• DocumentCode
    649577
  • Title

    FPGA-accelerated color edge detection using a Geometric-Algebra-to-Verilog compiler

  • Author

    Stock, Florian ; Koch, Andreas ; Hildenbrand, Dietmar

  • Author_Institution
    Embedded Syst. & Applic. Group, Tech. Univ. Darmstadt, Darmstadt, Germany
  • fYear
    2013
  • fDate
    23-24 Oct. 2013
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    Geometric Algebra (GA) is a branch of mathematics that generalizes complex numbers and quaternions. One of the advantages of the framework is, that it allows intuitive description and manipulation of geometric objects. While even complex operations can be described concisely, the actual evaluation of these GA expressions is extremely compute intensive. However, it has significant fine-grained parallelism, which makes it a profitable target for hardware implementation. In this paper, we present the automatic acceleration of a color edge-detection algorithm from a GA description. Using our Gaalop GA compiler with its Verilog back-end, we can show speed-ups of over 1000x even compared to a recent GA processor ASIC.
  • Keywords
    algebra; edge detection; field programmable gate arrays; geometry; hardware description languages; image colour analysis; program compilers; FPGA-accelerated color edge detection; GA description; GA expressions; Gaalop GA compiler; Verilog back-end; automatic acceleration; complex numbers; complex operations; fine-grained parallelism; geometric objects description; geometric objects manipulation; geometric-algebra-to-Verilog compiler; mathematics; quaternions;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    System on Chip (SoC), 2013 International Symposium on
  • Conference_Location
    Tampere
  • Type

    conf

  • DOI
    10.1109/ISSoC.2013.6675272
  • Filename
    6675272