Scalable Parallel Motion Estimation on Muti-GPU System

Abstract:

With NVIDIA’s parallel computing architecture CUDA, using GPU to speed up compute-intensive applications has become a research focus in recent years. In this paper, we proposed a scalable method for multi-GPU system to accelerate motion estimation algorithm, which is the most time consuming process in video encoding. Based on the analysis of data dependency and multi-GPU architecture, a parallel computing model and a communication model are designed. We tested our parallel algorithm and analyzed the performance with 10 standard video sequences in different resolutions using 4 NVIDIA GTX460 GPUs, and calculated the overall speedup. Our results show that a speedup of 36.1 times using 1 GPU and more than 120 times for 4 GPUs on 1920x1080 sequences. Further, our parallel algorithm demonstrated the potential of nearly linear speedup according to the number of GPUs in the system.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 3708-3714
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.3708
• Online since: August 2013
• Authors: Dong Chen, Hua You Su, Wen Mei, Li Xuan Wang, Chun Yuan Zhang
• Keywords: Full Search, Motion Estimation, Multi-GPU, Scalable

References

[1] Yu-Cheng Lin, Pei-Lun Li, Chin-Hsiang Chang, Chi-Ling Wu, You-Ming Tsao, and Shao-Yi Chien, Multi-Pass algorithm of motion estimation in video encoding for generic GPU, Proc. IEEE Symp. Circuits and Systems. Proceedings. 21-24 May 2006, pp.4451-4454.

DOI: 10.1109/iscas.2006.1693617

[2] Wei-Nien Chen and Hsueh-Ming Hang, H. 264/AVC motion estimation implementation on compute unified device architecture (CUDA), IEEE International Conference on Multimedia and Expo(ICME08), June 23 2008-April 26 2008 , pp.697-700.

DOI: 10.1109/icme.2008.4607530

[3] Bart Pieters, Charles F. Hollemeersch, Peter Lambert, and Rik Van de Walle, Motion estimation for H. 264/AVC on multiple GPUs using NVIDIA CUDA, Applications of Digital Image Processing XXXII, August 2-5 2009, Vol. 7743 77430X-2.

DOI: 10.1117/12.825995

[4] Gan Xinbiao, Shen Li, and Wang Zhiying, Parallel full search algorithm for motion estimation using CUDA, Journal of Computer-Aided Design and Computer Graphics, vol. 22, Mar. 2010, pp.457-460.

[5] Youngsub Ko, Youngmin Yi, and Soonhoi Ha, An efficient parallel motion estimation algorithm and X264 parallelization in CUDA, Design and Architectures for Signal and Image Processing(DASIP), 2-4 Nov. 2011, pp.1-8.

DOI: 10.1109/dasip.2011.6136860

[6] M.C. Kung, Oscar C. Au, P.H.W. Wong, Chun Hung Liu, Block based parallel motion estimation using programmable graphics hardware, International Conference on Audio, Language and Image Processing (ICALIP 08), 7-9 July 2008. pp.599-603.

DOI: 10.1109/icalip.2008.4590176

[7] Ngai-Man Cheung, Xiaopeng Fan, Oscar C. Au, Man-Cheung Kung, Video coding on multicore graphics processors, Signal Processing Magazine , vol. 27, 2010, pp.79-89.

DOI: 10.1109/msp.2009.935416

[8] Lee S, Kim JM, Chae S, New motion estimation using low-resolution quantization for MPEG2 video encoding, IEEE Workshop on VLSI Signal Processing, 20 Oct (1996).

DOI: 10.1109/vlsisp.1996.558375