Skip to main navigation Skip to search Skip to main content

Implementation of area efficient H.264/AVC CAVLC decoder

  • Byung Sik Choi*
  • , Jong Yeol Lee
  • *Corresponding author for this work

Research output: Contribution to conferenceConference paperpeer-review

Abstract

In this paper, we propose the VLSI architecture of H.264/AVC CAVLC Decoder which is able to reduce power consumption by using area-efficient method. In the proposed architecture, we reduce the lookup table area by rearranging the entries of lookup tables. We also save the bus area and processing cycles consumed decoding T1s by decoding T1s value at the final reordering step which is performed in output buffer. We can find overlapped logics between the controller and barrel shifter. To remove the overlapped logics, we combine a controller and a barrel shifter. By using these proposed methods, we can reduce the area and power consumption by about 30% and 15% separately compared with previous works. We design the proposed decoder using Verilog HDL and synthesize it using 0.35μm standard cell library. We verify the proposed architecture by simulation that the designed decoder can run at the frequency of 50Mhz.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Integrated Circuit Design and Technology, ICICDT 2009
Pages135-138
Number of pages4
DOIs
StatePublished - 2009
Event2009 IEEE International Conference on Integrated Circuit Design and Technology, ICICDT 2009 - Austin, TX, United States
Duration: 2009.05.182009.05.20

Publication series

Name2009 IEEE International Conference on Integrated Circuit Design and Technology, ICICDT 2009

Conference

Conference2009 IEEE International Conference on Integrated Circuit Design and Technology, ICICDT 2009
Country/TerritoryUnited States
CityAustin, TX
Period09.05.1809.05.20

Keywords

  • Area reduction
  • CAVLD
  • H.264/AVC
  • Power consumption

Fingerprint

Dive into the research topics of 'Implementation of area efficient H.264/AVC CAVLC decoder'. Together they form a unique fingerprint.

Cite this