Abstract
In this paper, we discuss strategies to parallelize selected deconvolution methods on a multi-GPU system. We provide a comparison of several approaches to split the deconvolution into subtasks while keeping the amount of costly data transfers as low as possible, and propose own implementation of three deconvolution methods which achieves up to 65× speedup over the CPU one. In the experimental part, we analyse how the individual stages of the computation contribute to the overall computation time as well as how the multi-GPU implementation scales in various setups. Finally, we identify bottlenecks of the system.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Amdahl, G.: Validity of the single processor approach to achieving large scale computing capabilities. In: Proceedings of the Spring Joint Computer Conference, April 18-20, pp. 483–485. ACM (1967)
Brigham, E., Morrow, R.: The fast Fourier transform. IEEE Spectrum 4(12), 63–70 (1967)
Castleman, K.R.: Digital Image Processing. Prentice Hall (1996)
D’Amore, L., Marcellino, L., Mele, V., Romano, D.: Deconvolution of 3D Fluorescence Microscopy Images Using Graphics Processing Units. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Waśniewski, J. (eds.) PPAM 2011, Part I. LNCS, vol. 7203, pp. 690–699. Springer, Heidelberg (2012)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society. Series B (Methodological), 1–38 (1977)
Domanski, L., Bednarz, T., Vallotton, P., Taylor, J.: Heterogeneous parallel 3D image deconvolution on a cluster of GPUs and CPUs. In: 19th Int’l Congress on Modelling and Simulation, Perth, Australia (December 2011), http://mssanz.org.au/modsim2011/A8/domanski.pdf (cited August 1, 2013)
Domanski, L., Bednarz, T., Gureyev, T.E., Murray, L., Huang, E., Taylor, J.A.: Applications of Heterogeneous Computing in Computational and Simulation Science. In: 2011 Fourth IEEE International Conference on Utility and Cloud Computing (UCC), pp. 382–389. IEEE (2011)
Domanski, L., Vallotton, P., Wang, D.: Two and three-dimensional image deconvolution on graphics hardware. In: Proceedings of the 18th World IMACS/MODSIM Congress, Cairns, Australia, pp. 13–17 (July 2009)
Frigo, M., Johnson, S.G.: The design and implementation of FFTW3. Proceedings of the IEEE 93(2), 216–231 (2005); Special Issue on Program Generation, Optimization, and Platform Adaptation
Gonzales, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Prentice-Hall (2007)
Karas, P., Svoboda, D.: Convolution of large 3D images on GPU and its decomposition. EURASIP Journal on Advances in Signal Processing 2011(1), 120 (2011)
Karas, P., Svoboda, D.: Algorithms for Efficient Computation of Convolution. In: Design and Architectures for Digital Signal Processing, 1st edn., pp. 179–208. InTech, Rijeka (2013)
Karas, P., Svoboda, D., Zemčík, P.: GPU optimization of convolution for large 3-D real images. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P., Zemčík, P. (eds.) ACIVS 2012. LNCS, vol. 7517, pp. 59–71. Springer, Heidelberg (2012)
Nussbaumer, H.: Fast Fourier transform and convolution algorithms. Springer Series in Information Sciences 2 (1982)
NVIDIA Corporation: CUFFT Library (2012), http://docs.nvidia.com/cuda/pdf/CUDA_CUFFT_Users_Guide.pdf (cited August 1, 2013)
NVIDIA Corporation: NVIDIA Developer Zone (2012), http://developer.nvidia.com/category/zone/cuda-zone (cited August 1, 2013)
Oppenheim, A., Schafer, R., Buck, J., et al.: Discrete-time signal processing, vol. 2. Prentice Hall, Upper Saddle River (1989)
Pawliczek, P., Romanowska-Pawliczek, A., Soltys, Z.: Parallel deconvolution of large 3D images obtained by confocal laser scanning microscopy. Microscopy Research and Technique 73(3), 187–194 (2010)
Quammen, C.W., Feng, D., Taylor II, R.M.: Performance of 3D Deconvolution Algorithms on Multi-Core and Many-Core Architectures. University of North Carolina at Chapel Hill, Dpt. of Computer Science, Tech. Rep. (2009)
Serafini, T., Zanella, R., Zanni, L.: Gradient projection methods for image deblurring and denoising on graphics processors. In: Int. Conf. on Parallel Computing ParCo 2009. Advances in Parallel Computing, vol. 19, pp. 59–66 (2010)
Shepp, L.A., Vardi, Y.: Maximum likelihood reconstruction for emission tomography. IEEE Transactions on Medical Imaging 1(2), 113–122 (1982)
Svoboda, D.: Efficient computation of convolution of huge images. In: Maino, G., Foresti, G.L. (eds.) ICIAP 2011, Part I. LNCS, vol. 6978, pp. 453–462. Springer, Heidelberg (2011)
Trussell, H., Hunt, B.: Image restoration of space variant blurs by sectioned methods. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1978, vol. 3, pp. 196–198. IEEE (1978)
Verveer, P.J.: Computational and optical methods for improving resolution and signal quality in fluorescence microscopy. Ph.D. thesis, Delft TU (1998)
Voort, H., Strasters, K.: Restoration of confocal images for quantitative image analysis. Journal of Microscopy 178(2), 165–181 (1995)
Wendykier, P., Nagy, J.G.: Image processing on modern CPUs and GPUs. Tech. rep., Emory University TR-2008-023 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Karas, P., Kuderjavý, M., Svoboda, D. (2013). Deconvolution of Huge 3-D Images: Parallelization Strategies on a Multi-GPU System. In: Kołodziej, J., Di Martino, B., Talia, D., Xiong, K. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2013. Lecture Notes in Computer Science, vol 8285. Springer, Cham. https://doi.org/10.1007/978-3-319-03859-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-03859-9_24
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-03858-2
Online ISBN: 978-3-319-03859-9
eBook Packages: Computer ScienceComputer Science (R0)