• DocumentCode
    3053674
  • Title

    Performing Advanced Bit Manipulations Efficiently in General-Purpose Processors

  • Author

    Hilewitz, Yedidya ; Lee, Ruby B.

  • Author_Institution
    Princeton Univ., Princeton
  • fYear
    2007
  • fDate
    25-27 June 2007
  • Firstpage
    251
  • Lastpage
    260
  • Abstract
    This paper describes a new basis for the implementation of a shifter functional unit. We present a design based on the inverse butterfly and butterfly datapath circuits that performs the standard shift and rotate operations, as well as more advanced extract, deposit and mix operations found in some processors. Additionally, it also supports important new classes of even more advanced bit manipulation instructions recently proposed: these include arbitrary bit permutations, bit scatter and bit gather instructions. The new functional unit´s datapath is comparable in latency to that of the classic barrel shifter. It replaces two existing functional units-shifter and mix-with a much more powerful one.
  • Keywords
    logic design; microprocessor chips; shift registers; arbitrary bit permutations; bit gather instructions; bit manipulation instructions; bit scatter instructions; butterfly datapath circuits; general-purpose processors; inverse butterfly; shifter functional unit; Algorithm design and analysis; Biometrics; Circuits; Cryptography; Delay; Digital arithmetic; Floating-point arithmetic; Microprocessors; Proposals; Scattering; arithmetic; bit; manipulations; permutations; processor; rotations; shifter;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Arithmetic, 2007. ARITH '07. 18th IEEE Symposium on
  • Conference_Location
    Montepellier
  • ISSN
    1063-6889
  • Print_ISBN
    0-7695-2854-6
  • Type

    conf

  • DOI
    10.1109/ARITH.2007.27
  • Filename
    4272872