• DocumentCode
    2230570
  • Title

    Co-processor architecture for MPEG-4 main profile visual compositing

  • Author

    Berekovic, M. ; Pirsch, P. ; Selinger, T. ; Wels, K.-I. ; Miro, C. ; Lafage, A. ; Heer, C. ; Ghigo, G.

  • Author_Institution
    Lab. fur Informationstechnol., Hannover Univ., Germany
  • Volume
    2
  • fYear
    2000
  • fDate
    2000
  • Firstpage
    180
  • Abstract
    The TANGRAM VLSI co-processor is intended to assist existing MPEG-4 video-decoders to perform the computation intensive final step of MPEG-4 video decoding: compositing of scenes at the display. TANGRAM consists of a RISC control processor and multiple powerful arithmetic units that perform rendering calculations directly in hardware. This hybrid architecture enables adaptation to changes in algorithms or support for different video-formats in software. Communication to a host CPU and video decoding hardware is done via the very common PI-bus on-chip interface. TANGRAM directly interfaces with the ITU-R601/656 digital video output. VHDL implementation and synthesis for a 0.35 μ standard-cell library provide an estimate of 100 MHz achievable clock-frequency (worst-case), 52 mm2 overall area and 1 Watt power dissipation. TANGRAM has sufficient performance for rendering of MPEG-4 Main Profile@Layer3 scenes (CCIR)
  • Keywords
    VLSI; coprocessors; decoding; digital arithmetic; hardware description languages; reduced instruction set computing; video signal processing; 0.35 micron; 1 W; 100 MHz; ITU-R601/656 digital video output; MPEG-4; Main Profile@Layer3 scenes; PI-bus on-chip interface; RISC control processor; TANGRAM VLSI co-processor; VHDL implementation; achievable clock-frequency; main profile visual compositing; multiple powerful arithmetic units; power dissipation; rendering calculations; scene compositing; standard-cell library; video decoding; Computer architecture; Computer displays; Coprocessors; Decoding; Hardware; Layout; MPEG 4 Standard; Reduced instruction set computing; Rendering (computer graphics); Very large scale integration;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on
  • Conference_Location
    Geneva
  • Print_ISBN
    0-7803-5482-6
  • Type

    conf

  • DOI
    10.1109/ISCAS.2000.856288
  • Filename
    856288