[Seminar] Scalable Data Processing with Intelligent Storage
Samsung Semiconductor Inc. America
■ 호스트: 김진수 교수 (x7302, 880-7302)
(다른 세미나와의 중복을 피해 시간을 오후 4시로 변경하였으니 착오없으시기 바랍니다.)
As the cloud becomes popular and data exponentially grows, modern Web-scale data-dependent services and applications require higher capacity and performance from the storage system. These services and applications need to handle a large number of objects in real time, but traditional storage systems designed primarily for HDDs are inefficient to handle workloads in a scalable way. The main reason is that existing software was developed assuming that storage devices are slow and unreliable. Legacy systems traded IOPS for bandwidth and adopted heavy recovery mechanisms for consistency and persistence. As storage gets faster, the performance gap between the user experience and the product spec is widen. In this presentation, Dr. Ki presents how intelligent storage can mitigate these problems and help to implement scalable data processing.
Yang Seok Ki is a Sr. Director and architect of Memory Software Lab, Samsung Semiconductor Inc. America. He leads the Advanced Datacenter Solutions group whose main focus is to innovate SSD and its ecosystem across datacenter hardware and software infrastructure, and drives a data-centric computing. Before joining Samsung, he worked for Oracle server technology group that builds a distributed database server system, and contributed to Oracle 12c release. Prior to his industrial experience, he worked on HPDC (High Performance Distributed Computing), Grid, and Cloud research in Information Sciences Institute of University of Southern California and Center of Networked Systems, University of California, San Diego. He received his Ph.D. degree of Electrical Engineering and Computer Science in parallel processing, his M.S. degree of Computer Engineering, and B.S. degree of Computer Engineering from Seoul National University, Korea.