Functionally scaled computing technology: From novel devices to non-von Neumann architectures and algorithms for a connected intelligent world
09/05/2019 – News: development of the first ever all-optical phase-change brain-like computing chip!
The Fun-COMP (Functionally scaled COMPuting technology) 4-year, 4 million euro project (grant #780848) involving seven academic and industrial partners – the Universities of Exeter, Oxford and Muenster, IMEC, C2C-CNRS, Thales-TRT and IBM Zurich. It runs from 2018 to 2022 and aims to develop ground breaking hardware technologies in the field of brain-inspired and non-von Neuman computing.
Future information processing and memory storage technology is being shaped by two main factors: (i) the ever-increasing demand of ubiquitous computing (e.g Internet Of Things and mobile devices), that will require small, flexible, power-efficient, connected devices and (ii) the rise of “big data”, pushing us to develop faster, less power-hungry and more intelligent hardware and software processing to enable us to extract and utilise relevant information from this abundant data .
The main objectives of Fun-COMP are to address these future computing imperatives by developing new electronic and photonic computing primitives (building blocks) and computing networks (architectures) that
- Fuse together the core information processing tasks of computing and memory
- Incorporate in hardware (not just in software) the ability to learn, adapt and evolve
- Can take advantage of the huge benefits, in terms of speed and power consumption, of the silicon photonics ‘revolution’
The description page provides a more detailed view of the project aims and plan.