Please use this identifier to cite or link to this item: https://hdl.handle.net/11000/31383

Frame-Based and Subpicture-Based Parallelization Approaches of the HEVC Video Encoder


Thumbnail

View/Open:
 02_applsci-08-00854 (1).pdf

1,3 MB
Adobe PDF
Share:
Title:
Frame-Based and Subpicture-Based Parallelization Approaches of the HEVC Video Encoder
Authors:
Migallon, Hector  
Piñol, Pablo  
López Granado, Otoniel Mario  
Galiano, Vicente  
Perez Malumbres, Manuel  
Editor:
MDPI
Department:
Departamentos de la UMH::Ingeniería de Computadores
Issue Date:
2018-05
URI:
https://hdl.handle.net/11000/31383
Abstract:
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).
Keywords/Subjects:
HEVC
video coding
parallel encoding
shared memory
distributed shared memory
Knowledge area:
CDU: Ciencias aplicadas: Ingeniería. Tecnología
Type of document:
application/pdf
Access rights:
info:eu-repo/semantics/openAccess
DOI:
https://doi.org/10.3390/app8060854
Appears in Collections:
Artículos Ingeniería de computadores



Creative Commons ???jsp.display-item.text9???