Abstract
Nowadays many computational systems are endowed of multi-cores in the main processor units, and one or more many-core cards. This makes possible the execution of codes on both computational resources concurrently. The challenge in this scenario is to balance correctly both execution paths. When the scenario is simple enough, by-hand optimization can be affordable, otherwise metaheuristic techniques are mandatory. In this work, Differential Evolution algorithm is implemented to optimize a concurrent CPU-GPU code calculating the Two-Point Angular Correlation Function applied to the study of Large-Scale Structure of the Universe. The Two-Point Angular Correlation Function is a computationally intensive function, requiring the calculation of three histograms with different execution times. Therefore, this forces to implement a parameter for describing the percentage of computation in CPU per histogram, and the counterpart in GPU; and to use metaheuristic techniques to fit the appropriate values for these three percentages. As a consequence of the optimization process described in this article, a significant reduction of the execution time is achieved. This proof of concept demonstrates that Evolutionary Algorithms are useful for fairly balancing computational paths in concurrent computing scenarios.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kindratenko, V.V., Myers, A.D., Brunner, R.J.: Implementation of the two-point angular correlation function on a high-performance reconfigurable computer. Sci. Program. 17, 247–259 (2009)
Roeh, D.W., Kindratenko, V.V., Brunner, R.J.: Accelerating cosmological data analysis with graphics processors. In: Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units, GPGPU-2, pp. 1–8. ACM, New York (2009)
Cárdenas-Montes, M., Rodríguez-Vázquez, J.J., Ponce, R., Sevilla, I., Sánchez, E., Colino, N., Vega-Rodríguez, M.A.: New computational developments in cosmology. In: Ibergrid, pp. 101–112 (2012)
Moore, A., Connolly, A., Genovese, C., Gray, A., Grone, L., Kanidoris, N., Nichol, R., Schneider, J., Szalay, A., Szapudi, I., et al.: Fast algorithms and efficient statistics: N-point correlation functions. astroph0012333, 71 (2000)
Eriksen, H.K., Lilje, P.B., Banday, A.J., Górski, K.M.: Estimating n-point correlation functions from pixelized sky maps. The Astrophysical Journal Supplement Series 151(1) (2004)
Frieman, J., Turner, M., Huterer, D.: Dark Energy and the Accelerating Universe (2008)
Landy, S.D., Szalay, A.S.: Bias and variance of angular correlation functions. American Journal of Physics 412, 64–71 (1993)
Storn, R., Price, K.V.: Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces. J. of Global Optimization 11(4), 341–359 (1997)
Price, K.V., Storn, R., Lampinen, J.: Differential Evolution: A practical Approach to Global Optimization. Springer, Berlin (2005)
Mezura-Montes, E., Velázquez-Reyes, J., Coello, C.A.C.: A comparative study of differential evolution variants for global optimization. In: GECCO, pp. 485–492 (2006)
Matsumoto, M., Nishimura, T.: Mersenne twister: A 623-dimensionally equidistributed uniform pseudorandom number generator. ACM Transactions on Modeling and Computer Simulation 8(1), 3–30 (1999)
García, S., Molina, D., Lozano, M., Herrera, F.: A study on the use of non-parametric tests for analyzing the evolutionary algorithms’ behaviour: A case study on the cec’2005 special session on real parameter optimization. J. Heuristics 15(6), 617–644 (2009)
García, S., Fernández, A., Luengo, J., Herrera, F.: A study of statistical techniques and performance measures for genetics-based machine learning: Accuracy and interpretability. Soft Comput. 13(10), 959–977 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cárdenas-Montes, M., Vega-Rodríguez, M.Á., Sevilla, I., Ponce, R., Rodríguez-Vázquez, J.J., Sánchez Álvaro, E. (2013). Concurrent CPU-GPU Code Optimization: The Two-Point Angular Correlation Function as Case Study. In: Bielza, C., et al. Advances in Artificial Intelligence. CAEPIA 2013. Lecture Notes in Computer Science(), vol 8109. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40643-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-642-40643-0_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40642-3
Online ISBN: 978-3-642-40643-0
eBook Packages: Computer ScienceComputer Science (R0)