Virtual Institute — High Productivity Supercomputing

2nd Wksp on Productivity & Performance (PROPER 2009)

at Euro-Par 2009 Conference, Delft, The Netherlands, 24 August 2009

Extended Deadline: June 12th

The current and future increase of computer performance is driven by raising the number of cores on a single chip and within a supercomputer. As a consequence, applications need to harness much higher degrees of parallelism in order to satisfy their growing demands for computing power. Writing code that runs correctly and efficiently on large numbers of processors and cores is extraordinarily challenging. The increased concurrency levels also place higher demands on the development process and thus require adequate and scalable tool support for debugging and performance analysis. This workshop will serve as a forum for discussing methods and experiences related to scalability and usability of HPC programming tools, including integration with compilers and the overall development environment.

Workshop Topics

  • tools and tool approaches for parallel program development and analysis
  • correctness checking
  • performance measurement and evaluation
  • success stories about optimization or parallel scalability achieved using tools

Emphasis will be put on giving younger researchers a chance to present their work. There will be a student grant for student researchers presenting their work. It will cover the conference fee and possibly a part of the travel expenses depending on demand. Please indicate whether you want to be considered for the student grant.

The workshop will take place on Monday, Aug 24th 2009 in conjunction with the EuroPar 2009 conference in Delft, The Netherlands.

Important Dates

  • June 12th: submission deadline for extended abstracts
  • June 24th: notification of acceptance
  • Aug 17th: full papers due
  • Oct 2nd: final review results
  • Oct 16th: camera ready papers

Workshop Chair

Andreas Knüpfer, phone +49 351 463 38323

Program Committee:

  • Andreas Knüpfer, TU Dresden
  • Jens Doleschal, TU Dresden
  • Michael Gerndt, TU München
  • Karl Fürlinger, University of California at Berkeley
  • Allen Malony, University of Oregon
  • Dieter an Mey, RWTH Aachen
  • Shirley Moore, University of Tennessee
  • Matthias Müller, TU Dresden
  • Martin Schulz, Lawrence Livermore National Lab
  • Felix Wolf, Jülich Supercomputing Centre

Workshop Program

14:30-16:00

  • Tilman Küstner, Josef Weidendorfer, Tobias Weinzierl: Argument Controlled Context Profling
  • Harald Servat, Germán Llort, Judit Giménez, Jesús Labarta: Detailed performance analysis using coarse grain sampling
  • Shajulin Benedict, Michael Gerndt, Ventsislav Petkov, Matthias Brehm, Carla Guillen, Wolfram Hesse: Automatic Performance Analysis of Large Scale Simulations

16:30-18:00

  • David Böhme, Marc-André Hermanns, Markus Geimer, Felix Wolf: Performance Simulation of Non-Blocking Communication in Message-Passing Applications
  • Karl Fürlinger, David Skinner: Capturing and Visualizing Event Flow Graphs of MPI Applications
  • Kathryn Mohror, Karen L. Karavanic: Scalable Event Trace Visualization