State-of-the-art in parallel nonlinear optimization,” Report 86-44, Faculty of Mathematics and Informatics, Delft University of Technology (Delft, 1986).
O.L. Mangasarian and R. DeLeone, “Parallel successive overrelaxation methods for symmetric linear complementarity and linear programs,” Mathematics Research Center Report 2947, University of Wisconsin (Madison, WI, Aug. 1986).
R.R. Meyer, “Parallel algorithms for large-scale nonlinear networks,” Presented at the SIAM Conference on Optimization (Houston, Texas, May 1987).
R.R. Meyer and S.A. Zenios, eds.,Parallel Optimization on Novel Computer Architectures. Annals of Operations Research 14 (A.C. Baltzer Scientific Publishing Co., Switzerland, 1988).
J.M. Mulvey and S. Zenios, “Solving large scale generalized networks,”Journal of Information and Optimization Science 6 (1985) 95–112.
J.M. Mulvey, S.A. Zenios and D.P. Ahlfeld, “Simplical decomposition for convex generalized networks,” Report EES-85-8, Civil Engineering Department, Princeton University (Princeton, NJ, 1985).
J.S. Pang and J.M. Yang, “Two-stage parallel iterative methods for the symmetric linear complementarity problem,” Working Paper, School of Management, University of Texas at Dallas (Richardson, TX, Jan. 1987).
A.T. Phillips and J.B. Rosen, “Multitasking mathematical programming algorithms,” Report 86-10, Computer Science Department, University of Minnesota (Minneapolis, MN, June 1986).
R.B. Schnabel, “Concurrent function evaluations in local and global optimization,” Report CS-CU-345-86, Computer Science Department, University of Colorado (Boulder CO, Oct. 1986).
S.A. Zenios and J.M. Mulvey, “Nonlinear network programming on vector supercomputers: A study on the CRAY X-MP”,Operations Research 34(5) (1986).
S.A. Zenios and J.M. Mulvey, “A distributed algorithm for convex network optimization problems,”Parallel Computing 6 (North-Holland, 1988).
S.A. Zenios,Sequential and Parallel Algorithms for Convex Generalized Network Problems and Related Applications, Ph.D. Dissertation, Civil Engineering Department, Princeton University (Princeton, NJ, May 1986).
S.A. Zenios and R.A. Lasken, “Nonlinear network optimization on a massively parallel connection machine,”Annals of Operations Research 14, Special Volume on Parallel Optimization on Novel Computer Architectures (R. R. Meyer and S. A. Zenios, eds., 1988).
S.A. Zenios, “An annotated bibliography on parallel optimization,”ORSA Journal on Computing (to appear, 1989).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Zenios, S.A., Mulvey, J.M. Vectorization and multitasking of nonlinear network programming algorithms. Mathematical Programming 42, 449–470 (1988). https://doi.org/10.1007/BF01589416
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01589416