Title: ”Challenge of MTJ-Based Nonvolatile Hardware for Edge AI Applications ”
Abstract: Nonvolatile spintronic devices have potential advantages such as fast read/write and high endurance together with back-end-of-the-line compatibility of semiconductor fabrication, which offers the possibility of constructing not only stand-alone RAMs and embedded RAMs that can be used in conventional VLSI circuits and systems but also realizing standby-power-free and high-performance VLSI processors, which could open up a practical intermittent-computing paradigm for internet-of-things (IoT) applications. In my presentation, some AI-hardware examples based on MTJ-based nonvolatile logic-in-memory architecture are presented, and their suitability for IoT applications is discussed.
Biography: Takahiro Hanyu received the B.E., M.E., and D.E. degrees in Electronic Engineering from Tohoku University, Sendai, Japan, in 1984, 1986, and 1989,
respectively. He is currently a full professor and the director (from April 2022 to present) at the Research Institute of Electrical Communication, Tohoku
University. His general research interests include nonvolatile logic circuits and their applications to ultra-low-power and/or highly dependable VLSI processors
and post-binary computing and their application to brain-inspired VLSI systems and edge AI hardware.
He received the Sakai Memorial Award from the Information Processing Society of Japan in 2000, the Judge’s Special Award at the 9th LSI Design of the Year
from the Semiconductor Industry News of Japan in 2002, the Special Feature Award at the University LSI Design Contest from ASP-DAC in 2007, the APEX
Paper Award of Japan Society of Applied Physics in 2009, the Excellent Paper Award of IEICE, Japan, in 2010, the Ichimura Academic Award in 2010, the Best
Paper Award of IEEE ISVLSI 2010, the Paper Award of SSDM 2012, the Best Paper Finalist of IEEE ASYNC 2014, and the Commendation for Science and
Technology by MEXT, Japan, in 2015. Dr. Hanyu is a Senior Member of the IEEE.
Title: ”The Silicon Photonics Marathon: From Optical Interconnect to Computing and Memory!”
Abstract: Silicon photonics technology has facilitated the deployment of integrated photonics across different application domains, from ultra-fast communication for chip-scale interconnect and Datacom applications to energy-efficient optical computation for accelerating AI and machine learning applications. More recently, the integration of silicon photonics and nonvolatile phase change materials has also created a unique opportunity to realize photonic memory and in-memory optical computing. In this keynote, through an interdisciplinary approach and from device to system level, I will present a holistic overview of the promise and challenges of silicon photonics when employed for inter- and intra-chip optical interconnect AI acceleration and memory applications. I will present several examples of many-core systems-on-chip (SoCs) integrating silicon photonics and how to design solutions based on hardware-software co-design and cross-layer co-optimization that can efficiently address some of the existing challenges in such systems.
Biography: Mahdi Nikdast is an Associate Professor and Endowed Rockwell-Anderson Professor in the Department of Electrical and Computer Engineering at Colorado State University (CSU), Fort Collins, where he is directing the Electronic-PhotoniC System Design (ECSyD) Laboratory. He received his Ph.D. in Electronic and Computer Engineering from The Hong Kong University of Science and Technology (HKUST), Hong Kong, in 2014. From 2014 to 2017, he was a postdoctoral fellow at McGill University and Polytechnique Montreal, Quebec, Canada. His research interests are at the intersection of integrated photonics, emerging technologies, and high-performance computing. Prof. Nikdast and his students have published numerous papers in refereed journals and international conference publications and across different areas of VLSI, EDA, Photonics, Embedded Systems, Systems-on-Chip (SoCs), Artificial Intelligence (AI), and Computer Architecture. He has edited a book on Silicon Photonics for High-Performance Computing and Beyond, published by Taylor and Francis Group in 2022, and another book on Photonic Interconnects for Computing Systems: Understanding and Pushing Design Challenges, published by River Publishers in 2017. Prof. Nikdast currently serves as an Associate Editor for IEEE Transactions on Very Large Scale Integration Systems (IEEE TVLSI), and has served on the TPC of various international conferences, including DAC, OFC, DATE, ICCAD, ESWEEK, NOCS, etc. He is a co-founder of the International Workshop on Optical/Photonic Interconnects for Computing Systems (OPTICS workshop) and the North American Workshop on Silicon Photonics for High-Performance Computing (SPHPC Workshop). Prof. Nikdast and his team were the recipient of various awards, including the Second Best Project Award at the AMD Technical Forum and Exhibition (AMD-TFE 2010, Taiwan), the Best Paper Award at the Asia Communications and Photonics Conference (ACP 2015, Hong Kong), the Best Paper Award at the Design, Automation, and Test in Europe (DATE) Conference (DATE 2016 – Test Track, Dresden), the Best Paper Award Candidate at ACM Great Lake Symposium on VLSI (GLSVLSI 2018, USA), and the Best Paper Honorable Mention Award at ACM Great Lake Symposium on VLSI (GLSVLSI 2020, China). Prof. Nikdast received the prestigious NSF CAREER Award (2021), the George T. Abell Award for Outstanding Early-Career Faculty (2022), the Rockwell-Anderson Professorship (2022), and the George T. Abell Award for Teaching and Mentoring (2023). He is a Senior Member of the IEEE.
Title: ”Challenges and Opportunities of Next-Generation Enterprise SSD Storage”
Abstract: Data is driving the transformation of the world, including the Internet of Everything, AI, and high-speed computing technologies. All of which are driving the digital transformation of all industries and assisting humans and enterprises to make faster and more accurate decisions through data analysis and artificial intelligence. In such a transformation process, data storage and reading and writing behaviors play a very important role; for example, the computing results of artificial intelligence come from the collection of big data, the foundation of cloud services comes from the construction of data centers, and the server environment for high-speed computing comes from the matching stable and high-speed enterprise-level storage architecture. What kind of challenges and opportunities will enterprise SSDs face due to the transformation of these digital technologies? Welcome to the keynote speech of KSPua, CEO of Phison, to explore the latest enterprise SSD technologies and development trends.
Biography: KS Pua is the Founder and CEO of Phison Electronics. He was born in a farming community Sekinchan in Selangor, Malaysia, in 1974. At the age of 19, he went to Taiwan with just US$4,000 in his pocket. With no relatives to help him, his only dream was to study hard; he graduated from National Chiao Tung University (NCTU) in Hsinchu, Taiwan, in 1997 and earned a Master’s from NCTU in 1999. Mr. Pua and his four friends founded Phison Electronics Corp. in Taiwan. He designed and produced the world’s first single-chip USB flash controller with other founders. Under his leadership, the company has become a global leader in NAND Flash controller IC and storage solutions. As an entrepreneur, Mr. Pua is a successful high-tech entrepreneur and the recipient of the Ten Outstanding Young Malaysian Awards and received the Outstanding Young Entrepreneur Award, the Outstanding Young Manager Award, and The President Award of National Management Excellence Award from the Government. He was elected a Fellow of the Chinese Society for Management Of Technology in 2009. In 2020, Phison enjoyed a turnover of US$1.64 billion and became the largest independent NAND controller and NAND storage solution provider globally, and was named 65th in U.S magazine Bloomberg Businessweek’s Tech 100 in the year of 2010. From 2015 to the present, the production value of Phison was ranked top 4 IC Design Houses in Taiwan’s IC design industry.