Abstract
We investigate the practical merits of a parallel priority queue through its use in the development of a fast and work-efficient parallel shortest path algorithm, originally designed for an EREW PRAM. Our study reveals that an efficient implementation on a real supercomputer requires considerable effort to reduce the communication performance (which in theory is assumed to take constant time). It turns out that the most crucial part of the implementation is the mapping of the logical processors to the physical processing nodes of the supercomputer. We achieve the requested efficient mapping through a new graph-theoretic result of independent interest: computing a Hamiltonian cycle on a directed hyper-torus. No such algorithm was known before for the case of directed hypertori. Our Hamiltonian cycle algorithm allows us to considerably improve the communication cost and thus the overall performance of our implementation.
This work was supported by the Consorzio Ricerche del Gran Sasso (CRGS), by the Human Potential Programme of EU under contract no. HPRN-CT-1999-00104 (project AMORE), and by the Future and Emerging Technologies Unit of EC (IST priority – 6th FP), under contract no. FP6-021235-2 (project ARRIVAL).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ahuja, R.K., Magnanti, T.L., Orlin, J.B.: Network Flows. Prentice-Hall, Englewood Cliffs (1993)
Aglietti, F., et al.: An overview of the APEmille parallel computer. Nucl. Inst. And Methods in Phys. A 389, 56–58 (1997)
Brodal, G.: Priority queues on parallel machines. In: Karlsson, R., Lingas, A. (eds.) SWAT 1996. LNCS, vol. 1097, pp. 416–427. Springer, Heidelberg (1996)
Brodal, G., Träff, J., Zaroliagis, C.: A Parallel Priority Queue with Constant Time Operations. Journal of Parallel and Distributed Computing 49, 4–21 (1998)
Cabasino, S., D’Autilia, R., Paolucci, P.S., Todesco, G.M.: The TAO language (1995), http://www-zeuthen.desy.de/ape/html/APEmille/Documentation/
Chen, D.Z., Hu, X.: Fast and efficient operations on parallel priority queues. In: Du, D.-Z., Zhang, X.-S. (eds.) ISAAC 1994. LNCS, vol. 834, pp. 279–287. Springer, Heidelberg (1994)
Chen, C.C., Quimpo, N.F.: On strongly Hamiltonian abelian group graphs. Lecture Notes in Mathematics, vol. 884, pp. 23–34 (1981)
Curran, S.J., Witte, D.: Hamilton paths in Cartesian products of directed cycles. Ann. Discrete Mathematics 27, 35–74 (1985)
Das, S.K., Pinotti, M.C., Sarkar, F.: Optimal and load balanced mapping of parallel priority queues in hypercubes. Trans. Par. Dist. Syst. 7, 555–564 (1996) [Corr. 896]
Dijkstra, E.W.: A note on two problems in connexion with graphs. Numer. Math. 1, 269–271 (1959)
Di Stefano, G., Petricola, A., Zaroliagis, C.: On the Implementation of Parallel Shortest Path Algorithms on a Supercomputer. Tech. Rep. Univ. of L’Aquila (2006)
Francia, M., Panizzi, E., Petricola, A., Visconti, G.: Parallel Simulation of Orography Influence on Large-Scale Atmosphere Motion on APEmille. In: ACM Computing Frontiers 2004, pp. 320–325 (2004)
Fredman, M.L., Tarjan, R.E.: Fibonacci Heaps and their uses in Improved Network Optimization Algorithm. Journal of ACM 34(3), 596–615 (1987)
Jájá, J.: An Introduction to Parallel Algorithms. Addison-Wesley, Reading (1992)
Karp, R.M., Ramachandran, V.: Parallel Algorithms for Shared-Memory Machines. Handbook of Theoretical Computer Science A, C17, 869–942 (1990)
Leontiev, V.K.: Hamiltonian cycles in torical lattices. In: DMTCS Conference, AE, pp. 397–400 (2005)
Panizzi, E., Sacco, G.: The APEmille project. In: HPCN 2000. LNCS, pp. 539–542. Springer, Heidelberg (2000)
Rankin, R.A.: A campanological problem in group theory. Proc. Camb. Phil. Soc. 44, 17–25 (1948)
Stone, H.S.: High Performance Computer Architecture. Addison-Wesley, Reading (1990)
Trotter, W., Erdös, P.: When the Cartesian product of directed cycles is Hamiltonian. J. Graph Theory 2, 137–142 (1978)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Di Stefano, G., Petricola, A., Zaroliagis, C. (2006). On the Implementation of Parallel Shortest Path Algorithms on a Supercomputer. In: Guo, M., Yang, L.T., Di Martino, B., Zima, H.P., Dongarra, J., Tang, F. (eds) Parallel and Distributed Processing and Applications. ISPA 2006. Lecture Notes in Computer Science, vol 4330. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11946441_40
Download citation
DOI: https://doi.org/10.1007/11946441_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68067-3
Online ISBN: 978-3-540-68070-3
eBook Packages: Computer ScienceComputer Science (R0)