• DocumentCode
    1850103
  • Title

    Memory Optimization Algorithm and Analysis Based on Block Architecture

  • Author

    Ge Hong-mei ; Xu Chao

  • Author_Institution
    Dept. of the Inf. Manage., XuZhou Coll. of Ind. Technol., Xuzhou, China
  • fYear
    2013
  • fDate
    21-23 June 2013
  • Firstpage
    1636
  • Lastpage
    1639
  • Abstract
    In order to solve an important problem of memory in a selected block: a block switching instruction may be used as little as possible to improve the execution efficiency of target code without affecting the correctness of a program, this paper combines Distribution method of Tiantian Liu et al to set up a corresponding mathematical model whose complexity is analyzed, and puts forward a memory optimization algorithm based on block architecture which is analyzed through the concrete example. This algorithm assigns variables without life cycle overlapping to the same storage space, thereby reducing the storage space variables occupied and also reducing some subsequent selected block instructions for life cycle overlapping of variables can allocate storage location of variables. This algorithm obviously reduces the number of the selected block instructions, realizes the effects of memory optimization and expects the references on all levels.
  • Keywords
    mathematical analysis; memory architecture; storage management; block architecture; block instructions; block switching instruction; distribution method; mathematical model; memory optimization algorithm; memory optimization analysis; storage space variables; target code; variable storage location allocation; Aerospace electronics; Algorithm design and analysis; Computer architecture; Concrete; Embedded systems; Optimization; Resource management; algorithm analysis; block architecture; memory optimization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational and Information Sciences (ICCIS), 2013 Fifth International Conference on
  • Conference_Location
    Shiyang
  • Type

    conf

  • DOI
    10.1109/ICCIS.2013.428
  • Filename
    6643346