Plenary Speakers

Tuesday, November 8

Linear vs Adhocracy Innovation in Imaging, Networking and Computing

Mr.Amane Inoue

Mr. Amane Inoue
President & COO, Socionext Inc., Japan


Amane Inoue has over 30 year experience in semiconductor industry and currently serves as President & COO of Socionext Inc.
Prior to Socionext, he had engaged in semiconductor business in Fujitsu and served as a Member of the Board and Corporate Senior Vice President.
Also Inoue has more than 10 years overseas work experience in England, Ireland & France in design and manufacturing.
He started his semiconductor industry career from the development of LSI for optical submarine cable repeater, followed by Memory, Security Device, MCU, and SOC.
He received master degree at McGill University in Canada.


Due to the ever-increasing cost, investment for the linear progress of technology is rarely economically viable. However, it doesn't mean that the technology innovation is ended. At the same time with linear innovation, we have seen another tide of innovation happening. Recent innovations such as virtual reality machines, drone cameras, smart watches, robotics and so on are created with combination of various technologies that have been linearly cultivated and unique ideas/conceptions. We call such innovation "Adhocracy Innovation."
Adhocracy is supposed to be used for organization that operates in an opposite fashion to a bureaucracy. And it was coined to express a flexible, adaptable and informal form of organization and has been further developed by academics such as Henry Mintzberg. Adhocracy is the phrase that perfectly encapsulates what is currently happening in innovation.
Socionext has been developing core technologies focusing on the imaging, networking and computing field and has contributed to Adhocracy Innovation. As the latest computing technology, we would like to introduce the prototype of server system based on the concept of as many cores as possible, that is,1536 CPU cores connected the network system.

A New Silicon Way: Generating Semiconductor-Intelligence Paradigm with a Virtual Moore's Law Economics and Heterogeneous Technologies

Dr. Nicky Lu

Dr. Nicky Lu
CTO and Founding Chairman, Etron Technology, Inc.
Chairman, Taiwan Semiconductor Industry Association, Taiwan


As a researcher, chip architect/designer, entrepreneur and chief executive, Dr. Lu has dedicated his career to the worldwide IC design and semiconductor industry. He is the CEO and Founding Chair of Etron Technology, Inc. since 1991, and co-founded several successful IC companies including Ardentec and Global Unichip (they are all public). He received his B.S. in Electrical Engineering from National Taiwan University and M.S. and Ph.D. from Stanford University. He worked for IBM and won numerous IBM recognition awards including an IBM Corporate Award. He holds over 27 U.S. patents and published over 50 technical papers. He is a TPC (Technical Program Committee) member of the Symposium of VLSI Circuits, served in the ISSCC TPC (25 years and received five times ISSCC Evening Awards) and as the TPC and Conference Chair of the A-SSCC 2007 and 2014, respectively. He received an IEEE Solid-State Circuits Field Award for his contributions in high speed DRAM cell/array technologies and chip designs. Since 2000, Dr. Lu has pioneered many Known-Good-Die Memory products, enabling customers' stacked-die system chips. This Multi-Dimensional-IC accomplishment summoned the new rise of both 3D-IC and Heterogeneous-Integration eras as demonstrated in his plenary talk of the 2004 ISSCC.
Dr. Lu is an IEEE Fellow, a Member of the National Academy of Engineering of U.S.A., and was honored as a Chair Professor and an Outstanding Alumnus of the National Chiao-Tung University, an Distinguished Alumnus of the National Taiwan University, General Chair of GSA (Global Semiconductor Alliance, 2009 to 2011) and WSC (World Semiconductor Council, 2014 to 2015), respectively.


Over the last five decades, the semiconductor industry has grown tremendously, from its infancy to now reaching over US$350 billion in annual revenue. This growth has been underpinned by two intelligent rules: one is an effective Return-on-Investment economic rule based on Moore's Law, which dictates that the number of transistors on a silicon chip should double every two years. The other rule is a design guideline, namely, scaling transistor line width to achieve enough productivity in lower power-delay products. Now that the line width has shrunk from several micrometers to 10 nanometers, the critical question the integrated-circuit industry faces is how far can both rules sustain? This talk proposes two points: firstly, a new observation on how the industry can continue to be very efficient and keep Moore's Law effectively for the 10 nanometer technology node. Secondly, this talk makes a bold prediction that we will see a new guideline, which can be called Virtual Moore's Law economy (VME) and achieve effective economics beyond the 5 nanometer node or even with an equivalent 3 nanometer node through a new scaling method described as 3D x 3D Microsystem Volume-Scaling for Heterogeneous Integration!
During these past five decades, the IC industry has aggressively pushed for progress and fortunately has also been pulled forward by killer applications, from mainframe computers and telecom switch machines, to PCs and notebooks, to mobile phones and today's smartphones. Now worries have arisen on whether any killer applications will emerge that can sustain semiconductor demand in the future. This talk describes more new killer applications which will continue healthy growth for the semiconductor industry, with values created by heterogeneous integration technology scaling. An emerging era named as Semiconductor-Intelligence Paradigm (SIP), however, will not only be created by scaling devices down, but also by generating more smarter integrations whereby more new technologies will focus on scaling versatile functions up!

