Accelerating Color Space Conversion Using CUDA-Enabled Graphic Processing Units

Article Preview

Abstract:

Color space conversion (CSC) is an important kernel in the area of image and video processing applications including video compression. CSC is a compute-intensive time-consuming operation that consumes up to 40% of processing time of a highly optimised decoder. Several hardware and software implementations for CSC have been found. Hardware implementations can achieve a higher performance compared with software-only solutions. However, the flexibility of software solutions is desirable for various functional requirements and faster time to market. Multicore processors, especially programmable GPUs, provide an opportunity to increase the performance of CSC by exploiting data parallelism. In this paper, we present a novel approach for efficient implementation of color space conversion. The proposed approach has been implemented and verified using computed unified device architecture (CUDA) on graphics hardware. Our experiments results show that the speedup of up to 17× can been obtained.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

505-509

Citation:

Online since:

July 2013

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] J. Nickolls and W. J. Dally: Micro, IEEE. Vol. 30 (2010), pp.56-69

Google Scholar

[2] R. Weber, A. Gothandaraman, R. J. Hinde, and G. D. Peterson: Parallel and Distributed Systems, IEEE Transactions. Vol. 22 (2011), pp.58-68

DOI: 10.1109/tpds.2010.125

Google Scholar

[3] Dupuis E, Optimizing YUV-RGB Color Space Conversion Using Intel's SIMD Technology (2003), on http://lestourtereaux.free.fr/papers/data/yuvrgb.pdf

Google Scholar

[4] Y. Yang, Y. Peng and Z. Liu: IEEE Transactions on Consumer Electronics, IEEE. Vol. 53 (2007), pp.1490-1493

Google Scholar

[5] A. Shahbahrami, B. Juurlink and S. Vassiliadis: ACM Transactions on Architecture and Code Optimization, Vol. 5 (2008), pp.1-30

Google Scholar

[6] C. Zheng, Y. Zhou, X. Chen and X. Guo: Measuring Technology and Mechatronics Automation (ICMTMA), Third International Conference, Vol. 3 (2011), pp.87-90

Google Scholar

[7] F. Bensaali, A. Amira and S. Chandrasekaran: Electronics, Circuits and Systems, 2006. ICECS '06. 13th IEEE International Conference (2006), pp.164-167

DOI: 10.1109/icecs.2006.379745

Google Scholar

[8] J. Hyeran, X. Yinglong and V. K. Prasanna: Parallel Processing (ICPP), 2010 39th International Conference (2010), pp.61-70

Google Scholar

[9] E. Lindholm, J. Nickolls, S. Oberman and J. Montrym: Micro, IEEE. vol. 28 (2008), pp.39-55

DOI: 10.1109/mm.2008.31

Google Scholar