Abstract
Cosmological studies, in particular those relating to the large scale distribution of galaxies, have to cope with an extraordinary increase in data volume with the current and upcoming sky surveys. These usually involve the estimation of N-point correlation functions of galaxy properties. Due to the fact that the correlation functions are based on histogram construction, they have a high computational cost, which worsens with the ever growing size of the datasets and the standard sample. At the same time, correlation functions exhibit a high sensitivity to the accuracy of the estimation. Therefore, their implementations require maintaining a high accuracy within a reasonable processing time. GPU computing can be adopted to overcome the latter problem, but the standard implementation of the histogram construction on GPU lacks the appropriate accuracy for calculating the cosmological correlation functions. In this work, the bin recycling strategy is implemented and evaluated for the estimation of the Two-Point Angular Correlation Function. At the same time the lack of the appropriate accuracy in the calculation of diverse implementations of histogram construction on GPU is demonstrated. The bin recycling strategy for the Two-Point Angular Correlation Function outperforms other implementations while enabling the processing of a large number of galaxies. As a consequence of this work, an accuracy-aware GPU implementation of the Two-Point Angular Correlation Function is stated and evaluated to assure the correctness of the results.
M. Cárdenas-Montes—The research leading to these results has received funding by the Spanish Ministry of Economy and Competitiveness (MINECO) for funding support through the grants FPA2012-30811, FPA2013-47804-C2-1-R, and “Unidad de Excelencia María de Maeztu”: CIEMAT - FÍSICA DE PARTÍCULAS through the grant MDM-2015-0509.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Mean and standard deviation are obtained from 15 executions for all the numerical experiments where processing time comparisons are made.
References
Fu, L., Semboloni, E., Hoekstra, H., Kilbinger, M., van Waerbeke, L., Tereno, I., Mellier, Y., Heymans, C., Coupon, J., Benabed, K., Benjamin, J., Bertin, E., Dore, O., Hudson, M., Ilbert, O., Maoli, R., Marmo, C., McCracken, H., Menard, B.: Very weak lensing in the CFHTLS wide: cosmology from cosmic shear in the linear regime. Astron. Astrophys. 479(1), 9–25 (2008)
Landy, S.D., Szalay, A.S.: Bias and variance of angular correlation functions. Am. J. Phys. 412, 64–71 (1993)
Cárdenas-Montes, M., Rodríguez-Vázquez, J.J., Vega-Rodríguez, M.A., Sevilla-Noarbe, I., Sánchez-Álvaro, E.: Performance and precision of histogram calculation on GPUs: cosmological analysis as a case study. Comput. Phys. Commun. 185(10), 2558–2565 (2014)
Cárdenas-Montes, M., Rodríguez-Vázquez, J.J., Vega-Rodríguez, M.A.: Bin recycling strategy for improving the histogram precision on GPU. Comput. Phys. Commun. 204, 55–63 (2016)
Cárdenas-Montes, M., Vega-Rodríguez, M.Á., Sevilla, I., Ponce, R., Rodríguez-Vázquez, J.J., Sánchez Álvaro, E.: Concurrent CPU-GPU code optimization: the two-point angular correlation function as case study. In: Bielza, C., Salmerón, A., Alonso-Betanzos, A., Hidalgo, J.I., Martínez, L., Troncoso, A., Corchado, E., Corchado, J.M. (eds.) CAEPIA 2013. LNCS (LNAI), vol. 8109, pp. 209–218. Springer, Heidelberg (2013). doi:10.1007/978-3-642-40643-0_22
Cárdenas-Montes, M., Vega-Rodríguez, M.A., Bonnett, C., Sevilla-Noarbe, I., Ponce, R., Sánchez-Álvaro, E., Rodríguez-Vázquez, J.J.: GPU-based shear-shear correlation calculation. Comput. Phys. Commun. 185(1), 11–18 (2014)
Goldberg, D.: What every computer scientist should know about floating-point arithmetic. ACM Comput. Surv. 23, 5–48 (1991)
The Institute of Electrical, Electronics Engineers Inc.: IEEE standard for floating-point arithmetic. Technical report, Microprocessor Standards Committee of the IEEE Computer Society, New York, USA, August 2008
Whitehead, N., Fit-Florea, A.: Precision and performance: floating point and IEEE 754 compliance of NVIDIA GPUs. Technical report, NVIDIA (2011)
Sanders, J., Kandrot, E.: CUDA by Example: An Introduction to General-Purpose GPU Programming, 1st edn. Addison-Wesley Professional, Salt Lake City (2010)
Acknowledgment
The CFHTLens data is based on observations obtained with MegaPrime/MegaCam, a joint project of CFHT and CEA/DAPNIA, at the Canada-France-Hawaii Telescope (CFHT) which is operated by the National Research Council (NRC) of Canada, the Institut National des Sciences de l’Univers of the Centre National de la Recherche Scientifique (CNRS) of France, and the University of Hawaii. This research used the facilities of the Canadian Astronomy Data Centre operated by the National Research Council of Canada with the support of the Canadian Space Agency. CFHTLenS data processing was made possible thanks to significant computing support from the NSERC Research Tools and Instruments grant program.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Cárdenas-Montes, M., Rodríguez-Vázquez, J.J., Vega-Rodríguez, M.A., Noarbe, I.S., Gómez-Iglesias, A. (2016). Bin Recycling Strategy for an Accuracy-Aware Implementation of Two-Point Angular Correlation Function on GPU. In: Carretero, J., Garcia-Blas, J., Ko, R., Mueller, P., Nakano, K. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2016. Lecture Notes in Computer Science(), vol 10048. Springer, Cham. https://doi.org/10.1007/978-3-319-49583-5_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-49583-5_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49582-8
Online ISBN: 978-3-319-49583-5
eBook Packages: Computer ScienceComputer Science (R0)