Digital Emerging – FERRO4EDGEAI – Scalable, Ferroelectric-based Accelerators for Energy Efficient Edge AI – Horizon-Europe

Digital Emerging – FERRO4EDGEAI – Scalable, Ferroelectric-based Accelerators for Energy Efficient Edge AI – Horizon-Europe


Nick Barett of IRAMIS/SPEC is coordinator of the Horizon-Europe-CL4-2023 “Digital Emerging” project FERRO4EDGEAI – “Scalable, Ferroelectric-based Accelerators for Energy Efficient Edge AI”. This project brings together 12 European partners from 6 countries, including industrial companies (ST-Microelectronics in France, and 2 SMEs) to conduct research into low-energy components.

Following up the research carried out by IRAMIS to exploit the ferroelectric properties of thin films, the aim of FERRO4EDGEAI is to design an ultra-low-power, scalable peripheral booster for artificial intelligence, incorporating an augmented-memory neural network and based on integrated, low-cost, high-density, multi-level ferroelectric technology right through to the component connection step.

The project aims to achieve an energy efficiency gain of 2500x, breaking the peta-operations/s/W (Pops/w) barrier, well beyond the capacity of current CMOS boosters.

FERRO4EDGEAI Project Coordinator : Nick Barrett (SPEC/LENSIS)
Collaboration: CEA/Leti, NaMLab, INL, TU Delft, ST Microelectronics, FMC, SynSense…