Wednesday, November 9

Let Anyone Experience Tangible Intelligence

Dr. Sungwoo Hwang

Dr. Sungwoo Hwang
Head, Device & System Research Center, Samsung Advanced Institute of Technology, Korea


The role of Dr. Hwang in SAIT (Samsung Advanced Institute of Technology), as the center head, is pursuing systematic inter-disciplinary research ranging from nano-devices to processors and deep learning algorithms for various future applications in semiconductor, mobile, and home appliances.
Dr. Hwang himself is a research specialist in the field of nano-devices and nano-materials. He has been developing devices using various nano-materials such as graphene, atom-thick 2-dimensional materials, quantum dots, and nanowires. Recently, together with his collaborators, he realized the wafer scale growth of single crystal graphene on germanium, which was considered a new generation graphene growth technology.
Dr. Hwang was born in 1962 and got his B. S. and M. S. in the Electronics Engineering at Seoul National University. He got his Ph. D. from Professor Daniel C. Tsui at Princeton University who was Nobel Laureate in physics for the discovery of "Fractional Quantum Hall Effect". He worked in NEC Fundamental Research Lab. from 1993 to 1995, and he was a professor of Korea University from 1995 to 2012. He holds more than 350 journal papers with 4163 Google scholar citations, h-index = 31, and i10 index = 104. He has been serving as an editorial board member of Solid State Electronics since 2013 and he co-authored the textbook "Nano-electronics". He is a senior member of IEEE, member of APS, MRS, and KIEE


With my great respect towards circuit society and this wonderful conference, I would like to share what I have been witnessing and experiencing as a researcher and supervisor in the industry. The recent trends can be summarized as (1) convergence, (2) paradigm shift in computing, (3) change of hardware form factor, and finally (4) incorporation of various nano-technology. The convergence shows up in many different forms. While everyone agrees on that recent IT products such as a mobile phone are the results of heavy convergence of SoCs, display, sensors, algorithms, and even clouds, a long-sought system such as AR (augmented reality) see-through display is now becoming reality. The boundary between industries has also been fallen. Examples are autonomous driving, cheap DNA reading based on nano-technology, and payment and banking in smart phones. Deep learning has a great impact on the computing paradigm. The computing is making a quick shift from "calculation" to "recognition" in both algorithm and hardware. This shift in computing paradigm requires new processors working similarly as human brain and soon we will be in the world of tangible machine intelligence. Another type of convergence between processor and memory can be possible here and we will eventually need to adopt a new memory that can handle brain-like processing more efficiently. Recent development of flexible and stretchable material and devices possibly create the world of "printable electronics" where low performance circuit IPs can be down-loaded from the web and printed home. Nanotechnology always has been the most important working horse in supplying high performance devices to circuit designers. It is now impacting other areas such as optics and such impact would strikes back to the circuits.

The Doctor Prescribes Silicon - Healthcare in the 21st Century

Prof. Chris Van Hoof

Prof. Chris Van Hoof
IMEC Director, Wearable Health Solutions, IMEC Fellow, Belgium


Chris Van Hoof is Director of the Wearable Health Solutions activities at imec, where he is responsible for the R&D direction and business strategy of a multi-site R&D team across 3 imec locations (Eindhoven (the Netherlands), Leuven (Belgium) and Gent (Belgium)). Chris Van Hoof is also imec Fellow and full professor at the University of Leuven. Chris Van Hoof has a track record of over 25 years of initiating, executing and leading international R&D with worldwide customers in diverse fields (detectors and image sensors, microsystems, wireless sensors, energy harvesting, wearable healthcare, biomedical circuits, ...) and he has taken the healthcare activities at imec from early research to a major business line.
Chris Van Hoof is the author of more than 600 publications in journals and conference proceedings and has given over 70 invited and plenary talks at international conferences and symposia.


We are all enjoying an ever-increasing life expectancy and as a result are more susceptible to chronic diseases. Today, this effectively implies that we will be sick during a larger and increasing part of our lives. As a consequence, it is essential that we focus on creating building stones that will contribute to a longer and healthier life span through silicon technology. Wearable sensors have the grand promise and the largely untapped potential to become a cornerstone technology in the care and cure cycle as well as to enable true prevention. Wearable sensor technologies will seamlessly fit in the different phases of someone's life. For chronic patients, new wearable sensors are needed that improve the risk stratification, follow-up and management to monitor disease progression and prevent relapse, in cases like heart failure, sleep disorders and hypertension to name just a few. New personalized tools that help us to adopt and maintain a healthy life style are needed to tackle global grand challenges such as weight management, stress management and behavior change (such as smoking cessation). We need to invest in such a lifelong healthy future by leveraging state-of-the-art circuit and sensor technologies that enable true primary prevention based on accurate medical data. A virtual coach will be our lifelong companion to a healthier life, for our own generation as well as for the next! These efforts across the continuum of care will benefit the patient of today and may reduce the number of patients of tomorrow. The doctor of the future may no longer prescribe medication, he will for sure prescribe silicon sensors for prevention, cure and care of his patients.