A mean field model of work stealing in large-scale systems

Performance Evaluation Review

Volumn 38, Issue 1 SPEC. ISSUE, 2010, Pages 13-24

  Gast, Nicolas ^a   Gaujal, Bruno ^b  

^a UNIV GRENOBLE ALPES   (France)

^b INRIA   (France)

Author keywords

Grid computing; Load balancing; Mean field

Indexed keywords

AVERAGE RESPONSE TIME; COMPUTATIONAL GRIDS; GENERIC MODELS; HETEROGENEOUS SYSTEMS; HOMOGENEOUS PROCESSORS; JOB ALLOCATION; KEY ISSUES; MARKOVIAN MODEL; MEAN FIELD; MEAN FIELD MODELS; PERFORMANCE EVALUATION; PERFORMANCE FUNCTIONS;

COMPUTER SYSTEMS; GRID COMPUTING; MARKOV PROCESSES; MEAN FIELD THEORY; NETWORK MANAGEMENT; ORDINARY DIFFERENTIAL EQUATIONS; STATISTICAL MECHANICS;

PARALLEL ARCHITECTURES;

EID: 77954912766     PISSN: 01635999     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/1811099.1811042     Document Type: Conference Paper

References (22)

1. Grid 5000, a large scale nation wide infrastructure for grid research. https://www.grid5000.fr/.
2. J. Anselmi and B. Gaujal. Performance evaluation of a work stealing algorithm for streaming applications. In 13th Int. Conf. On Principles Of DIstributed Systems (OPODIS), Nîmes, 2009.
3. F. Baccelli and P. Bremaud. Elements of queueing theory. Springer-Verlag, 2003.
4. M. Benaim. Recursive algorithms, urn processes and chaining number of chain recurrent sets. Ergodic Theory and Dynamical Systems, 18(01):53-87, 1998.
5. M. Bender and M. Rabib. Online scheduling of parallel programs on heterogeneous systems with applications to cilk. Theory of Computing Systems, 35:289-304, 2002. Special issue on SPA00.
6. P. Berenbrink, T. Friedetzky, and L. Goldberg. The natural work-stealing algorithm is stable. SIAM J. Comput., 32(5):1260-1279, 2003.
7. J. Bernard, J-L. Roch, and D. Traore. Processor-oblivious parallel stream computations. In 16th Euromicro Int. Conf. on Parallel, Distributed and network-based Processing, Toulouse, 2008.
8. S. Ethier and T. Kurtz. Markov processes: Characterization and convergence. Wiley, 1986.
9. M. Frigo, C. Leiserson, and K. Randall. The implementation of the cilk-5 multithreaded language. In ACM SIGPLAN'98 Conf. on Programming Language Design and Implementation, volume 33, pages 212-223, Montreal, 1998.
10. T. Gautier, X. Besseron, and L. Pigeon. Kaapi: A thread scheduling runtime system for data flow computations on cluster of multi-processors. In Proc. of the 2007 int. workshop on Parallel symbolic computation, PASCO'07, pages 15-23, N.Y., 2007.
11. O. Kallenberg. Foundations of modern probability. Springer Verlag, 2002.
12. A. Kukanov and M. Voss. The foundations for scalable multi-core software in intel threading building blocks. Intel Technology Journal, 11(4):309-322, 2007.
13. T. Kurtz. Approximation of population processes. Society for Industrial Mathematics, 1981.
14. M. Mitzenmacher. Analyses of load stealing models based in differential equations. In 10th ACM Symposium on Parallel Algorithms and Architectures (SPAA), pages 212-221, 1998.
15. A. Müller and D. Stoyan. Comparison methods for stochastic models and risks. Series in Probability and Statistics. Wiley, 2002.
16. M. Norman. A central limit theorem for Markov processes that move by small steps. The Annals of Probability, 2(6):1065-1074, 1974.
17. J.-N. Quintin and F. Wagner. Hierarchical work stealing. Technical Report 7077, INRIA, 2009.
18. M. Squillante and R. Nelson. Analysis of task migration in shared-memory multiprocessor scheduling. SIGMETRICS Perf. Eval. Rev., 19(1):143-155, 1991.
19. M. Tchiboukdjian, D. Trystram, J.-L. Roch, and J. Bernard. List Scheduling: The Price of Distribution. Research Report 7208, INRIA, 2010.
20. H. Tembine, J.-Y. Le Boudec, R. El-Azouzi, and E. Altman. Mean Field Asymptotic of Markov Decision Evolutionary Games and Teams. GameNets, 2009.
21. R. Van Nieuwpoort, T. Kielmann, and H. Bal. Efficient load balancing for wide-area divide-and-conquer applications. ACM SIGPLAN, 36(7):34-43, 2001.
22. R. van Nieuwpoort, J. Maassen, R. Hofman, T. Kielmann, and H. Bal. Satin: Simple and efficient java-based grid programming. In AGridM Workshop on Adaptive Grid Middleware, New Orleans, 2003.