SpinAge, a unique approach for brain-inspired computing systems

November 25, 2022

SpinAge project is a unique approach for brain-inspired computing systems filling the gap between the performance of the best computing systems and the human brain. This will be achieved by the novel structures using spintronics and memristors, on-chip laser technology, nanoelectronics and finally advanced integration of all these technologies.

The brain is a highly complex, high-performance and low-energy computing system due to its massive parallelism and intertwined network. The brain outperforms the current computers by orders of magnitudes, especially for cognitive computing applications. A large effort has been made into understanding computing and mimicking the brain in an artificial implementation – the so-called neuromorphic computing systems (NCSs).

NCSs, as with the brain, use many parallel processors (neurons), communicating using simple messages (spikes) or continuous interactions (oscillations), mediated by programmable memory units (synapses).

The current implementation of NCSs using Complementary Metal-Oxide-Semiconductor (CMOS) technologies has very low performance and efficiency compared to the brain. This has driven a significant effort to investigate the development of NCSs beyond CMOS. Spintronic devices, using the spin of the electron instead of its charge, have been considered one of the most promising approaches for implementing NCSs leading to high density, high speed, and energy efficiency.

The team is working towards reaching at least 4-5 orders of magnitude better performance than the state-of-the-art NCSs based in CMOS. The breakthrough platform technology will demonstrate EU leadership of advanced neuromorphic computing.

SpinAge is a multidisciplinary project conducted by a strong consortium – the Spintronics research group at INL – International Iberian Nanotechnology Laboratory, together with Aarhus Universitet, Agencia Estatal Consejo Superior de Investigaciones Cientificas, NanoSC AB, Politecnico di Milano, University College Cork and Universitaet Greifswald.

This work was funded by the EU project SpinAge (No 899559).