• DocumentCode
    3275002
  • Title

    The Backstroke framework for source level reverse computation applied to parallel discrete event simulation

  • Author

    Vulov, George ; Hou, Cong ; Vuduc, Richard ; Fujimoto, Richard ; Quinlan, Daniel ; Jefferson, David

  • Author_Institution
    Georgia Inst. of Technol., Atlanta, GA, USA
  • fYear
    2011
  • fDate
    11-14 Dec. 2011
  • Firstpage
    2960
  • Lastpage
    2974
  • Abstract
    We introduce Backstroke, a new open source framework for the automatic generation of reverse code for functions written in C++. Backstroke enables reverse computation for optimistic parallel discrete event simulations. It is built using the ROSE open-source compiler infrastructure, and handles complex C++ features including pointers and pointer types, arrays, function and method calls, class types, inheritance, polymorphism, virtual functions, abstract classes, templated classes and containers. Backstroke also introduces new program inversion techniques based on advanced compiler analysis tools built into ROSE. We explore and illustrate some of the complex language and semantic issues that arise in generating correct reverse code for C++ functions.
  • Keywords
    C++ language; discrete event simulation; parallel processing; program compilers; C++ features; ROSE open-source compiler infrastructure; abstract classes; advanced compiler analysis tools; arrays; automatic generation; backstroke framework; class types; containers; inheritance; method calls; open source framework; parallel discrete event simulations; pointer types; polymorphism; program inversion; reverse code; source level reverse computation; templated classes; virtual functions; Computational modeling; Debugging; Discrete event simulation; Equations; Image restoration; Mathematical model; Syntactics;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Simulation Conference (WSC), Proceedings of the 2011 Winter
  • Conference_Location
    Phoenix, AZ
  • ISSN
    0891-7736
  • Print_ISBN
    978-1-4577-2108-3
  • Electronic_ISBN
    0891-7736
  • Type

    conf

  • DOI
    10.1109/WSC.2011.6147998
  • Filename
    6147998