Highly parallel mode decision method for HEVC

Jun Zhang, Feng Dai, Yike Ma, Yongdong Zhang

Abstract: High Efficiency Video Coding (HEVC) standard achieves double compression efficiency compared to H.264/AVC with the adoption of more flexible coding structure and advanced coding tools. On the other hand, the coding mode space is too large and it's very time consuming for an HEVC encoder to search for the best coding mode. With the development of multi-core or many-core computing architecture, parallelizing HEVC encoding on such platforms is an efficient approach to fulfill the high computational requirement. In this paper, we exploit the potential parallelism in HEVC mode decision (MD) process and propose a highly parallel MD method which works in a motion estimation region (MER). Specifically, we analyze and remove data dependencies that hinder parallel MD, including motion estimation (ME) dependencies and entropy coding dependencies, and then the MD computation for different blocks within the same MER can be computed concurrently. Experimental results show that our proposed parallel MD method gets an overall speed up of more than 14x with negligible quality loss (1.79% bit rate increasing), compared with the non-parallel baseline.