Progress in electronics performance has been achieved over the past 60 years via CMOS scaling, benefiting both mainstream design paradigms (analogue/digital). By virtue of operating in voltage (and continuous-time), analogue has been considered as inherently more powerful than the digital paradigm; however, over time scaling has favoured digital implementations over analogue in a rather disproportionate fashion. Yet nowadays, digital performance is also becoming increasingly difficult to pursue further due to fundamental physical scaling limitations. Simultaneously, reconfigurability has remained mainly in the domain of software engineering, relying for its physical implementation on dedicated memory blocks and progressively bottlenecked by power-hungry data transfers between physically separate memory and processing elements.

 

Recent advancements in nanotechnologies and smart materials have prompted the creation of a new class of devices which, compared to conventional CMOS transistors, are capable of achieving ‘more’ functionalities (e.g. multi-bit operation) for ‘less’ energy/space. The rich landscape of modern electronics design became even more diverse with the steady introduction of memristive technologies. The ability of memristors to act as electrically tuneable multi-level, non-volatile resistive loads, combined with their inherently scaling-friendly, low power and back-end integrable fabrication processes has rendered them a highly promising candidate for use in future electronics applications. These properties promote memristors as ideal candidates for achieving reconfigurability in a post-Moore and post-Von Neumann context, i.e. without relying on front-end integration density for performance and operating on the principle of separate, dedicated memory and processing elements. During this keynote, I will present how memristive technologies can be exploited in practical applications, with particular emphasis in the areas of memory and computation. I shall highlight the opportunities that this emerging technology brings for addressing the needs of modern massively parallel computing and identify the current challenges hindering their full potential.

Prof Prodromakis is Professor of Nanotechnology and Head of the Electronic Materials and Devices Research Group in the Zepler Institute, University of Southampton, UK. He is recognized as a pioneer of metal-oxide Resistive Random-Access Memory technologies and is leading an interdisciplinary team comprising 10 researchers with expertise ranging from materials process development to electron devices and circuits and systems for embedded applications. He holds an EPSRC Fellowship, a Royal Society Industry Fellowship and is a Visiting Professor at the Department of Microelectronics and Nanoelectronics at Tsinghua University, CN and Honorary Fellow at Imperial College London. He is Fellow of the IET, Fellow of the Institute of Physics, Senior Member of the IEEE and serves as the Director of the Lloyds Register Foundation International Consortium for Nanotechnology (ICoN: www.lrf-icon.com). In 2015, Prof Prodromakis established ArC Instruments Ltd, a start-up that delivers high-performance testing infrastructure for automating characterisation of novel nanodevices.