Paper Title: HeatWatch: Exploiting 3D NAND Self-Recovery and Temperature Effects

Paper Abstract: In NAND flash memory, damage from wearout can be partially repaired on its own during the idle time between program or erase operations (known as the dwell time), via a phenomenon known as the self-recovery effect. We perform the first detailed experimental characterization of the effects of self-recovery and temperature on real, state-of-the-art 3D NAND flash memory devices. We show that these effects influence two major factors in NAND flash memory reliability: (1) retention loss speed, and (2) program variation (i.e., the difference in programming speed across flash cells). We develop a new model that predicts how retention, wearout, self-recovery, and temperature affect raw bit error rates and cell threshold voltages, with an error of only 4.9%. Based on our experimental findings and our model, we propose HeatWatch, a new mechanism to improve 3D NAND flash memory reliability. HeatWatch optimizes the read reference voltage by adapting it to the dwell time of the workload and the current operating temperature. Our detailed experimental evaluations show that HeatWatch improves flash lifetime by 3.85x over a baseline that uses a fixed read reference voltage.

Paper Author: Yixin Luo, Doctoral Student, Carnegie-Mellon University

Author Bio: Yixin Luo is a graduating PhD student from Carnegie Mellon. His advisor is Professor Onur Mutlu. Yixin will be looking for an industry position in the next few months, he is interested in storage systems, data center infrastructure, and solving any other challenging problems in computer architectures and systems. Yixin just successfully defended his thesis on "Architectural Techniques for Improving NAND Flash Memory Reliability".