• DocumentCode
    1966075
  • Title

    A Low-Power Associative Processor with the R-th Nearest-Match Hamming-Distance Search Engine Employing Time-Domain Techniques

  • Author

    Bui, Trong Tu ; Shibata, Tadashi

  • Author_Institution
    Fac. of Electron. & Telecommun., Univ. of Sci.-HCM City, Hochiminh City, Vietnam
  • fYear
    2010
  • fDate
    13-15 Jan. 2010
  • Firstpage
    54
  • Lastpage
    57
  • Abstract
    In this paper, a low-power Hamming distance associative processor employing time-domain techniques has been developed focusing on the implementation of an r-th nearest-match location identification function. The architecture not only inherits advantages of analog implementations on power consumption but also improves the accuracy of such implementations. This is because it employs digital technique for distance comparison and delay-time technique for searching for the r-th nearest-match template word. A 64-bit 32-word proof-of-concept chip has been designed and fabricated in a 0.18-¿m CMOS process and has been successfully tested. Power consumption is below 1.8 mW and core size is 0.65 × 0.445 mm2, respectively.
  • Keywords
    CMOS digital integrated circuits; content-addressable storage; search engines; time-domain analysis; CMOS process; R-th nearest-match hamming-distance search engine; content-addressable memory; delay-time technique; digital technique; distance comparison; low-power associative processor; power 1.8 mW; r-th nearest-match location identification function; size 0.18 mum; time domain techniques; CADCAM; Circuits; Cities and towns; Computer aided manufacturing; Delay; Electronic equipment testing; Energy consumption; Hamming distance; Search engines; Time domain analysis; CAM; Hamming distance; ROF; associative processor; time-domain techniques;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Electronic Design, Test and Application, 2010. DELTA '10. Fifth IEEE International Symposium on
  • Conference_Location
    Ho Chi Minh City
  • Print_ISBN
    978-0-7695-3978-2
  • Electronic_ISBN
    978-1-4244-6026-7
  • Type

    conf

  • DOI
    10.1109/DELTA.2010.37
  • Filename
    5438711