• DocumentCode
    1764544
  • Title

    Profiling Support for Runtime Managed Code: Next Generation Performance Monitoring Units

  • Author

    Gibert, Enric ; Martinez, Raul ; Madriles, Carlos ; Codina, Josep M.

  • Author_Institution
    Intel Labs., Intel Corp., Barcelona, Spain
  • Volume
    14
  • Issue
    1
  • fYear
    2015
  • fDate
    Jan.-June 1 2015
  • Firstpage
    62
  • Lastpage
    65
  • Abstract
    Given the increase of runtime managed code environments in desktop, server, and mobile segments, agile, flexible, and accurate performance monitoring capabilities are required in order to perform wise code transformations and optimizations. Common profiling strategies, mainly based on instrumentation and current performance monitoring units (PMUs), are not adequate and new innovative designs are necessary. In this paper, we present the desired characteristics of what we call next generation PMUs and advocate for hardware/software collaborative approaches where hardware implements the profiling hooks and mechanisms and software implements the complex heuristics. We then propose a first design in which the hardware uses a small, yet flexible table to profile specific code regions and the software decides what/when/how to profile. This first design meets all required features and we aim it as the seed for future PMUs extensions to enable novel dynamic code transformations and optimizations.
  • Keywords
    groupware; optimising compilers; software performance evaluation; system monitoring; PMUs; dynamic code optimizations; dynamic code transformations; hardware-software collaborative approaches; instrumentation; next generation performance monitoring units; profiling hooks; profiling support; runtime managed code environments; Hardware; Instruments; Monitoring; Optimization; Phasor measurement units; Runtime; Software; Performance monitoring unit (PMU); just in time (JIT) compiler; profiling; runtime managed code;
  • fLanguage
    English
  • Journal_Title
    Computer Architecture Letters
  • Publisher
    ieee
  • ISSN
    1556-6056
  • Type

    jour

  • DOI
    10.1109/LCA.2014.2321398
  • Filename
    6809167