Facing the Multicore-Challenge

Conference for Junior Researchers


March 17-19, 2010

Conference theme

The prevalence of multicore technologies has brought ubiquitous parallelism and a huge theoretical potential for compute-intensive tasks. In theory, advancements in technology bring us closer to the solution of the Grand Challenges in modern computing. In practice however, it is hard to achieve maximal throughput in the results and to exploit all available capabilities. Due to the inevitable paradigm shift towards multicore technologies, parallelism is now affecting all kinds of software development processes – from large-scale numerical simulation to desktop commodity applications. And parallelism is no longer restricted to well-balanced systems built of homogeneous nodes. In recent systems parallelism spreads over many systems levels including nodes, processors, cores, threads, registers, SIMD and vector units. Moreover, heterogeneity of the systems is growing on the node as well as on the chip level. Most applications and algorithms are not yet ready to utilize available capabilities and a tremendous effort is required to close the gap. Different technologies and processing models, non-adjusted interfaces, and incomplete tool chains complicate holistic programming approaches and impede programmer’s productivity. On the other hand, resource contention, data conflicts and hardware bottlenecks keep performance away from theoretical peak.

At the current state of the art in technologies and methodologies an interdisciplinary approach is required to tackle the obstacles in multicore computing. Only a comprehensive approach with contributions from computer science, applied mathematics, high performance computing, and engineering disciplines can face the multicore challenge. Compute- and memory-intensive applications can only benefit from the full hardware potential if all features on all system levels are taken into account in a holistic approach.

This conference aims to combine new aspects of multicore microprocessor technologies, parallel applications, numerical simulation, software development and tools. The primary goal is to bring together young researchers working in related fields. Contributions are welcome from all participating disciplines.

Program outline

Introductory tutorials will give an insight to multicore processor technology, accelerators, parallel programming models, current applications and tools for multicore application development. Keynote lectures from invited speakers will consider comprehensive aspects and problems arising from deployment of multicore technologies and parallel applications. In three focus sessions on

  • Hardware and parallel programming
  • Applications on multicore
  • Practice, experience and results

researchers are presenting their recent work on topics around the conference theme. In short talks, young researchers are given a chance to present their ongoing work. Furthermore, research projects can be presented in a poster session. In a final panel discussion all elaborated aspects and future topics will be discussed.

Submission topics

Topics of interest for conference submissions include (but are not limited to):

  • Emerging hardware architectures (Multicore, GPUs, Cell, FPGAs, Accelerators, ...)
  • Parallel programming models, environments and languages (MPI, OpenMP, CUDA, OpenCL, PGAS, ...) for multicore computing
  • Parallelization strategies in hybrid and hierarchical setups
  • Hardware-aware computing and auto-tuning strategies
  • Heterogeneous computing, adaptive and reconfigurable computing
  • Aspects of microprocessor technologies Prospect of manycore technologies
  • Virtualization strategies and hardware transparency
  • Library and tool support
  • Scalability issues
  • Portability of software solutions
  • Performance analysis and modeling
  • Parallel data structures
  • Architecture-aware approaches for parallel numerical simulations, implementation and algorithm design
  • Compiler techniques and code optimization strategies for parallel systems
  • Memory behavior analysis and parallel data access
  • Efficient numerical methods
  • Practice and experience of multicore programming
  • Benchmarking results of scientific applications
  • Parallel applications (e.g. numerical simulation, image processing)
  • Multicore application studies
  • Interdisciplinary approaches and theoretical concepts

Conference language is English.

Conference Organizers

David Kramer

Chair for Computer Architecture

Institute of Computer Science and Engineering

Karlsruhe Institute for Technology (KIT), Universität Karlsruhe (TH), Germany

Phone: +49 721 608 6048, Fax: +49 721 608 3962

Email: kramer@ira.uka.de

URL: http://ca.itec.uka.de/~kramer/


Rainer Keller

Oak Ridge National Laboratory

PO Box 20008 MS6164

Oak Ridge TN 37831-6164, USA

Phone: +1 865 241 6293, Fax: +1 865 241 4811

Email: keller@ornl.gov

URL: http://www.ornl.gov

Jan-Philipp Weiß

Shared Research Group

New Frontiers in High Performance Computing Exploiting Multicore and Coprocessor Technology

Institute for Applied and Numerical Mathematics and Steinbuch Centre for Computing (SCC)

Karlsruhe Institute of Technology (KIT), Universität Karlsruhe (TH), Germany

Engesserstr. 2, Build. 20.50, 76128 Karlsruhe

Phone: +49 721 608 7406, Fax: +49 721 608 4178

Email: jan-philipp.weiss@kit.edu

URL: http://srg-multicore.rz.uni-karlsruhe.de


The conference will be held at the

Heidelberg Academy of Sciences / Heidelberger Akademie der Wissenschaften

Karlstr. 4, 69117 Heidelberg

Tel. +49 6221 5432 -65 / -66, Fax +49 6221 5433-55

Email: haw@adw.uni-heidelberg.de

URL: http://www.haw.baden-wuerttemberg.de

Further Information

Further information is available at http://www.multicore-challenge.org

responsible: editorial office
Latest Revision: 2009-07-24
zum Seitenanfang