The fusion of high-performance computing (HPC) and high-performance data (HPD) could potentially result in the generation of robust systems that are at least one order of magnitude faster than anything the HPC community currently uses for certain applications, says San Diego Supercomputer Center (SDSC) interim director Michael Norman.
Last November, SDSC announced plans to construct Gordon, a data-intensive supercomputer that is expected to read latency-bound files at 10 times the speed and efficiency of current HPC systems with the help of flash memory solid state drives. Ultimately, Gordon will possess 245 teraflops of total compute power, 64 TB of digital random access memory, and 256 TB of flash memory. Gordon also will assist in the integration of HPC and HPD because it is designed for data-intensive predictive science as well as data-mining applications.
From UCSD News
View Full Article
Abstracts Copyright © 2010 Information Inc., Bethesda, Maryland, USA