Data Shaping for Improving Endurance and Reliability in Sub-20nm NAND

Abstract: Sub-20nm NAND scaling introduces significant endurance and reliability challenges, which require advanced system level solutions. Hence, it becomes ever more important to realize and leverage the potential embedded in the low data entropy of typical hosts for coping with these scaling issues. We describe a data manipulation and shaping technique that leverages this potential for significant endurance, performance and reliability improvements.

Bio: Eran Sharon is an Engineering Fellow at SanDisk, heading an R&D team developing a broad range of coding, DSP and memory management solutions for NVM. Eran has over 20 publications in leading venues, holds 88 patents and over 130 patent applications in the fields of storage and communications. Eran received his PhD in EE from Tel-Aviv University, Israel in 2009. He is the recipient of several awards, including Weinstein signal processing excellence prize and ACC Feder Prize for best graduate student research.