menu ☰
menu ˟

Applied Sciences, Vol. 8, Pages 854: Frame-Based and Subpicture-Based Parallelization Approaches of the HEVC Video Encoder

23 May 2018

Applied Sciences, Vol. 8, Pages 854: Frame-Based and Subpicture-Based Parallelization Approaches of the HEVC Video Encoder

Applied Sciences doi: 10.3390/app8060854

Authors:
Héctor Migallón
Pablo Piñol
Otoniel López-Granado
Vicente Galiano
Manuel P. Malumbres

The most recent video coding standard, High Efficiency Video Coding (HEVC), is able to significantly improve the compression performance at the expense of a huge computational complexity increase with respect to its predecessor, H.264/AVC. Parallel versions of the HEVC encoder may help to reduce the overall encoding time in order to make it more suitable for practical applications. In this work, we study two parallelization strategies. One of them follows a coarse-grain approach, where parallelization is based on frames, and the other one follows a fine-grain approach, where parallelization is performed at subpicture level. Two different frame-based approaches have been developed. The first one only uses MPI and the second one is a hybrid MPI/OpenMP algorithm. An exhaustive experimental test was carried out to study the performance of both approaches in order to find out the best setup in terms of parallel efficiency and coding performance. Both frame-based and subpicture-based approaches are compared under the same hardware platform. Although subpicture-based schemes provide an excellent performance with high-resolution video sequences, scalability is limited by resolution, and the coding performance worsens by increasing the number of processes. Conversely, the proposed frame-based approaches provide the best results with respect to both parallel performance (increasing scalability) and coding performance (not degrading the rate/distortion behavior).

Click here to view the full article which appeared in Applied Sciences