HPDC Workshop on Next-Generation Distributed Data Management

http://www.isi.edu/~annc/distributedDataWorkshop.html

June 20, 2006

Paris, France

Distributed data management is a challenging problem in high performance computing environments, and the difficulty of managing scientific and commercial data sets will increase as they scale to terabytes and petabytes in the coming years. In conjunction with HPDC, we will hold a one-day workshop that will gather together researchers and industry participants to discuss future trends for distributed data management in HPDC environments. We invite short papers (maximum 6 pages) of two types: position papers that discuss the authors’ vision for trends or developments in data management in the three to five year timeframe or papers that describe innovative algorithms, tools or services for distributed data management.

Topics of interest include, but are not limited to:

• Peer-to-peer approaches to data discovery and data storage
• Distributed Metadata management
• Services for generating and maintaining provenance information
• Techniques for replica management, including consistency of replicas
• Algorithms for data placement, prefetching, staging, proactive replication
• Federation of diverse databases, data mediation services
• Distributed query processing
• Virtualization of data resources
• Interaction of data management with execution environments, including workflow management services, virtual machines
• Validation of correctness of distributed data
• Publish/subscribe systems
• Advanced data transfer techniques
• Namespace management, globally unique naming
• Support for streaming data

Important dates:

• Position papers due: February 28, 2006 (Tuesday)
• Program committee discussion: March 23, 2006 (Thursday)
• Notification of acceptance of papers: March 27, 2006 (Monday)
• Final papers due: April 14, 2006 (Friday)

Submission: We will be using the HPDC conference submission site. Submission instructions to follow on workshop web site.

Workshop organizers/co-chairs:

Ann Chervenak, USC Information Sciences Institute (annc@isi.edu)

Dave Berry, National UK e-Science Center (daveb@nesc.ac.uk)

Neil P. Chue Hong, EPCC, University of Edinburgh (N.ChueHong@epcc.ed.ac.uk)

Program committee:

Gagan Agrawal, Ohio State

Bill Allcock, Argonne National Laboratory

Chaitan Baru, SDSC

Karan Bhatia, SDSC     

Dieter Gawlick, Oracle

Pilar Herrero, UPM

Tahsin Kurc, Ohio State

Allen Luniewski, IBM

Andre Merzky, Zuse Institute Berlin

Reagan Moore, SDSC

Beth Plale, Indiana University

Osamu Tatebe, AIST

Kurt Stockinger, Lawrence Berkeley National Laboratory

Stratis Viglas, U. Edinburgh