Special Session on GPU computing


For the next decade, Moore's Law is still going to bring higher transistor densities allowing Billions of transistors to be integrated on a single chip. However, it becomes obvious that exploiting significant amounts of instruction-level parallelism with deeper pipelines and more aggressive wide-issue superscalar techniques, and using most of the transistor budget for large on-chip caches has come to a dead end. Especially, scaling performance with higher clock frequencies is getting more and more difficult because of heat dissipation problems and too high energy consumption. The latter is not only a technical problem for mobile systems, but is even going to become a severe problem for computing centers because high energy consumption leads to significant cost factors in the budget. For the moment, improving performance can only be achieved by exploiting parallelism on all system levels. Multicore architectures like Graphics Processing Unit (GPU) offer a better performance/Watt ratio than single core architectures with similar performance. Combining multicore and coprocessor technology promises extreme computing power for highly CPU-time-consuming applications like in image processing. The Special Session on GPU Computing and Hybrid Computing aims at providing a forum for scientific researchers and engineers on hot topics related to GPU computing and hybrid computing with special emphasis on applications, performance analysis, programming models and mechanisms for mapping codes.

Topics of interest include, but are not limited to:
 
  • GPU computing, multi GPU processing, hybrid computing;
  • Programming models, programming frameworks, CUDA, OpenCL, communication libraries;
  • Mechanisms for mapping codes;
  • Task allocation;
  • Fault tolerance;
  • Performance analysis;
  • Applications: image processing, signal processing, linear algebra, numerical simulation, optimisation;
  • Domains: computer science, electronic, embedded systems, telecommunication, medical imaging, finance.
 

Important dates

Paper submission: 26th Aug 2013
Acceptance notification: 7th Oct 2013 21st Oct 2013
Camera ready due: 31st Oct 2013 21st Nov 2013
Conference: 12th - 14th Feb 2014

Chair:

Didier El Baz
team CDA, LAAS-CNRS
France

Programme Committee:

 
  • Grey Ballard, UC Berkeley, USA
  • Daniel Becker, Siemens AG, Germany
  • Matthias Birk, Karlsruher Institut für Technologie, Germany
  • Vincent Boyer, CIRRELT, University of. Montréal, Canada
  • David Defour, University of Perpignan, France
  • Didier. El Baz, LAAS-CNRS, France
  • Dominik Göddeke, TU Dortmund, Germany
  • Diana Göhringer, Fraunhofer IOSB, Germany
  • Antonio Gomez Iglesias, Universidad de Extremadura, Spain
  • Fumihiko Ino, Osaka University, Japan
  • Volodymyr Kindratenko, NCSA, University of Illinois, USA
  • Dimitri Komatisch, University of Toulouse, France
  • Jens Kruger, IVDA Saarbrücken, and Scientific Computing and Imaging Institute, Germany
  • Mohamed Lalami, LAAS-CNRS, France
  • Jacobo Lobeiras Blanco, University of A Coruña (UDC), Spain
  • Rasmus Pagh, IT University of Copenhagen, Denmark
  • Mathias Paulin, IRIT, Université Paul Sabatier, France
  • Everett Phillips, NVIDIA, USA
  • Enrique Quintana-Orti, Universidad Jaime I, Spain
  • Girish Ravunnikutty, University of Florida, USA
  • Přemysl Šůcha, LAAS-CNRS, Toulouse/Technical University in Prague, Cezch Republic
  • C. Vuik, TU Delft, Netherlands
  • Daniel Weiskopf, VISUS - Visualization Research Center, Universitaet Stuttgart, Germany
 

Submission guidelines

Prospective authors should submit a full paper not exceeding 8 pages in the IEEE Conference proceedings format (IEEEtran, double-column, 10pt). Double-bind review: the first page of the paper should contain only the title and abstract; in the reference list, references to the authors' own work should appear as "omitted for blind review" entries. Manuscript submission

Publication

Proceedings will be published by the Conference Publishing Services (CPS) in the same volume of the main track. Authors of accepted papers are expected to register and present their papers at the Conference. Conference proceedings will be submitted for inclusion in Xplore and the CSDL, and for indexing, among others, to DBLP, Scopus ScienceDirect, and ISI Web of Knowledge.

Contacts

Didier El Baz
team CDA, LAAS-CNRS
France