In a groundbreaking development poised to revolutionize the future of computing, Chinese scientists have created the world’s first carbon-based microchip capable of executing artificial intelligence (AI) tasks using an innovative ternary logic system. This achievement, led by researchers from Peking University and Beijing University of Posts and Telecommunications, represents a major leap in semiconductor technology, potentially overcoming the limitations of traditional silicon-based chips.
The new chip leverages carbon nanotubes (CNTs), a material renowned for its exceptional mechanical and electrical properties. CNTs, which are cylindrical structures made from graphene sheets, have primarily been used as conductive additives in lithium-ion batteries. However, their superior electrical conductivity, stability, and ultra-thin structure make them a promising candidate for next-generation semiconductors.
Unlike conventional silicon chips that rely on binary logic (using only zeros and ones), this carbon-based chip employs a ternary logic system, incorporating a third state. This advancement enables faster computations while consuming less energy, significantly improving data transmission efficiency within the same physical space.
The research team developed a novel carbon nanotube transistor using a concept called source-gated transistors (SGTs). By adjusting the gate voltage, the CNT transistor can switch between three distinct current states, forming the basis for ternary logic circuits. This design addresses key limitations of current chip technologies, particularly in power consumption and processing speed.
To demonstrate the chip’s capabilities, the researchers constructed a neural network that mimics the connections between neurons in the human brain. Extensive testing showed that the CNT-based neural network achieved perfect accuracy in classifying handwritten digits, highlighting its potential for AI applications such as image recognition and machine learning.
Peng Lianmao, a leading researcher and member of the Chinese Academy of Sciences, has been at the forefront of carbon-based chip technology for over two decades. His team has made significant strides in developing high-performance CNTs and achieving precise control over nanotube arrays. In 2020, they created an eight-inch CNT wafer that outperformed comparable silicon-based devices in integrated circuit performance, solidifying China’s leadership in carbon-based semiconductor research.
The new chip offers high efficiency, stability, and resistance to interference, making it ideal for high-performance computing, machine learning, AI, and low-power storage devices. It also holds promise for Internet of Things (IoT) applications, where energy efficiency is critical.
Despite these advantages, carbon nanotube chips currently lag behind silicon chips in integration density. For instance, Nvidia’s RTX 5090 GPU, announced in January 2025, contains 92 billion transistors, far surpassing the capabilities of current CNT technology. Nevertheless, carbon-based chips are seen as the next frontier in semiconductors, with China leading the charge.
Peng Lianmao expressed optimism about the future, aiming to make carbon nanotube-based chips mainstream within the next 10 to 15 years. If successful, this technology could replace silicon-based chips in various applications, from supercomputers and data centers to smartphones and other electronic devices. This transition would mark a transformative shift in the semiconductor industry, ushering in a new era of high-performance, low-power computing solutions.
