• DocumentCode
    248136
  • Title

    VLSI architecture of HEVC intra prediction for 8K UHDTV applications

  • Author

    Jianbin Zhou ; Dajiang Zhou ; Heming Sun ; Goto, S.

  • Author_Institution
    Grad. Sch. of Inf., Production & Syst., Waseda Univ., Kitakyushu, Japan
  • fYear
    2014
  • fDate
    27-30 Oct. 2014
  • Firstpage
    1273
  • Lastpage
    1277
  • Abstract
    This paper presents an efficient VLSI architecture of intra prediction for 8K×4K HEVC decoder. It supports all 35 intra prediction modes and prediction sizes ranging from 4×4 to 64×64. This works proposed a Cyclic SRAM Banks based Parallel Reference Sample Fetching (CSB-PRSF), which guarantees enough reference samples for prediction and reduces the number of registers used for storing reference samples. To guarantee high throughput, 16 pixels are predicted by 4×4 Block Based Pipelining, and dependency between neighboring blocks is eliminated by Hybrid Data Forwarding and Block Reordering. This architecture is synthesized using 90nm technology and the maximum working frequency is 469 MHz, with 72.1K gates area. Running at 397MHz, the architecture can support 4320p@120fps HEVC intra decoding, with full modes and full sizes.
  • Keywords
    SRAM chips; VLSI; high definition television; image sampling; prediction theory; video coding; 8K UHDTV application; CSB-PRSF; HEVC decoder; HEVC intradecoding; HEVC intraprediction; VLSI architecture; block based pipelining; block reordering; cyclic SRAM bank; frequency 469 MHz; high efficiency video coding; hybrid data forwarding; parallel reference sample fetching; size 90 nm; static random access memory; ultrahigh-definition television; very large scale integration; Computer architecture; Decoding; Filtering; Random access memory; Registers; Throughput; Very large scale integration; 8K UDTV; HEVC decoder; VLSI architecture; intra prediction;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing (ICIP), 2014 IEEE International Conference on
  • Conference_Location
    Paris
  • Type

    conf

  • DOI
    10.1109/ICIP.2014.7025254
  • Filename
    7025254