TDK Corporation has announced the development of a neuromorphic element called a “spin-memristor” featuring a very low power consumption. Primarily, this element mimics the energy-efficient operation of the human brain. Thus, it could cut the power consumption of AI applications down to 1/100th of traditional devices.

Collaborating with the French research organization CEA (Alternative Energies and Atomic Energy Commission), TDK has proven that its “spin-memristor” can serve as the basic element of a neuromorphic device. Going forward, TDK will collaborate with the Center for Innovative Integrated Electronic Systems at Tohoku University on the practical development of the technology.

In recent years, digital transformation (DX) has advanced due to the development of AI. Moreover, it is predicted that energy consumption utilizing big data and AI will boom and make certain issues more apparent. Among them are the complexity around the computational processing of vast amounts of data and the increased power consumption associated with the development of AI. Along this line, TDK strives to contribute to solving these social and environmental issues.

The human brain requires around 20W of power. Accordingly, it enables more complex decisions than current digital AI processors, but with far lower power consumption. Therefore, TDK set itself a goal to develop a device that electrically simulates the synapses of the human brain: the memristor.

Conventional memory elements store data in the form of either 0 or 1. Meanwhile, a “spin-memristor” can store data in analog form, just as the brain does. This makes it possible to perform complex computations with ultra-low power consumption. Memristors for neuromorphic devices already exist. However, they face issues such as changes in resistance over time and difficulties in controlling the precise writing of data. Also, they need control to ensure that data is retained. TDK’s “spin-memristor” solves these issues. Moreover, it is expected to offer immunity to environmental influences and long-term data storage while reducing power consumption by cutting leakage current in existing devices.

AI Circuit with Spin-Memristor

To achieve this, TDK started collaborating with the CEA in 2020. With this support, they have developed an AI circuit equipped with a “spin-memristor” (3 elements × 2 sets × 4 chips). Subsequently, they confirmed its successful operation through a sound separation demonstration. Thus, they proved that “spin-memristors” can serve as basic elements in AI circuits. In the demonstration, even when three types of sound (music, speech, and noise) were mixed with arbitrary ratios, the circuit was able to learn and separate the three types of sound in real-time.

In general machine learning, AI operations are performed based on data that the AI model has previously been trained on. However, TDK’s device is uniquely capable of learning in a changing environment in real-time.

Now, it has been confirmed that the “spin-memristor” can serve as the basic element of a neuromorphic device. Thus, TDK will advance this project from basic development to the next stage, practical application. Moreover, the manufacturing of these products requires the integration of semiconductor and spintronic manufacturing processes. Specifically, this integration has been achieved in the manufacturing of MRAM, a product similar to memristors. Accordingly, TDK has decided to pursue integrated technological development on a joint basis with Tohoku University, a leading academic institution in MRAM research and development.

Dr. Marc Duranton, Senior Fellow of CEA, commented, “The synergy between TDK and CEA is remarkable, as our complementary expertise fosters a highly creative and constructive collaboration. This research partnership is breaking new ground to develop more sustainable, reliable, highly efficient solutions that will meet the growing demands of modern AI applications.”

Dr. Tetsuo Endoh, director of CIES Tohoku University, said, “AI semiconductors are extremely important for the information-oriented society of the future. However, the societal issues are improving AI processing power and reducing power consumption. In light of this social demand, TDK’s AI semiconductor development program, which fuses memristor and spintronics technology, is extremely important. We will do our best to contribute to this project with the academic knowledge held by Tohoku University and the manufacturing technology of the 12-inch prototype line.”

-03 October 2024-