University of Minnesota
University Relations
http://www.umn.edu/urelate
612-624-6868
myU OneStop


Go to unit's home.

Home | News and Announcements | Archive | DISC receives NSF award

September 29, 2006

DISC receives NSF award

The DTC Intelligent Storage Consortium (DISC) is pleased to announce that it has been awarded a three year, $600K grant by the National Science Foundation (NSF) to study critical issues in High Performance Computing and Data Security. Congratulations to Professors Andrew Odlyzko (DTC Director and Mathematics), Yongdae Kim (Computer Science and Engineering), David Lilja (Head Electrical and Computer Engineering) and the entire team at DISC. This award will complement DISC’s research efforts.

NSF award information below
More information about DISC is available at: DISC

Other related links:

NSF Award Information

Integrated Infrastructure for Secure and Efficient Long-Term Data Management
Principal Investigators: Andrew Odlyzko, Yongdae Kim, David Lilja

Current storage and data archiving technologies are simply incapable of satisfying the increasing demands for bandwidth and long-term data security.

Archive systems have been identified as a key bottleneck in high-performance storage systems. It is estimated that over 35 TB/hr (10GB/sec) of archive bandwidth was needed by typical HPC applications in 2003, while the required bandwidth is expected to grow to over 350 TB/hr in 2007!

The need to protect and preserve cryptographic keys in a long-term archive also presents a major challenge since many unforeseen changes can occur during the data’s lifetime. For instance, the user who originally encrypted the data may be unknown or unavailable when the data is to be decrypted. Furthermore, keys can become compromised as can the cryptographic algorithms themselves. All of these issues require fundamentally new approaches to develop a storage archive capable of securely preserving data for thirty years or more.

We are proposing to develop a tape-based long-term archival data management system that will enable high-performance while maintaining appropriate levels of security throughout the data’s lifecycle.