ISG Talks are sponsored by Couchbase.
- This event has passed.
Prof. Sang-Woo Jun: Lowering the cost of large-scale data analytics via efficient use of flash storage
February 8, 2019 @ 3:00 pm - 4:00 pm
In this talk, I present the storage systems aspect of the ongoing work on using relatively cheap solid-state secondary storage to replace expensive DRAM for analytics on large amounts of data, using as examples graph analytics and the bioinformatics application somatic mutation finding.
Both applications are inherently random access intensive, which is a bad fit with the coarse access granularity of secondary storage.
In both cases, performance impact of random access is addressed in two ways: reorganizing the computation and access pattern to remove random access, and modifying the internals of the storage device controller to optimize for random accesses.
In both cases, a desktop-class system with secondary storage was able to match the performance of a system with an order of magnitude higher cost.
Sang-Woo Jun is a faculty member at Donald Bren School of Information and Computer Sciences at the University of California, Irvine. His research focus is on computer architecture and system design for lowering the cost of handling large amounts of data. Before joining UCI, Sang-Woo did his Ph.D with Professor Arvind at the Massachusetts Institute of Technology, and his B.S. at Seoul National University in Korea. His industry experience includes intern at the Big Data Discovery team at Oracle, and Server/Client developer at Nexon inc.