Tutorial Session 05

Advanced Memory Systems: Reliable Storage and Efficient Computing

Date: October 27, 2026 | Time: 14:00 - 17:00

Speakers

Prof. Jianjun Luo
Prof. Jianjun Luo

Hangzhou Dianzi University, China

Talk Title: Error Correction Codes for Next-Generation NAND Flash Memory

Bio.: Jianjun (Jerome) Luo, the Dean of Microelectronic Research Institute in Hangzhou Dianzi University, also the founder and CTO of Sage Microelectronics. He earned a PhD in semiconductor technology from Zhejiang University in China, a Master's in Microelectronics from the Hangzhou Dianzi University, and a Bachelor's in Electronics Engineering from Shanghai Jiaotong University. He accumulated his experience in communication and storage IC design for more than 30 years. He won the second prize of National Scientific and Technological Progress Award, and Ho Leung Ho Lee Foundation's Scientific and Technological Award.

Assoc. Prof. Wei Mao
Assoc. Prof. Wei Mao

Xidian University, China

Talk Title: Computing-in-Memory Readout Circuits: Design Principles and Optimization

Bio.: Wei Mao received the B.Eng. degree from Southeast University and the Ph.D. degree from the National University of Singapore. Since 2023, he has been an Associate Professor with Xidian University, Xi'an, China. His research interests include emerging computing and memory chip design for AI applications. He has published over 90 papers in leading journals and conferences, along with one first-author monograph and two book chapters. His awards include the Second Prize of the 2020 Wu Wenjun Artificial Intelligence Chip Award, the 2021 Ministry of Education-Huawei "Intelligent Foundation" Pioneer Teacher Award, and the Best Live Demonstration Award at IEEE AICAS 2026. He serves on the IEEE Circuits and Systems Society Standards Committee and the executive committees of CCF's Integrated Circuit Design and Information Storage Technology Technical Committees. He is an Associate Editor of ICAS and a Guest Editor of IEEE TCAS-I. He has also served on the organizing or technical program committees of conferences including ISCAS, ISICAS, and AICAS.

Abstract

Advanced memory systems play a critical role in the AI era, as growing data volumes and computational demands place increasing pressure on storage and processing capabilities. Ensuring reliable data storage and supporting energy-efficient computing are two key directions in their development. The first talk addresses error correction codes for next-generation NAND flash memory. It begins with an overview of NAND flash reliability challenges and error correcting fundamentals, then introduces two-dimensional turbo product codes. Implementation and evaluation considerations are discussed to highlight practical design trade-offs, followed by a summary and outlook on future developments in NAND flash error correction. The second talk examines computing-in-memory (CIM) readout circuit design and optimization. It explains how analog accumulation and output quantization affect accuracy, throughput, energy consumption, and area efficiency. Representative techniques and circuit examples illustrate performance trade-offs in different CIM readout architectures, emphasizing the co-design of accumulation and quantization to reduce conversion overhead while meeting computational requirements. This tutorial is intended for researchers and engineers working in memory technologies, integrated circuit design, and AI hardware.