Huawei rotating chairman David Wang said on Thursday that the company plans to launch its 960DT processor in the first quarter of 2027, followed by the Ascend 960PR in the third quarter.
The planned chips are part of a broader Huawei strategy that goes beyond developing individual processors. The company is also investing heavily in technologies that allow large numbers of AI chips to be connected and operate collectively as a single, more powerful computing system.
That capability is becoming increasingly important as AI applications demand processing capacity that can exceed what a single semiconductor can deliver.
Speaking at a company event in Shanghai, Wang said Huawei's UnifiedBus technology would play a central role in the next generation of the company's large-scale AI systems.
The technology is designed to allow AI processors to communicate with one another and share data more efficiently, helping multiple chips function as a coordinated computing platform.
"Huawei's UnifiedBus technology would be a key link in the company's next generation of large AI systems," Wang said.
Huawei has developed 11 semiconductors based on UnifiedBus technology for use in its large computing systems, according to Wang. The company says its largest configurations, which it calls "superclusters", can support as many as 1 million AI processors.
The scale of those systems highlights the direction of Huawei's AI ambitions. Rather than relying solely on increasingly powerful individual chips, the company is seeking to combine large numbers of processors into interconnected systems capable of handling demanding AI workloads.
Huawei has also shipped more than 1,000 smaller interconnected systems, known as "supernodes", to more than 370 customers, Wang said.
A supernode combines multiple AI chips so that they can work on the same computing task. Wang did not disclose how many processors can be incorporated into an individual supernode, identify the customers receiving the systems or provide a detailed breakdown of shipments.
CHINA'S AI PUSH
Huawei's expansion comes as the United States and China compete over the technologies underpinning the global artificial-intelligence industry, including advanced processors, data centres and semiconductor manufacturing.
U.S. export controls have restricted China's access to certain advanced computing chips and semiconductor manufacturing equipment. In response, Chinese technology companies and policymakers have placed greater emphasis on developing domestic alternatives and improving the performance of locally available hardware.
The restrictions have also increased the importance of technologies that can link large numbers of processors together.
If Chinese companies have limited access to the most advanced foreign chips, combining larger numbers of domestically available processors could provide an alternative route to greater computing capacity. However, the effectiveness of such systems depends heavily on how quickly and efficiently the chips can communicate and exchange data.
This makes interconnect technology an increasingly important part of the AI hardware race.
Huawei has emerged as one of China's prominent suppliers of AI processors, with U.S. restrictions on advanced semiconductor technology helping to accelerate the country's efforts to develop domestic alternatives.
The company nevertheless faces Nvidia, the established leader in the global AI chip market. Nvidia's position has been strengthened not only by its powerful processors but also by the extensive software ecosystem surrounding its hardware, which is widely used by AI developers.
For Huawei, expanding its developer community will therefore be an important part of making its AI hardware more widely adopted.
Wang said Huawei's AI chip ecosystem currently has 5,270 monthly active developers.
The company is consequently pursuing a strategy that combines new processors, high-speed chip interconnection and a growing software and developer ecosystem.
Its planned 960DT and Ascend 960PR chips, alongside UnifiedBus-based systems, are intended to give Huawei greater capacity to compete in an increasingly strategic AI computing market while supporting China's broader drive for greater technological self-reliance.