A new Germany-based startup, Semron, is revolutionizing mobile devices with their innovative “3D-scaled” chips, designed to run AI models directly on smartphones, earbuds, and VR headsets.
“Due to an expected shortage in AI compute resources, many companies with a business model that rely on access to such capabilities risk their existence – for example, large startups that train their own models,” says co-creator and engineering graduate from the Dresden University of Technology, Aron Kirschen.
Co-founded by Kirschen and fellow engineering graduate Kai-Uwe Demasius, Semron’s chips use electrical fields instead of traditional electrical currents to perform computations. This unique approach results in higher energy efficiency and lower fabrication costs.
“The unique features of our technology will enable us to hit the price point of today’s chips for consumer electronics devices, even though our chips are capable of running advanced AI, which others are not,” claims Kirschen.
Filing their initial patent in 2016, four years before founding Semron, Kirschen and Demasius utilized a somewhat unconventional component in their chips known as a “memcapacitor,” which is essentially a capacitor with memory. This allows the chips to control an electric field between a top electrode and a bottom electrode, greatly reducing the movement of electrons and resulting in less energy usage and heat production.
Kirschen explains, “We use this property as an enabler to deploy several hundred times the compute resources on a fixed silicon area. Think of it like hundreds of chips in one package.”
In a 2021 study published in the journal Nature Electronics, researchers at Semron and the Max Planck Institute of Microstructure Physics successfully trained a computer vision model at energy efficiencies of over 3,500 TOPS/W – a dramatic increase from existing techniques. However, this is just the beginning for Semron, as they are currently in the “pre-product” stage with minimal revenue.
Kirschen acknowledges the competition in the custom chip market, with companies like Kneron, EnCharge, and Tenstorrent already well-funded. But Semron has managed to attract investors such as Join Capital, SquareOne, OTB Ventures, and Onsight Ventures, and has raised 10 million euro (~$10.81 million) to date.
Georg Stockinger, partner at SquareOne, explains the importance of Semron’s technology:
“Computing resources will become the ‘oil’ of the 21st century. With infrastructure-hungry large language models conquering the world and Moore’s law reaching the limits of physics, a massive bottleneck in computing resources will shape the years to come. Insufficient access to computing infrastructure will greatly slow down productivity and competitiveness both of companies and entire nation-states. Semron will be a key element in solving this problem by providing a revolutionary new chip that is inherently specialized on computing AI models. It breaks with the traditional transistor-based computing paradigm and reduces costs and energy consumption for a given computing task by at least 20x.”
Semron currently has an 11-person workforce, with plans to expand to around 25 employees by the end of the year. They are determined to revolutionize the world of AI compute resources and pave the way for a more energy-efficient future.
