A novel parallel pipeline structure of VP9 decoder

Huabiao Qin; Wu Chen; Sijun Yi; Yunfei Tan; Huan Yi

doi:10.1117/12.2304688

10 April 2018 A novel parallel pipeline structure of VP9 decoder

Huabiao Qin, Wu Chen, Sijun Yi, Yunfei Tan, Huan Yi

Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 1061543 (2018) https://doi.org/10.1117/12.2304688
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China

Abstract

To improve the efficiency of VP9 decoder, a novel parallel pipeline structure of VP9 decoder is presented in this paper. According to the decoding workflow, VP9 decoder can be divided into sub-modules which include entropy decoding, inverse quantization, inverse transform, intra prediction, inter prediction, deblocking and pixel adaptive compensation. By analyzing the computing time of each module, hotspot modules are located and the causes of low efficiency of VP9 decoder can be found. Then, a novel pipeline decoder structure is designed by using mixed parallel decoding methods of data division and function division. The experimental results show that this structure can greatly improve the decoding efficiency of VP9.

Citation Download Citation

Huabiao Qin, Wu Chen, Sijun Yi, Yunfei Tan, and Huan Yi "A novel parallel pipeline structure of VP9 decoder", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061543 (10 April 2018); https://doi.org/10.1117/12.2304688

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available