Approximate-SAD Circuit for Power-efficient H.264 Video Encoding under Maintaining Output Quality and Compression Efficiency

We develop a novel SAD circuit for power-efficient H.264 encoding, namely a-SAD. Here, some highest-order MSB’s are approximated to single MSB. Our theoretical estimations show that our proposed design simultaneously improves performance and power of SAD circuit, achieving good power efficiency. We decide that the optimal number of approximated MSB’s is four under 8-bit YUV-420 format, the largest number not to affect video quality and compression-rate in our video experiments. In logic simulations, our a-SAD circuit shows at least 9.3% smaller critical-path delay compared to existing SAD circuits. We compare power dissipation under iso-throughput scenario, where our a-SAD circuit obtains at least 11.6% power saving compared to other designs. We perform same simulations under two-and three-stage pipelined architecture. Here, our a-SAD circuit delivers significant performance (by 13%) and power (by 17% and 15.8% for two and three stages respectively) improvements.

[1]  G. Bjontegaard,et al.  Calculation of Average PSNR Differences between RD-curves , 2001 .

[2]  Iain E. G. Richardson,et al.  The H.264 Advanced Video Compression Standard , 2010 .

[3]  Takashi Ishikawa,et al.  Design methodology of ultra low-power MPEG4 codec core exploiting voltage scaling techniques , 1998, Proceedings 1998 Design and Automation Conference. 35th DAC. (Cat. No.98CH36175).

[4]  Kaushik Roy,et al.  IMPACT: IMPrecise adders for low-power approximate computing , 2011, IEEE/ACM International Symposium on Low Power Electronics and Design.

[5]  Fore June An Introduction to Video Compression in C/C++ - Volume 1 , 2010 .

[6]  John V. McCanny,et al.  A VLSI architecture for variable block size video motion estimation , 2004, IEEE Transactions on Circuits and Systems II: Express Briefs.

[7]  Liang-Gee Chen,et al.  An efficient and simple VLSI tree architecture for motion estimation algorithms , 1993, IEEE Trans. Signal Process..

[8]  Liang-Gee Chen,et al.  Analysis and architecture design of an HDTV720p 30 frames/s H.264/AVC encoder , 2006, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Lara Dolecek,et al.  Underdesigned and Opportunistic Computing in Presence of Hardware Variability , 2013, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[10]  Gary Sullivan,et al.  Recommended Simulation Common Conditions for H.26L Coding Efficiency Experiments on Low Resolution Progressive Scan Source Material , 2001 .

[11]  S. Borkar,et al.  A 320 mV 56 μW 411 GOPS/Watt Ultra-Low Voltage Motion Estimation Accelerator in 65 nm CMOS , 2009, IEEE Journal of Solid-State Circuits.

[12]  Wang Qin,et al.  A High-Performance Low Cost SAD Architecture for Video Coding , 2007, IEEE Transactions on Consumer Electronics.

[13]  Frederic Dufaux,et al.  Motion estimation techniques for digital TV: a review and a new contribution , 1995, Proc. IEEE.

[14]  Timo Hämäläinen,et al.  A High-Performance Sum of Absolute Difference Implementation for Motion Estimation , 2006, IEEE Transactions on Circuits and Systems for Video Technology.