Multiview encoder parallelized fast search realization on NVIDIA CUDA

Chih Te Lu*, Hsueh-Ming Hang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

NVIDIA announced a powerful GPU architecture called Compute Unified Device Architecture (CUDA) in 2007, which is able to provide massive data parallelism under the SIMD architecture constraint. We use NVIDIA GTX-280 GPU system, which has 240 computing cores, as the platform to implement a very complicated video coding scheme, the Multiview Video Coding (MVC) scheme. MVC is an extension of H.264/MPEG-4 Part 10 AVC. It is an efficient video compression scheme; however, its computational compexity is very high. Two of its most time-consuming components are motion estimation (ME) and disparity estimation (DE). In this thesis, we propose a fast search algorithm, called multithreaded one-dimensional search (MODS). It can be used to do both the ME and the DE operations. We implement the integer-pel ME and DE processes with MODS on the GTX-280 platform. The speedup ratio can be 89 times faster than the CPU only configuration. Even when the fast search algorithm of the original JMVC is turned on, the MODS version on CUDA can still be 20 times faster.

Original languageEnglish
Title of host publication2011 IEEE Visual Communications and Image Processing, VCIP 2011
DOIs
StatePublished - 1 Dec 2011
Event2011 IEEE Visual Communications and Image Processing, VCIP 2011 - Tainan, Taiwan
Duration: 6 Nov 20119 Nov 2011

Publication series

Name2011 IEEE Visual Communications and Image Processing, VCIP 2011

Conference

Conference2011 IEEE Visual Communications and Image Processing, VCIP 2011
CountryTaiwan
CityTainan
Period6/11/119/11/11

Keywords

  • CUDA
  • disparity estimation
  • fast search algorithm
  • GPU
  • H.264/AVC
  • motion estimation
  • Multi-core
  • Multiview video coding (MVC)
  • parallel

Fingerprint Dive into the research topics of 'Multiview encoder parallelized fast search realization on NVIDIA CUDA'. Together they form a unique fingerprint.

  • Cite this

    Lu, C. T., & Hang, H-M. (2011). Multiview encoder parallelized fast search realization on NVIDIA CUDA. In 2011 IEEE Visual Communications and Image Processing, VCIP 2011 [6116010] (2011 IEEE Visual Communications and Image Processing, VCIP 2011). https://doi.org/10.1109/VCIP.2011.6116010