Ferroelectric Memory Back Up Data Quickly And Energy-Efficiently

Related Vendors

FAULHABER Drive Systems

Taiwan Machine Tool & Accessory Builders' Association (TMBA)

SIMTOS (Seoul International Machine Tool Show)

Researchers at Fraunhofer IPMS have collaborated with GlobalFoundries to develop an energy-efficient FRAM memory technology and integrate it into chip manufacturing. It enables fast, non-volatile data storage and is relevant for applications such as edge AI.

Digital systems place high demands on memory: it must be fast, durable, non-volatile, and energy-efficient. In applications such as the automotive sector, industrial automation, and medical technology, existing memory solutions are reaching their limits. Researchers at the Fraunhofer Institute for Photonic Microsystems IPMS, in collaboration with GlobalFoundries, have developed a new memory technology that enables energy-efficient electronics and new computing architectures.

Ferroelectric Memory for Permanent Data Storage

At the heart of the system is a FRAM (Ferroelectric Random Access Memory) device that uses the ferroelectric material hafnium oxide to store information permanently. “In ferroelectric memory technology, ions are shifted very rapidly within a crystal lattice, which leads to a change in polarization. It is precisely this effect that can be used to store information,” explains Konrad Seidel, head of the Emerging Memory Solutions business unit at Fraunhofer IPMS. The information is retained even without power and can be read out as often as desired.

Integration into Industrial Chip Manufacturing

A key step is integrating the technology into existing industrial manufacturing processes. The researchers developed a reproducible method for embedding ferroelectric FRAM cells into GlobalFoundries’ 22FDX technology node. The memory cells operate at voltages below one volt, switch in a few nanoseconds, and exhibit high endurance.

“It’s a major milestone when you can demonstrate that what you’ve been researching intensively can actually be manufactured on a large industrial scale,” says Dr. Franz Müller, project leader at Fraunhofer IPMS.

The Foundation for Edge AI And New Applications

The technology is particularly relevant for applications where energy efficiency is critical—such as autonomous sensors, battery-powered systems, or artificial intelligence integrated directly into the device. “Power consumption is much lower with our non-volatile memory technology than with existing solutions. This makes it possible to use artificial intelligence not only in data centers but directly in edge applications,” explains Dr. Maximilian Lederer, Lead Scientist at Fraunhofer IPMS.

“An affordable ultra-low-power technology paired with a storage solution that’s ideally suited to it is particularly attractive for applications such as edge AI,” adds Dr. Sven Beyer of GlobalFoundries.

Collaborative Research As A Key to Success

The project was developed through a collaboration between Fraunhofer IPMS and GlobalFoundries at the Dresden site within the “Silicon Saxony” innovation ecosystem. The technology provides a foundation for energy-efficient electronic systems and enhances competitiveness in semiconductor manufacturing.

Future-Proof Authentication with Universal RFID Readers

Universal RFID Readers: One Solution for All Credentials