Fraunhofer IPMS and imec are taking part in TEMPO (Technology & hardware for nEuromorphic coMPuting), a cross-border collaboration among 19 research and industrial partners, funded by ECSEL Joint Undertaking which supports public-private partnerships in the EU.
The three-year program intends to develop process technology and hardware platforms using emerging memory technologies for neuromorphic computing for future applications in mobile devices that demand complex machine-learning.
TEMPO is a unique collaborative effort to enable applications that now need cloud-based server racks, to be executed within battery-powered mobile devices including smartphones and cars (at the edge of the IoT).
Fraunhofer IPMS points out that increasingly, edge artificial intelligence and machine-learning algorithms are being adopted in day-to-day products and applications including autonomous vehicles, smart home assistants with natural-language processing, and face-recognition-based security systems.
Fraunhofer says that in the future, the demand for these increasingly complex computational algorithms will only grow further. Currently, high-end server parks process the data in the cloud. However, sending data to the cloud consumes energy, increases latency, and is often not preferred due to privacy issues . For this reason, the edge artificial intelligence applications demand intelligent energy-efficient local processing.
TEMPO intends to undertake this challenge by leveraging the process technology platforms that European research technology organizations and cooperating foundries in the project are developing. The collaborative effort will combine these process technology platforms with the application and hardware knowledge from additional partners.
The TEMPO project will assess the current solutions at device, architecture and application level. It will build and expand the technology roadmap for European AI hardware platforms.
The project plans to leverage MRAM (imec), FeRAM (Fraunhofer) and RRAM (CEA-Leti) memory to execute both spiking neural network (SNN) and deep neural network (DNN) accelerators for 8 different use cases, ranging from automotive and medical to consumer applications.
“It is our aim to sweep technology options, covering emerging memories, and attempt to pair them with contemporary (DNN) and exploratory (SNN) neuromorphic computing paradigms. The process- and design-compatibility of each technology option will be assessed with respect to established integration practices and meet our industrial partner roadmaps and needs to prepare the future market of Edge IA where Europe is well positioned with multiple disruptive technologies,” Emmanuel Sabonnadiere, CEO at CEA-Leti, said.
“A key enabler for machine learning and pattern recognition is the capability of the algorithms to browse through large datasets. Which, in terms of hardware, means having rapid access to large memory blocks. Therefore, one of the key focal areas of TEMPO are energy efficient nonvolatile emerging memory technologies and novel ways to design and process memory and processing blocks on chip,” Prof. Hubert Lakner, Director of the Fraunhofer Institute for Photonic Microsystems (IPMS) and Chairman of the Board of Directors of the Fraunhofer Group Microelectronics, commented.
“We are delighted to enter in such broad European collaboration effort on Edge Artificial Intelligence, gathering the relevant stakeholders in Europe, including CEA-Leti and Fraunhofer, two of our most renowned colleague research centers in Europe. Thanks to our combined expertise, we can scan more potential routes forward than what would be possible by each of us individually, and as such, position Europe in the driver seat for R&D on AI. Imec looks forward to the progress we can make together in the TEMPO project and hopes this will lead to more similar collaborations in the future. Behind the scenes, we are already defining more public and bilateral agreements with several of the partners involved,” Luc Van den hove, CEO at imec, said.
The TEMPO project received funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826655. The JU gets support from the European Union’s Horizon 2020 research and innovation programme, and from Switzerland, Netherlands, Germany, France, and Belgium.