Indiana University (IU) and its collaborators won the SC07 Bandwidth Challenge for the IU Data Capacitor, a system designed to store and manipulate
massive datasets. The IU team achieved a peak transfer rate of 18.21Gbps out of 20Gbps, nearly twice that of the nearest competitor. The IU team achieved an overall
sustained rate of 16.2Gbps (roughly equivalent to sending 170 CDs of data per minute) using a transatlantic network path that included the Internet2, GÉANT2, and DFN
research networks.
During the competition, the IU-led team ran several applications, all of which depended upon the Data Capacitor’s ability to read and write data at extreme speeds.
A key aspect of the demonstration was the ability to simultaneously support a mix of several different applications from the sciences and humanities, including
modeling and analysis of the amyloid peptide (cause of Alzheimer’s disease); live acquisition of X-ray crystallography data; digital preservation of ancient Sanskrit
manuscripts; performance analysis of a computational fluid dynamics application; and simulations of a high-energy physics reaction between the basic particles of
matter.
URL:
http://newsinfo.iu.edu/news/page/normal/6839.html
Collaborators:
USA:
University Information Technology Services, Indiana University
School of Informatics, Indiana University
Pervasive Technology Labs, Indiana University
Rochester Institute of Technology
Oak Ridge National Laboratory
Pittsburgh Supercomputing Center
Germany:
Technische Universitat Dresden
Other:
DataDirect Networks
Dell
Myricom
Force10
