Abstract
In this paper, we study and evaluate fault-tolerant technology for use in the parallel acceleration of evolutionary computation on many-core processors. Specifically, we show running evolutionary computation in parallel on a GPU results in a system that not only performs better as the number of processor cores increases, but is also robust against any physical faults (e.g., stuck-at faults) and transient faults (e.g., faults caused by noise), and makes it less likely that the application program will be interrupted while running. That is, we show that this approach is beneficial for the implementation of systems with sustainability.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
[1] Mühlenbein, H.: Evolution in time and space - the parallel genetic algorithm. In Foundations of Genetic Algorithms, pp. 316–337. Morgan Kaufmann (1991).
[2] Shonkwiler, R.: Parallel genetic algorithm. In Proc. of the 5th International Conference on Genetic Algorithms, pp. 199–205 (1993).
[3] Pham, D., Asano, S., Bolliger, M., Day, M. N., Hofstee, H. P., Johns, C., Kahle, J., Kameyama, A, Keaty, J., Masubuchi, Y., Riley, M., Shippy, D., Stasiak, D., Suzuoki, M., Wang, M., Warnock, J., Weitzel, S., Wendel, D., Yamazaki, T., and Yazawa, K.: The design and implementation of a first-generation CELL processor. In 2005 IEEE International Solid- State Circuits Conference, vol. 1, pp. 184–592 (2005).
[4] Shiota, T., Kawasaki, K., Kawabe, Y., Shibamoto, W., Sato, A., Hashimoto, T., Hayakawa, F., Tago, S., Okano, H., Nakamura, Y., Miyake, H., Suga, A., and Takahashi, H.: A 51.2 gops 1.0 gb/sdma single-chip multi-processor integrating quadruple 8-way vliw processors. In 2005 IEEE International Solid-State Circuits Conference, vol. 1, pp. 194–593 (2005).
[5] Torii, S., et al.: A 600mips 120mw 70ua leakage triple-cpu mobile application processor chip. In the IEEE ISSCC Digest of Technical Papers, pp. 136–137 (2005).
[6] Byun, J.-H., Datta, K., Ravindran, A., Mukherjee, A., and Joshi, B.: Performance analysis of coarse-grained parallel genetic algorithms on the multi-core sun UltraSPARC T1. In SOUTHEASTCON’09. IEEE, pp. 301–306 (2009).
[7] Serrano, R., Tapia, J., Montiel, O., Sep´ulveda, R., and Melin, P.: High performance parallel programming of a GA using multi-core technology. In Soft Computing for Hybrid Intelligent Systems, pp. 307–314 (2008).
[8] Tsutsui, S., and Fujimoto, N.: Solving quadratic assignment problems by genetic algorithms with GPU computation: a case study. In Proceedings of the 2009 ACM/SIGEVO Genetic and Evolutionary Computation Conference, pp. 2523–2530 (2009).
[9] Sato, M., Sato, Y., and Namiki, M.: Proposal of a multi-core processor from the viewpoint of evolutionary computation. In Proceedings of the 2010 IEEE Congress on Evolutionary Computation, CD-ROM (2010).
[10] Sato, Y., Hasegawa, N., and Sato, M.: GPU Acceleration for Sudoku Solution with Genetic Operations. In Proceedings of the 2011 IEEE Congress on Evolutionary Computation, CD-ROM (2011).
[11] Lara, P. K.: Fault Tolerant and Fault Testable Hardware Design. Prentice-Hall International Ltd (1985).
[12] Toy, W. N., and Gallaher, L. E.: Overview and architecture of 3B20D processor. Bell Syst. Tech. J., Vol. 62, No. 1, pt. 2, pp. 181-19 (1983).
[13] Bartlet, F.: The Tandem 16; A “NonStop” operating system. In The Theory and Practice of Reliable System Design (Ed. By D. P. Siewiorek and R. S. Searz), pp. 453-460 (1982).
[14] Siewiorek, D. P., et al.: A case study of C.mmp, Cm and C.Vmp: Part 1 – Experience with fault-tolerance in multiprocessor systems. ibid., pp. 1178-1199 (1978).
Acknowledgments
This research is partly supported by the collaborative research program 2012, Information Initiative Center, Hokkaido University, and a grant from the Institute for Sustainability Research and Education of Hosei University 2012.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer India
About this paper
Cite this paper
Sato, Y. (2013). Parallelization of Genetic Algorithms and Sustainability on Many-core Processors. In: Bansal, J., Singh, P., Deep, K., Pant, M., Nagar, A. (eds) Proceedings of Seventh International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA 2012). Advances in Intelligent Systems and Computing, vol 202. Springer, India. https://doi.org/10.1007/978-81-322-1041-2_15
Download citation
DOI: https://doi.org/10.1007/978-81-322-1041-2_15
Published:
Publisher Name: Springer, India
Print ISBN: 978-81-322-1040-5
Online ISBN: 978-81-322-1041-2
eBook Packages: EngineeringEngineering (R0)