ECSEL JU Project StorAIge

The storAIge project will develop and industrialize the FD-SOI 28nm and the next generation embedded Phase Change Memory (ePCM) world-class semiconductor technologies. This will allow prototyping of high performance, ultra-low power, secured & safe System on Chip (SoC) solutions enabling competitive Artificial Intelligence (AI) for Edge applications. The main challenge addressed by the project is to handle the complexity of sub-28nm ‘more than Moore’ technologies and to bring them up to a high level of maturity, while handling the design of complex SoCs for more intelligent, secure, flexible, low power and cost-effective consumption. The project targets chipsets and solutions with very efficient memories and high computing power. 

The development of the most advanced automotive microcontrollers in 28nm FD-SOI ePCM will be the supporting technology to demonstrate the high performance as well as the robustness of the ePCM solution. The next generation of FD-SOI ePCM will be the main path for general purpose advanced microcontrollers, usable for large volume Edge AI applications in industrial and consumer markets, with the best compromise on three requirements: performance, low power, and adequate security. Furthermore, the project targets the development of hardware and software environments that will allow users to define architectures tailored to their specific needs. These architectures will support and make possible the introduction of artificial intelligence in a very large number of applications. 

On top of the development and industrialization of silicon process lines and SoC design, storAIge will also address new design methodologies and tools to facilitate the exploitation of these advanced technology nodes, particularly for high performance microcontrollers having AI capabilities. Work will be done to setup robust and adequate Security and Safety levels in the final applications, defining and implementing the good ‘mixture’ and trade-off between hardware and software solutions, to speed up adoption for large volume applications.