Call for papers
Data management is becoming a more and more important issue in every kind of
computing system. High-performance computing, data visualization, multimedia
and data mining systems are examples of application areas where input/output
and storage are critical issues for performance. A key challenge in those
areas is how to transfer large amounts of data in and out of large-scale
systems, like clusters, Grids and peer-to-peer systems. Another key point is
how to transfer large amount of data in a timely manner. The aim of the
workshop is to identify, discuss, and share the barriers and workarounds that
have been discovered in the storage and input/output fields.
Compute and I/O-intensive applications, as represented by the Grand
Challenge problems, multimedia, cosmology simulation, climate modeling and
collaborative large-scale visualizations, large data acquisition networks,
data fussion and integration to name just a few, call for innovative
approaches to alleviate the I/O devices and networks(both bandwidth and
file access) bottlenecks.
The advent of commodity (COTS) hardware platforms has
opened up numerous possibilities in massive data
gathering and storage, scalable systems, and
large-scale simulations. The goal of this workshop is
to bring together educators, researchers, developers
and vendors to discuss problems and solutions in the
former areas, to identify new issues, and to shape
future research and development directions. We are
soliciting papers reporting original work on, but not
limited to the following
Particular areas of interest include, but are not limited to:
- File systems, protocols and storage management for parallel and distributed systems, including supercomputers,
clusters, grid, peer to peer, and embedded systems.
- Internet services scalability, including locally and geographically distributed web systems, web clusters, web applications architecture, mobile applications, web services, load balancing, availability and reliability of web systems, web caching, web replication, edge services, web performance modeling, web workload characterization, etc.
- High performance I/O, including massively parallel storage architectures, data and meta-data consistency, allocation and utilization
strategies for exploiting parallel and distributed memory, Ad-hoc parallel file systems, parallel I/O architectures, compilers and I/O APIs, etc.
- Parallel and distributed databases, including OLAP, replication schemes, optimal data allocation, multidimensional analysis,
access patterns, data declustering, Client Caching Data Management Systems, index distribution schemes, memory management techniques, etc.
- Performance evaluation: benchmarking of data management systems, I/O benchmarks, performance under faulty conditions,
I/O optimization techniques for scientific and business applications, performance tuning, I/O modeling, performance tools, tests of products, etc.
- Security, reliability and availability in distributed storage systems, including fault tolerance mechanisms,
impact of replication on reliability, reliability and availability modelling, highly available storage systems, cryptographic techniques, secure protocols, etc.
- Data management applications, including data mining, knowledge discovery, data fussion, ontologies,
bioinformatics, simulations, geographical information systems, image processing, Web retrieval, checkpointing, astrophysics, particle physics, etc.
- Storage technology and protocols including both hardware and software elements, including new I/O architectures,
active storage, virtualization, I/O middleware, quality of service issues, etc.
Review process
All papers will be reviewd by (at least) two members of the program committee.
Important dates
- Papers due: March, 3, 2008.
- Notification to authors: April, 4, 2008.
- Camera ready papers: April, 20, 2008.
- Workshop dates: July, 14-17, 2008.
Academic co-sponsors
The list of co-sponsors of PDPTA'08/WORLDCOMP'08 will soon be finalized which
will include research laboratories and centers affiliated with major
institutions. The reputation and caliber of the co-sponsors of the
2008 conference will be comparable to the 2007 offering of the
conference which included:
Academic co-sponsors
- Massachusetts Institute of Technology (MIT) Media Lab., MIT
- Computational Biology and Functional Genomics Lab., Harvard University
- Statistical Genomics and Computational Biology Lab., Dept. of Statistics, Harvard University
- Biomedical Cybernetics Lab., Harvard University
- Texas Advanced Computing Center, University of Texas at Austin
- Statistical and Computational Intelligence Lab., Purdue University
- Center for Computational Biology and Bioinformatics, Indiana University and Purdue University Indianapolis (IUPUI)
- University of Iowa's Medical Imaging HPC Lab.
- BioMedical Informatics and Bio-Imaging Lab. of Georgia Institute of Technology and Emory University
- Intelligent Data Exploration and Analysis Lab., University of Texas at Austin
- Statistical Genetics Research Group of Columbia University, New York
- Institute for Informatics Problems of the Russian Academy of Sciences
- University of North Dakota (Grand Forks, North Dakota).
Corporate co-sponsors
- Google
- Intel
- Salford Systems
Other co-sponsors
- Int'l Technology Inst. (ITI)
- GridToday
- HPCwire
- HPC Software Inc.
- STEM Education Society
- Hodges' Health
|
