Parallel Scalability and Efficiency of HEVC Parallelization Approaches

• Published in: IEEE transactions on circuits and systems for video technology Vol. 22; no. 12; pp. 1827 - 1838
• Main Authors: Chi Ching Chi, Alvarez-Mesa, M., Juurlink, B., Clare, G., Henry, F., Pateux, S., Schierl, T.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2012; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bit rate; Circuits; Coding; Computation; Decoding; Encoding; High Efficiency Video Coding (HEVC); Parallel processing; parallel programming; Proposals; Running; Tiles; Video coding; Wave fronts
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2012.2223056

Unlike H.264/advanced video coding, where parallelism was an afterthought, High Efficiency Video Coding currently contains several proposals aimed at making it more parallel-friendly. A performance comparison of the different proposals, however, has not yet been performed. In this paper, we will fill this gap by presenting efficient implementations of the most promising parallelization proposals, namely tiles and wavefront parallel processing (WPP). In addition, we present a novel approach called overlapped wavefront (OWF), which achieves higher performance and efficiency than tiles and WPP. Experiments conducted on a 12-core system running at 3.33 GHz show that our implementations achieve average speedups, for 4k sequences, of 8.7, 9.3, and 10.7 for WPP, tiles, and OWF, respectively.