Abstract
The problem of 3-Point Correlation Function (3PCF) in astrophysics processes megabytes data with complex calculations, which is an important tool for calculating properties of heterogeneous systems, but its algorithmic complex is a notorious problem. The fast 3PCF Approximation algorithm can improve the efficiency by reduce the precision of result. In this paper, we are going to introduce a design of this algorithm on GPU, which is 13x speedup over a single CPU. Moreover, we will optimize it in the calculation details: converting the 3D arrays to 1D, padding 0s to arrays and shrinking the kernel array. Finally, this algorithm can achieve 27x speedup additional, and 347x speedup over a single CPU.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bentley, J.: Multidimensional binary search trees used for associative searching. Commun. ACM 18(9), 509–517 (1975)
Buck, I.: GPU computing with NVIDIA CUDA. In: ACM SIGGRAPH 2007 Courses, p. 6. ACM (2007)
FFTW: Fftw reference (2003). http://www.fftw.org/fftw2_doc/fftw_3.html
Frigo, M., Johnson, S.G.: The design and implementation of FFTW3. Proc. IEEE 93(2), 216–231 (2005)
Gangui, A., Lucchin, F., Matarrese, S., Mollerach, S.: The three-point correlation function of the cosmic microwave background in inflationary models. arXiv preprint astro-ph/9312033 (1993)
Moore, A., Connolly, A., Genovese, C., Gray, A., Grone, L., Kanidoris II, N., Nichol, R., Schneider, J., Szalay, A., Szapudi, I., et al.: Fast algorithms and efficient statistics: N-point correlation functions. In: Banday, A.J., Zaroubi, S., Bartelmann, M. (eds.) Mining the Sky, pp. 71–82. Springer, Heidelberg (2001)
Moreland, K., Angel, E.: The FFT on a GPU. In: Proceedings of the ACM SIGGRAPH/EUROGRAPHICS Conference on Graphics Hardware, pp. 112–119. Eurographics Association (2003)
Nvidia, C.: CUDA toolkit documentation - cuFFT (2012). http://docs.nvidia.com/cuda/cufft/index.html
Peebles, P.: The Large-Scale Structure of the Universe. Princeton University Press, Princeton (1980)
Sefusatti, E., Scoccimarro, R.: Galaxy bias and halo-occupation numbers from large-scale clustering. Phys. Rev. D 71(6), 063001 (2005)
Yin, L., Yu, C., Sun, J., Liu, X., Xiao, J., Sun, C.: Three-point correlation function parallel algorithm based on MPI. In: 2013 IEEE 10th International Conference on High Performance Computing and Communications and 2013 IEEE International Conference on Embedded and Ubiquitous Computing (HPCC\_EUC), pp. 482–489. IEEE (2013)
Zhang, L., Pen, U.: Fast n-point correlation functions and three-point lensing application. New Astron. 10(7), 569–590 (2005)
Zhang, X., Yu, C.: Fast n-point correlation function approximation with recursive convolution for scalar fields. In: 2011 IEEE Third International Conference on Cloud Computing Technology and Science (CloudCom), pp. 634–639. IEEE (2011)
Acknowledgments
The work is sponsored by the National Natural Science Foundation of China (61303021).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Sun, C., Yang, M., Yu, C., Sun, J. (2015). Fast 3-Point Correlation Function Approximation on GPU. In: Wang, G., Zomaya, A., Martinez, G., Li, K. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2015. Lecture Notes in Computer Science(), vol 9529. Springer, Cham. https://doi.org/10.1007/978-3-319-27122-4_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-27122-4_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27121-7
Online ISBN: 978-3-319-27122-4
eBook Packages: Computer ScienceComputer Science (R0)