Virtual Institute – High Productivity Supercomputing

5th Wksp on Productivity & Performance (PROPER 2012)

Date

August 28, 2012

Location

in conjunction with
Euro-Par 2012 Conference
Rhodes Island, Greece

Workshop Proceedings

Euro-Par 2012: Parallel Processing Workshops (BDMC, CGWS, HeteroPar, HiBB, OMHI, Paraphrase, PROPER, Resilience, UCHPC, VHPC), LNCS 7640

Online version

Overview

Driven by current trends in microprocessor design, the number of processor cores available on modern supercomputers grows rapidly from generation to generation while the amount of memory per core will be degrading. To keep pace, applications need to harness much higher degrees of parallelism while ensuring efficient use of the underlying computing resources.

Writing code that runs correctly and efficiently on large numbers of processors and cores is extraordinarily challenging. The increased concurrency levels place higher demands on the application development process and thus require adequate tool support for debugging and performance analysis. The PROPER workshop will serve as a forum to present novel work on scalable methods and tools for high-performance computing. The workshop covers parallel program development and analysis, debugging, correctness checking, and performance measurement and evaluation. Further topics include the integration of tools with compilers and the overall development environment, as well as success stories reporting application performance, scalability, reliability, or productivity improvements that have been achieved using tools.

The workshop is supported by the Virtual Institute - High Productivity Supercomputing (VI-HPS), an initiative to promote the development and integration of HPC programming tools.

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

 

Paper Submission

All submissions will undergo a review by at least three reviewers. We welcome submissions of full papers not exceeding 10 pages in Springer LNCS format. Please send your submissions via EasyChair. See Instructions for Authors for more details.

Important Dates

 

  • June 4th June 11th: submission deadline extended for full papers (submission remains open till Friday 15 June 2012; abstract submission requested by Monday 11 June)
  • July 10th: notification of acceptance
  • July 20th: camera ready papers due
  • July 30th: early registration deadline
  • August 28th: day of workshop
  • September 30th: final paper versions due for electronic proceedings

 

Instructions for authors

Papers are limited to 10 pages (purchasing additional pages is not possible, main font size 11 points) and should be applied in LaTeX source form (pdf and latex files should be handed in as zip-file). All accepted papers will be included in the conference proceedings (electronic proceedings only), published by Springer in the LNCS series. Authors of accepted papers will be required to sign a Springer copyright form. One author may sign on behalf of all of the authors of a particular paper. Put "Euro-Par 2012: Parallel Processing Workshops" as "Title of the book or Conference name". At least one author of an accepted paper must register for and attend the workshop for inclusion in the proceedings.

 

  • Springer's authors guidelines: here
  • Download Latex LNCS: zip
  • Springer copyright form: pdf
  • Submission of papers: via EasyChair

 

Details instructions

 

  • all the files necessary to build the file need to be included - including all libraries
  • delete all temporary files such as *.aux, *.bbl and *.log
  • figures need to be in a separate directory (case sensitive), eps being preferred
  • the main.tex file should explicitly specify the coding system (\usepackage[latin1]{inputenc}, for instance), so that it can be compiled on any operating system

 

Filenames

 

  • package: .zip
  • pdf: "original.pdf" (NOT main.pdf) to enable comparing compiled to posted output
  • paper source in a single file: main.tex
  • bibliography in a single file: main.bib
  • copyright form: _copyrightform.pdf

 

Program Committee:

 

  • Jean-Thomas Acquaviva, Exascale Computing Research
  • Dieter an Mey, RWTH Aachen
  • Patrick Carribault, CEA
  • Jens Doleschal, TU Dresden
  • Karl Fürlinger, LMU München
  • Michael Gerndt, TU München
  • Andreas Knüpfer, TU Dresden
  • Bettina Krammer, Université de Versailles St-Quentin-en-Yvelines (Chair)
  • Allen Malony, University of Oregon
  • Matthias Müller, TU Dresden
  • Shirley Moore, University of Texas at El Paso
  • Marc Pérache, CEA
  • Martin Schulz, Lawrence Livermore National Lab
  • Jan Treibig, RRZE, Friedrich-Alexander-Universität Erlangen-Nürnberg
  • Felix Wolf, German Research School for Simulation Sciences

 

Workshop Program

 

Session 1, 10:00-11:00: Invited Talk, Session Chair: Bettina Krammer

 

  • Invited Presentation: Performance engineering: From numbers to insight, Georg Hager (pdf)

 

Session 2, 11:30-13:00: Instrumentation Techniques, Session Chair: Dieter an Mey

 

  • Runtime function instrumentation with EZTrace, Charles Aulagnon, Damien Martin-Guillerez, François Rué and François Trahay (pdf)
  • Compiler Help for Binary Manipulation Tools, Tugrul Ince and Jeffrey K. Hollingsworth (pdf)
  • On the Instrumentation of OpenMP and OmpSs Tasking Constructs, Harald Servat, Xavier Teruel, Germán Llort, Alejandro Duran, Judit Giménez, Xavier Martorell, Eduard Ayguadé and Jesús Labarta (pdf)

 

Session 3, 14:30-16:00: Performance Analysis Tools and Practices, Session Chair: Bettina Krammer

 

  • Strategies for Real-Time Event Reduction, Michael Wagner and Wolfgang E. Nagel (pdf)
  • A Scalable InfiniBand Network-Topology-Aware Performance Analysis Tool for MPI, Hari Subramoni, Jerome Vienne and Dhabaleswar Panda (pdf)
  • Performance patterns and hardware metrics on modern multicore processors: Best practices for performance engineering, Jan Treibig, Georg Hager and Gerhard Wellein (pdf)