• DocumentCode
    653349
  • Title

    Analysis Method of Energy for C Source Program and Its Application

  • Author

    Yang Yuechuan ; Zeng Guosun ; Ding Chunling ; Wang Wei

  • Author_Institution
    Dept. of Comput. Sci. & Technol., Tongji Univ., Shanghai, China
  • fYear
    2013
  • fDate
    20-23 Aug. 2013
  • Firstpage
    1397
  • Lastpage
    1402
  • Abstract
    Effective management of energy is the urgent task for high performance computing, but the analysis methods for energy of computer are very lack. This paper presents an analysis method of energy for C source program. Based on the basic operations and structure of C program, we present a classification of atomic operation, and establish an energy database of these atomic operations by means of experiment. Then we propose three kinds of energy calculation method for the sequential statement block, if statement block, for statement block, respectively. After changing the whole C program into a flow analysis tree, we put forward energy prediction algorithm for such a C source program. Finally, some classic algorithms are chosen to test and verify our prediction. The results show that our method has good feasibility and rationality.
  • Keywords
    C language; green computing; power aware computing; C source program; atomic operation classification; effective energy management; energy calculation method; energy database; energy prediction algorithm; flow analysis tree; high performance computing; sequential statement block; Algorithm design and analysis; Arrays; Atomic measurements; Computers; Databases; Energy consumption; Energy measurement; Analysis of energy consumption; Atomic operation; C program structure; C source program; Green computing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Green Computing and Communications (GreenCom), 2013 IEEE and Internet of Things (iThings/CPSCom), IEEE International Conference on and IEEE Cyber, Physical and Social Computing
  • Conference_Location
    Beijing
  • Type

    conf

  • DOI
    10.1109/GreenCom-iThings-CPSCom.2013.244
  • Filename
    6682256