Conference Program
(Version March 9, 2010)


Wednesday, March 17

13:30h - 14:00hRegistration
14:00h - 14:15h Welcome
Hermann H. Hahn, President of the Heidelberg Academy of Sciences
Willy Jäger, Conference mentor

Tutorials - Afternoon Session
14:15h - 15:00h

Multicore to Manycore: Technologies and Programming Concepts
Jan-Philipp Weiss, Karlsruhe Institute of Technology, Germany

15:00h - 15:30h
Coffee Break
15:30h - 16:45h

Programming Ct – Part I: Scaling Towards Future Multicore
Michael Klemm, Intel, Germany

16:45h - 17:15h
Coffee Break
17:15h - 18:30h

Programming Ct – Part II: Porting Applications to Multicore
Michael Klemm, Intel, Germany


  Evening Session
19:00h - 20:00h

Evening Reception
Bel Etage of the Heidelberg Academy of Sciences                                   

20:00h - 20:15h
Conference Opening
20:15h - 21:15 h 

- Invited Talk -
Analyzing Massive Social Networks Using
Multicore and Multithreaded Architectures

David A. Bader, Georgia Institute of Technology, USA

(Abstract)



Thursday, March 18

 Morning Session: Computer Architecture and Parallel Programming
 8:30h - 8:50h
Registration
 8:50h - 9:00h
Welcome and Information
 9:00h - 10:00h 

- Invited Talk -
MareIncognito: A Perspective Towards Exascale
Jesus Labarta, Barcelona Supercomputing Centre, Spain

(Abstract)

10:00h -10:30h
Coffee Break and Poster Session
10:30h - 10:55h 

RapidMind: Portability across Architectures and its Limitations
Iris Christadler, Leibniz Supercomputing Centre Munich, Germany

10:55h - 11:20h

A Majority-Based Control Scheme for Way-Adaptable Caches
Masayuki Sato, Tohoku University, Japan

11:20h - 11:45h

Improved Scalability by Using Hardware-Aware Thread Affinities
Sven Mallach, University of Cologne, Germany

11:45h - 12:10h

Thread Creation for Self-aware Parallel Systems
Oliver Mattes, Karlsruhe Institute of Technology, Germany



12:10h - 14:00Lunch Break
Kulturbrauerei Heidelberg                                                                                                       


  Afternoon Session: Applications on Multicore I                                    
14:00h - 14:45h

Where Does Manycore Lead Us?
Moderated Discussion

14:45h - 15:10h

G-means Improved for Cell BE Environment
Gomide Foina, Barcelona Supercomputing Centre, Spain

15:10h - 15:40hCoffee Break and Poster Session
15:40h - 16:05h

Parallel 3D Multigrid Methods on the STI Cell BE Architecture
Fabian Oboril, Karlsruhe Institute of Technology

16:05h - 16:30h

FPGA vs. Multi-Core CPUs vs. GPUs: 
Hands-on Experience with a Sorting Application
Cristian Grozea, Fraunhofer Institute FIRST Berlin, Germany

16:30h - 17:10h

Short Talks - Session I (see Table at bottom)

17:10h - 17:30h
Coffee Break
17:30h - 18:30h
Short Talks - Session II (see Table at bottom)

18:45h - 20:15h Guided Tour: Old City of Heidelberg                                                                                

20:15h-22:30h Conference Dinner
Vetter's Alt Heidelberger Brauhaus                                                                                                     


Friday, March 19

 

Morning Session: Applications on Multicore II                    

 8:50h - 9:00h          Welcome and Information
 9:00h -10:00h 

- Invited Talk -
The Natural Parallelism
Robert Strzodka, MPI Informatik, Saarbrücken, Germany

10:00h - 10:30h
Coffee Break and Poster Session (see Table at bottom)
10:30h - 10:55h

Lattice-Boltzmann Simulation of the Shallow-Water Equations
with Fluid-Structure Interaction on Multi- and Manycore Processors
Markus Geveler, Technical University of Dortmund, Germany

10:55h -11:20h

Applying Classic Feedback Control for Enhancing the Fault-Tolerance
of Parallel Pipeline Workflows on Multi-Core Systems

Tudor Ionescu, University of Stuttgart, Germany

11:20h - 12:05h

Programming for Manycore - Challenges and Solutions                                                                                
Moderated Discussion


