Abstract
Task scheduling is an essential aspect of parallel process system. This NP-hard problem assumes fully connected homogeneous processors and ignores contention on the communication links. However, as arbitrary processor network (APN), communication contention has a strong influence on the execution time of a parallel application. This paper investigates the incorporation of contention awareness into task scheduling. The innovation is the idea of dynamically scheduling edges to links, for which we use the earliest finish communication time search algorithm based on shortest-path search method. The other novel idea proposed in this paper is scheduling priority based on recursive rank computation on heterogeneous arbitrary processor network. In the end, to reduce time complexity of algorithm, a parallel algorithm is proposed and speedup O(PPE) is achieved. The comparison study, based on both randomly generated graphs and the graphs of some real applications, shows that our scheduling algorithm significantly surpasses classic and static communication contention awareness algorithm, especially for high data transmission rate parallel application.
References
Sih G C, Lee E A. A compile-time scheduling heuristic for interconnection-constrained heterogeneous machine architectures. IEEE Trans Parallel Distrib Syst, 1993, 4 (2): 175–187
Gary M R, Johnson D S. Computers and Intractability: A Guide to the Theory of NP-Completeness. San Francisco: W.H. Freeman and Co., 1979
Ahmad I, Kwok Y.-K. On exploiting task duplication in parallel program scheduling. IEEE Trans. Parallel Distrib. Systems, 1998, 9(9): 872–892
Darbha S, Agrawal D P. Optimal scheduling algorithm for distributed-memory machines. IEEE Trans Parallel Distrib Syst, 1998, 9(1): 87–95
Papadimitriou C H, Yannakakis M. Towards an architecture-Independent analysis of parallel algorithms. SIAM J Comput, 1990, 19(2): 322–328
Dhodhi M, Ahmad I, Yatama A, et al. An integrated technique for task matching and scheduling onto distributed heterogeneous computing system. J Parallel Distrib Comput, 2002, 62(9): 1338–1361
Topcuoglu H, Hariri S, Wu M Y. Task scheduling algorithms for heterogeneous machines. In: Proceedings of the Heterogeneous Computing Workshop, Mexico, 1999. 3–14
Radulescu A, van Gemund A J C. Low-cost task scheduling for distributed-memory machines. IEEE Trans Parallel Distrib Syst, 2002, 13(6): 648–658
Park H J, Kim B K. An optimal scheduling algorithm for minimizing the computing period of cyclic synchronous tasks on multiprocessors. J Syst Software, 2001, 56(3): 213–229
Kim D, Yi B G. A two-pass scheduling algorithm for parallel programs. Parallel Comput, 1994, 20(6): 869–885
Kwok Y -K, Ahmad I. Dynamic critical-path scheduling: an effective technique for allocating task graphs onto multiprocessors. IEEE Trans Parallel Distrib Syst, 1996, 7(5): 506–521
Sinnen O, Sousa L A. Communication contention in task scheduling. TIEEE Trans Parallel Distrib Syst, 2005, 6(6): 503–515
Sinnen O, Sousa, L A. List scheduling: extension for contention awareness and evaluation of node priorities for heterogeneous cluster architectures. Parallel Comput, 2004, 30(1): 81–101
El-Rewini H, Lewis T G. Scheduling parallel program tasks onto arbitrary target machines. J Parallel Distrib Comput, 1990, 9(2): 138–153
Iverson M, Ozuner F, Follen G. Parallelizing existing applications in a distributed heterogeneous environment. In: Proceedings of Heterogeneous Computing Workshop, 1995. 93–100
Liu G Q, Poh K L, Xie M. Iterative list scheduling for heterogeneous computing. J Parallel Distrib Comput, 2005, 65(5): 654–665
Topcuoglu H, Hariri S, Wu M -Y. Performance-effective and low complexity task scheduling for heterogeneous computing. IEEE Trans Parallel Distrib Syst, 2002, 13(3): 260–274
Macey B S, Zomaya A Y. A performance evaluation of CP list scheduling heuristics for communication intensive task graphs. In: Parallel Processing Symposium, 1998. 538–541
Ahmad I, Kwok Y K. On parallelizing the multiprocessor scheduling problem. IEEE Trans Parallel Distrib Syst, 1999, 10(4): 414–432
Kwok Y -K, Ahmad I. Efficient scheduling of arbitrary task graphs to multiprocessors using a parallel genetic algorithm. J Parallel Distrib Comput, 1997, 47(1): 58–77
De Falco I, Del Balio R, Tarantino E. An analysis of parallel heuristics for task allocation in multicomputers. Computing: Archiv fuÈr Informatik und Numerik, 1997, 59(3): 259–275
Pramanick I, Kuhl J G. An inherently parallel method for heuristic problem-solving: Part general framework. IEEE Trans Parallel Distrib Syst, 1995, 6(10): 1006–1015
Cormen T H, Leiserson C E, Rivest R L. Introduction to Algorithms. Cambridge: MIT Press, 1990
Culler D E, Singh J P. Parallel Computer Architecture. San Fransisco: Morgan Kaufmann Publishers, 1999
Sinnen O, Sousa L. Exploiting unused time slots in list-scheduling considering communication contention. In: Euro-Par 2001 Parallel Processing, Lecture Notes in Computer Science. Berlin: Springer-Verlag, 2001, 2150: 166–170
Lee B, Hurson A R, Feng T Y. A vertically layered allocation scheme for data flow systems. J Parallel Distrib Comput, 1991, 11: 175–187
Ramamoorthy C V, Chandy K M, Gonzalez M J. Optimal scheduling strategies in a multiprocessor system. IEEE Trans Comput, 1972, 21: 137–146
Gerasoulis A, Yang T. A comparison of clustering heuristics for scheduling DAGs on multiprocessors. J Parallel Distrib Comput, 1992, 16(4): 276–291
Woodside C M, Monforton G G. Fast allocation of processes in distributed and parallel systems. IEEE Trans Parallel Distrib Syst, 1993, 4(2): 164–174
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by the National Natural Science Foundation of China (Grant Nos. 90715029 and 60603053), the Cultivation Fund of the Key Scientific and Technical Innovation Project, Ministry of Edacation of China, and the Key Project of Science & Technology of Hunan Province (Grant No. 2006GK2006)
Rights and permissions
About this article
Cite this article
Tang, X., Li, K. & Padua, D. Communication contention in APN list scheduling algorithm. Sci. China Ser. F-Inf. Sci. 52, 59–69 (2009). https://doi.org/10.1007/s11432-009-0010-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11432-009-0010-3