Optimization of Phase Change Memory for In-Memory Computing

Abstract: 

The need to shuttle data between processing and memory units has been a key performance bottleneck for conventional hardware implementations of artificial neural networks. Analog in-memory computing (AIMC) emerges as a promising solution to this challenge by directly performing computations within non-volatile memory devices, such as phase change memory (PCM). However, the utilization of PCMs for analog computing introduces nonidealities, including resistance drift, read noise, limited memory window, and various device failures. I will discuss our work on optimizing PCM devices to alleviate these nonidealities and mitigate their impact on AIMC. Additionally, I will talk about the effort to package such computer chips with photovoltaic power conversion devices and optical communication devices for ultra-small form factor edge computing applications.

Bio:

Ning Li obtained his B.S. and M.S. from Tsinghua University and his Ph.D. from the University of Texas at Austin, TX. He was a Research Staff Member at IBM T. J. Watson Research Center, Yorktown Heights, NY, from 2010 to 2022. His research work is related to memory devices and their applications in neuromorphic computing, flexible and new form factor devices and systems, optoelectronic devices for interconnects and communications, heterogeneous integration, organic electronics, etc. He was awarded more than 250 US patents, many IBM High Value Patent Awards, IBM Invention Achievement Awards, and Master Inventor Awards. His work has been featured on Nature Research Highlight, Semiconductor Today, Nanowerk most popular spotlight article, etc.  He joined the Electrical Engineering Department at Penn State University in the Spring of 2024.