• DocumentCode
    2269118
  • Title

    200 MHz 0.8 μm CMOS gradient vector processor for real-time execution

  • Author

    Margala, Martin ; Durdle, Nelson G.

  • Author_Institution
    Dept. of Electr. & Comput. Eng., Alberta Univ., Edmonton, Alta., Canada
  • Volume
    1
  • fYear
    1998
  • fDate
    24-28 May 1998
  • Firstpage
    261
  • Abstract
    This paper describes a gradient vector processor which forms an important part of a shading processor being developed for a high resolution high performance real-time general purpose volume imaging system. The proposed architecture overcomes current image resolution and frame-rate limitations through the use of custom high-speed processors. The gradient vector processor evaluates three arithmetic operations: a square and add operation, square-root, and three division operations. Fully pipelined operation produces a vector every 5 ns or with a 200 MHz frequency at Vdd=3 V and with an accuracy of ±0.78%. The algorithms and implementation in silicon are described in detail
  • Keywords
    CMOS digital integrated circuits; digital arithmetic; digital signal processing chips; image resolution; pipeline processing; real-time systems; vector processor systems; 0.8 micron; 200 MHz; 3 V; 5 ns; CMOS; Si; accuracy; algorithms; architecture; arithmetic operations; custom high-speed processors; division operations; frame-rate limitation; frequency; general purpose volume imaging system; gradient vector processor; high performance system; high resolution system; image resolution; pipelined operation; real-time execution; real-time system; shading processor; square and add operation; square-root; Arithmetic; CMOS process; Computer architecture; Computer graphics; Geophysics computing; High-resolution imaging; Image reconstruction; Image resolution; Real time systems; Vector processors;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Electrical and Computer Engineering, 1998. IEEE Canadian Conference on
  • Conference_Location
    Waterloo, Ont.
  • ISSN
    0840-7789
  • Print_ISBN
    0-7803-4314-X
  • Type

    conf

  • DOI
    10.1109/CCECE.1998.682732
  • Filename
    682732