1 / 8

Prophesy: Performance Analysis & Modeling of Parallel & Distributed Applications

Prophesy: Performance Analysis & Modeling of Parallel & Distributed Applications. Valerie Taylor Texas A&M University Xingfu Wu, Joseph Paris Northwestern University Rick Stevens, Ivan Judson, Mark Hereld Argonne National Laboratory.

mstier
Télécharger la présentation

Prophesy: Performance Analysis & Modeling of Parallel & Distributed Applications

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Prophesy: Performance Analysis & Modeling of Parallel & Distributed Applications Valerie Taylor Texas A&M University Xingfu Wu, Joseph Paris Northwestern University Rick Stevens, Ivan Judson, Mark Hereld Argonne National Laboratory SPONSORS: National Science Foundation, National Aeronautics and Space Administration

  2. Problem Statement • Given: • Performance models and analyses are critical • Requires significant development time • Distributed systems are complex • Some applications require distributed systems • Goal • Efficient execution of distributed applications • Proposed Solution • Automate as much as possible • Community involvement http://prophesy.mcs.anl.gov

  3. Prophesy System PROPHESY GUI Profiling & Instrument. Template Database Model Builder Performance Database Actual Execution Symbolic Predictor Systems Database DATA ANALYSIS DATA COLLECTION DATABASES http://prophesy.mcs.anl.gov

  4. Automated Instrumentation • In-line data collection • Instrument at the level of basic loops • Allow for user-specified instrumentation Profiling & Instrument. Execution Manager T=E * f; INSTRUMENTATION CODE for (I=1; I<N; I++){ V(I) = A(I) * C(I); B(I) = A(2I + 4); } INSTRUMENTATION CODE Actual Execution T=E * f; for (I=1; I<N; I++){ V(I) = A(I) * C(I); B(I) = A(2I + 4); } http://prophesy.mcs.anl.gov

  5. Databases • Hierarchical organization • Organized into 4 areas: • Application • Executable • Run • Performance Statistics Template Database Performance Database Systems Database http://prophesy.mcs.anl.gov

  6. Prophesy Database Application Performance Application Executable Run Modules Inputs Module_Info Function Performance Systems Compilers Functions Model Template Basic Unit Performance Function_Info Resource Connection Control Flow Data Structure Performance Model_Info Library http://prophesy.mcs.anl.gov

  7. Automated Modeling Techniques • Utilize information in the template and system databases • Currently include three techniques • Curve fitting • Parameterization • Composition using coupling values http://prophesy.mcs.anl.gov

  8. Modeling Example http://prophesy.mcs.anl.gov

More Related