A research team from the San Diego Supercomputer Center (SDSC) at the University of California, San Diego and the University of California's Lawrence Berkeley National Laboratory won the Storage Challenge competition at the recent SC09 supercomputing conference. The winning submission was based on the architecture of SDSC's recently announced Dash high-performance compute system.
The hypothesis presented for the challenge stated that solid state drives based on NAND flash technology are reliable and inexpensive enough to improve input/output density (I/O) by more than an order of magnitude. "The current data storage I/O rate is far lower than the ever-increasing rate of enthusiasm among researchers and scientists, who are now drowning in a sea of data because of this differential," says SDSC's Arun Jagatheesan. "With the SC09 Storage Challenge, our team demonstrated the prototype of a data-intensive supercomputer that can bridge this gap."
The Dash system presented in the challenge is a prototype for a significantly larger flash-memory high-performance computing (HPC) system called Gordon, which is scheduled to go online in mid-2011. Both Dash and Gordon are designed to accelerate research in a variety of data-intensive science problems by providing cost-effective data performance that is more than 10 times faster than most other HPC systems currently in use.
From UCSD News
View Full Article
Abstracts Copyright © 2009 Information Inc., Bethesda, Maryland, USA