The “NeAIxt” research project is dedicated to the rapid expansion of artificial intelligence (AI) applications with a particular focus on edge AI and its integration into existing systems. Edge AI refers to the use of artificial intelligence directly at the point of data collection, i.e. at the edge of the network, instead of first sending the data to a central data center or a cloud. This enables real-time decisions with low latency, increased security and without a constant internet connection. The aim of the project is thus to strengthen European independence and control over edge AI technologies by developing innovative memory solutions, such as embedded non-volatile memories (eNVM), and high-performance, highly reliable microcontrollers with AI capabilities.
Fraunhofer IPMS is working on the further development of ferroelectric HfO2 materials as part of the project. Dr. David Lehninger, project manager at Fraunhofer IPMS, explains: “These materials can permanently store electrical polarization states and thus enable energy-efficient, non-volatile storage functions. These are an important element for future, reliable electronic solutions, including in the automotive sector.” The optimized ferroelectric layers are then embedded in existing X-FAB CMOS technologies. Building on this, Fraunhofer IPMS is developing new types of test chips that combine both non-volatile memory concepts and functions for AI acceleration. After production, the components are comprehensively electrically characterized and compared with established technologies in order to classify their performance and efficiency.
To complete the project, two demonstrators will be created: one is a non-volatile data memory based on ferroelectric HfO2 layers and the other is a hardware-based AI accelerator.
About the project
The “NeAIxt” project is funded by the EU as part of the “Chips Joint Undertaking” with total funding of 25 million euros. The close cooperation and exchange of knowledge between the project partners aims to create a European solution for reliable and independent edge AI applications. Research into energy-efficient computing is urgently needed, as without progress in this area, computing could account for a significant proportion of global energy consumption by the end of the 2030s. AI data centers with capacities in the gigawatt range are already being planned today. In this context, the project will run until August 2028 and promises not only to promote Europe’s innovative strength, but also to ensure independence in the research and integration of AI technologies. The extensive, multidisciplinary research project will help to consolidate European competitiveness in the global technology market and thus make an important contribution to Europe’s digital sovereignty.
About Fraunhofer IPMS
Fraunhofer IPMS is a leading international research and development service provider for electronic and photonic microsystems in the application fields of intelligent industrial solutions, medical technology and health, mobility as well as green and sustainable microelectronics. Research focuses on customer-specific miniaturized sensors and actuators, MEMS systems, microdisplays and integrated circuits as well as wireless and wired data communication. Research and development takes place in the clean rooms on 200 and 300 mm wafers. The services offered range from consulting and design to process development and pilot series production.
With the Center Nanoelectronic Technologies (CNT), Fraunhofer IPMS offers applied research on 300 mm wafers for microchip producers, suppliers, device manufacturers and R & D partners.
– – – – – –
Further links
👉 www.ipms.fraunhofer.de
Photo: Fraunhofer IPMS