12:05h - 13:30h Lunch Break
Kulturbrauerei Heidelberg                                                                                                                                    

  Afternoon Session: GPGPU Computing      
13:30h - 13:55h  Considering GPGPU for HPC Centers: Is it Worth the Effort?                                        
Hans Hacker, Technical University Munich, Germany  
13:55h - 14:20h  Real-time Image Segmentation on a GPU
Alexey Abramov, University of Goettingen, Germany  
14:20h - 14:45h Parallel Volume Rendering Implementation on
Graphics Cards using CUDA

Jens Fangerau, University of Heidelberg, Germany
 
14:45h - 15:00h
Coffee Break
15:00h - 15:50hShort Talks - Session III (see Table at bottom)
15:50h - 16:00hConference Closing and Farewell




Overview of Short Talks 
Session I
Thursday, March 18, 2010
16:30h - 17:10h
  • Performance Modeling and Multicore-aware Optimization for 3D Parallel Lattice Boltzmann Simulations, Johannes Habich, University of Erlangen-Nuremberg, Germany
  • A Multicore Implementation of the Lattice Boltzmann Method for Non-uniform Grids, Kostyantyn Kucher, TU Braunschweig, Germany
  • A Lattice Boltzmann CUDA-GPU-Implementation on Non-uniform Grids, Martin Schönherr, TU Braunschweig, Germany
  • Survey of the QPACE Architecture, Nils Meyer, University of Regensburg, Germany
Session II
Thursday, March 18, 2010
17:30h - 18:30h
  • A Pipelined, Multicore-aware Approach to Parallel Temporal Blocking of Stencil
    Codes for Shared and Distributed Memory, Markus Wittman, University of Erlangen-Nuremberg, Germany
  • Autotuning Parallel Stencil Computations, Mathias Christen, University of Basel, Switzerland
  • Mixed Precision in Computational Fluid Dynamics - An Error Correcting Approach
    for Solving Linear Systems, Hartwig Anzt, Karlsruhe Institute of Technology, Germany
  • MPI, OpenMP and CUDA Approaches for Solving Large Sparse Linear Systems of
    Equations, Benedikt Galler, Karlsruhe Institute of Technology, Germany
  • Large Sparse Exact Matching Algorithms for Massive Graph Analysis, Madan Sathe, University of Basel, Switzerland
  • Numerical Simulation in Computational Finance: Option Pricing with Monte Carlo
    Methods, Philipp Werner, Karlsruhe Institute of Technology, Germany
Session III
Friday, March 19, 2010
15:00 - 15:50h
  • Applying Software Engineering Methods and Tools to Scientific Research
    Projects-ATLAS Project, Hoda Naguib, TU Munich, Germany
  • Applying Software Engineering Methods and Tools to the SeisSol Project, Yang Li, TU Munich, Germany 
  • Single Pattern Multi Value LU Decomposition - Basic Ideas and Parallelization, Martin Köhler, TU Chemnitz, Germany
  • Efficient Stereo-image-sequence Segmentation on the GPUs, Alexey Abramov, University of Goettingen, Germany
  • Moist Planetary Boundary Layer Simulation Using OpenGL and GLSL, Stefan Horn, Leibniz Institute for Tropospheric Research, Leipzig, Germany


Overview of Posters 
  • C.M.E.S.S. Solving Large Scale Matrix Equations on Mulitcore Processors, Jens Saak, TU Chemnitz, Germany
  • Efficient Stereo-image-sequence Segmentation on the GPUs, Alexey Abramov, University of Goettingen, Germany
  • Mixed Precision in Computational Fluid Dynamics - An Error Correcting Approach for Solving Linear Systems, Hartwig Anzt, Karlsruhe Institute of Technology, Germany
  • MPI, OpenMP and CUDA Approaches for Solving Large Sparse Linear Systems of Equations, Benedikt Galler, Karlsruhe Institute of Technology, Germany
  • Numerical Simulation in Computational Finance: Option Pricing with Monte Carlo Methods, Philipp Werner, Karlsruhe Institute of Technology, Germany
  • The QPACE Network Processor, Thilo Maurer, University of Regensburg, Germany
  • Implementation of a Sparse Linear System Solver Utilizing Commodity GPU Hardware and Application to Combustion Simulation, Markus Meingast, TU Berlin, Germany