Removing the memory bottleneck

Today’s computers are transforming almost all forms of human behaviour. In particular artificial intelligence based on machine learning is helping us work more effectively, improve healthcare, live happier lives and take more care of our environment. A fundamental part of all these computing systems is the memory needed to store data. This memory stores the data we use to train our AI machines and the subsequent program the machines use to perform their increasingly intelligent tasks, and the need for it is increasing relentlessly. It is perhaps surprising, therefore, to realise that today we cannot store this data on the same silicon chip we use do the computation. Today’s non-volatile memory technologies cannot be integrated with the most advanced CMOS processes we use to build our best computers. This is causing an increasingly challenging memory bottleneck.

Intrinsic is working to change this. We aim to deliver a non-volatile memory that can not only be easily integrated on the same chip that is doing the computation, but at memory that is faster, cheaper and lower energy than the Flash memory we use today.

To achieve this goal, Intrinsic has partnered with imec, a leading semiconductor R&D facility. Headquartered in Leuven (Belgium), imec leverages its state-of-the-art R&D infrastructure and its team of about 4,000 expert scientists, to drive open innovation. Imec unites the semiconductor value chain, including international industry leaders, to drive innovation in advanced semiconductor scaling. The aim of the project with imec is to transfer Intrinsic’s technology to a standard CMOS process on 300mm wafers. This project will demonstrate that the device performance already achieved by Intrinsic can be replicated at scale in standard CMOS production facilities.

Silicon-based resistive random access memory (RRAM) technology has the potential to become the backbone for the next generation of computers

THE MISSING
ELEMENT
The Missing Element

Intrinsic is a UCL spinout company, established to commercialise the novel memristive RRAM devices developed by Prof Tony Kenyon, Dr Adnan Mehonic and Dr Wing Ng at UCL’s Department of Electronic and Electrical Engineering.

The research that led to the demonstration of the RRAM devices was supported by EPSRC and UCL Business Proof of Concept funding. The team is also supported by the UCL Technology Fund as a recipient of funding through their Proof of Concept early stage investment.

UCLB
UCL Technology Fund

Dr Mark Dickinson – CEO

Prior to joining Intrinsic Mark held a number of senior and executive positions at leading semiconductor companies and brings a deep experience in IP licensing and development. He was most recently at Imagination Technologies where he was Executive Vice President responsible for the circa $100m PowerVR business unit. Prior to Imagination Mark was at ARM as VP/General Manager of the Mali GPU/multimedia business unit. Mark also spent many years as a vice president at Altera, an FPGA company now owned by Intel, where he built up the UK R&D team as well as running a world-wide system IP development group.

Mark’s technical background spans a wide range of semiconductor and electronics technologies and applications including artificial intelligence, graphics, multimedia, automotive and communications. Mark has a PhD in electronics (wireless communications) from Birmingham University and a degree in Physics from Oxford University.

Professor Tony Kenyon – Chief Scientific Officer

www.ucl.ac.uk/nanoelec-lab

Tony Kenyon is the Vice Dean (Research) for the Faculty of Engineering Sciences and Professor of Nanoelectronic & Nanophotonic Materials in the Department of Electronic & Electrical Engineering. His research interests include resistance switching; RRAM; neuromorphic devices; nanostructured materials for electronics and photonics; silicon photonics, and self-assembled nanoscale systems.

Professor Kenyon is a Fellow of both the Institute of Physics and the IET, a Senior Member of the IEEE, a member of the EPSRC ICT Strategic Advisory Team, and serves on the Executive Committee of the European Materials Research Society. He is the author of more than 100 peer-reviewed publications, and regularly gives invited talks at major international conferences.

Dr Adnan Mehonic – Chief Technical Officer

Adnan Mehonic is an Assistant Professor in Nanoelectronics and Research Fellow of Royal Academy of Engineering at the Department of Electronic & Electrical Engineering, UCL. He has authored more than 100 journal publications and international conference proceedings. Adnan’s research activities include the development of energy-efficient nanoelectronics and computing systems based on memristors.  He is particularly interested in ways to increase on-device processing by developing application-specific systems using a holistic approach (materials -> devices -> circuits -> algorithms -> applications) and by considering non-conventional methods for information processing such as spike-based computing.

He graduated in Electrical and Electronic Engineering from the University of Sarajevo, Bosnia in 2009 and was awarded the Golden Award Badge for the best student of the 2006-2009 cohort (~200 students). He received the MSc (Distinction) and PhD degrees in nanotechnology and electronic engineering from the University College London in 2010 and 2014, respectively, receiving the Oxford Instruments prize (the best MSc project) and being selected among the top 3 PhD graduated students in 2013/14 in E&E Department. In 2017, he has been awarded a highly prestigious 5-year Royal Academy of Engineering Research Fellowship (seven applicants are awarded annually from more than 130 applicants in the UK). He received the “One to Watch 2015” award from UCL Enterprise for UCL’s most innovative staff.

Dr Wing Ng – Staff Scientist

Dr Wing Ng is a Staff Scientist at Intrinsic and a Senior Research Fellow at the Department of Electronic and Electrical Engineering, University College London. He has extensive experience in the design and fabrication of novel semiconductor electronic and optoelectronic structures and devices at nanoscale, including memory devices, semiconductor lasers, and nano-electromechanical (NEMS) devices for optical storage applications. He holds a PhD degree in semiconductor physics from the University of Sheffield. Most of his PhD work was carried out at the National Centre for III-V Technologies (now National Epitaxy Facility) where he developed the first broadband quantum cascade laser operating above room temperature.

After working at a UK based scientific instrumentation company as an application engineer for several years, Wing moved to his current position at UCL and Intrinsic where he develops and fabricates novel metal oxide-based resistance memory devices. In the course of his work he has developed a novel fast electron beam lithography technique improving the patterning time by over an order of magnitude compared to conventional methods. He has published over 20 peer-reviewed papers in high impact journals and over 30 international conference proceedings. Wing is also a patent holder for a resistance memory technology developed at UCL.