Call for papers
High-Performance I/O is currently a major
problem in clusters, grids, and HPC centers
due to several problems. However, it has
become a strategic part of the computer
architecture to achieve global computing
performance, as the speed of processors and
networks is increasing every day.
In this workshop we will address theoretical
and practical issues related to new solutions
trying to solve the I/O problem in large systems
scale high-performance I/O systems, and also
the practical issues associated with the
deployment of very large scale I/O systems in
HPC centers. The goal is to identify, discuss,
and share the barriers and workarounds that
have been discovered.
Particular areas of interest include, but are not limited to:
- High-performance storage systems technologies: Storage Area Networks, NAS, Storage networks, active storage devices, ...
- Parallel and distributed I/O in clusters and Grids.
- Parallel file systems
- I/O optimization techniques for scientific and business applications.
- I/O interfaces and formats.
- New topics on I/O architectures for clusters and grids.
- I/O middleware in grids.
- Content management and data mining in large storage systems and networks.
- New trends in clusters file systems.
- System architectures deployed in very large scale systems.
- Archive strategies.
- Data intensive computing.
- Data driven applications.
- Performance and scalability.
- Reliability, availability, disaster tolerance.
- Security.
- Virtualization.
- Network connectivity within the data center and with external sites.
- Tools that work and tools that don't.
- Environmental (power, cooling, structural, etc) concerns/issues.
Review process
All papers will be reviewed by (at least) two members of the program committee.
Important dates
- Papers due: May, 5, 2008.
- Notification to authors: June, 15, 2008.
- Camera ready papers: June, 25, 2008.
- Workshop dates: October, 1, 2008.
|
