DocumentCode :
2688321
Title :
Applying CUDA Architecture to Accelerate Full Search Block Matching Algorithm for High Performance Motion Estimation in Video Encoding
Author :
Monteiro, Eduarda ; Vizzotto, Bruno ; Diniz, Cláudio ; Zatt, Bruno ; Bampi, Sergio
Author_Institution :
Inf. Inst., Fed. Univ. of Rio Grande do Sul (UFRGS), Porto Alegre, Brazil
fYear :
2011
fDate :
26-29 Oct. 2011
Firstpage :
128
Lastpage :
135
Abstract :
This work presents a parallel GPU-based solution for the Motion Estimation (ME) process in a video encoding system. We propose a way to partition the steps of Full Search block matching algorithm in the CUDA architecture. A comparison among the performance achieved by this solution with a theoretical model and two other implementations (sequential and parallel using OpenMP library) is made as well. We obtained a O(n^2/log^2n) speed-up which fits the proposed theoretical model considering different search areas. It represents up to 600x gain compared to the serial implementation, and 66x compared to the parallel OpenMP implementation.
Keywords :
computer graphic equipment; coprocessors; image matching; motion estimation; parallel architectures; video coding; CUDA architecture; OpenMP library; compute unified device architecture; full search block matching algorithm; graphics processing unit; high performance motion estimation; parallel GPU-based solution; video encoding; Accuracy; Algorithm design and analysis; Complexity theory; Computer architecture; Encoding; Graphics processing unit; Motion estimation; CUDA; GPU; H.264/AVC; Motion Estimation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Architecture and High Performance Computing (SBAC-PAD), 2011 23rd International Symposium on
Conference_Location :
Vitoria, Espirito Santo
ISSN :
1550-6533
Print_ISBN :
978-1-4577-2050-5
Type :
conf
DOI :
10.1109/SBAC-PAD.2011.19
Filename :
6106014
Link To Document :
بازگشت