Chinese researchers have made a significant breakthrough in artificial intelligence (AI) processing technology by unveiling the world’s first carbon-nanotube-based tensor processor chip.
Developed by a team from Peking University, this new processor addresses the growing limitations of traditional silicon-based semiconductors, which are increasingly inadequate for the data processing demands of modern AI.
The research findings were published on Monday in the journal Nature Electronics, in a paper titled “A carbon-nanotube-based tensor processing unit.”
The study introduces an innovative systolic array architecture that leverages the unique properties of carbon nanotube transistors and tensor operations. This architecture presents a potential solution to extend Moore’s Law, which predicts the doubling of transistors on a chip approximately every two years.
Traditional silicon-based computing chips face challenges related to further size reduction and escalating power consumption. Carbon nanotubes, renowned for their exceptional electrical properties and ultra-thin structures, have emerged as a promising alternative to overcome these hurdles.
Professor Zhang Zhiyong, a member of the research team, noted that carbon nanotube transistors outperform commercial silicon-based transistors in both speed and power efficiency. “These transistors offer a tenfold advantage, enabling the production of more energy-efficient integrated circuits and systems, which are crucial in the AI era,” he said.
This development marks a significant step forward in the quest for more efficient AI processing technologies, potentially revolutionizing the semiconductor industry and paving the way for future advancements in AI applications.
Reference(s):
China develops first carbon-nanotube-based tensor processor chip
cgtn.com