Fired Response: Huawei Launches New AI Architecture, Rivals Nvidia

Is a tech war on our hands? Chinese companies may be facing the heat of the trade tariffs from the United States government, but Huawei is one company that is continuing on its path. According to recent reports, the company has launched a new artificial intelligence (AI) infrastructure architecture that is reportedly set to rival US chip giant Nvidia’s offerings in addressing computing power bottlenecks.

Introducing the CloudMatrix 384 Supernode 

The CloudMatrix 384 Supernode was introduced last week and was described by experts as a “nuclear-level product” that matched Nvidia’s NVL72 system in alleviating computing bottlenecks for AI data centres, STAR Market Daily reported on Monday, citing unnamed sources from Huawei.

In March last year, Nvidia launched the NVL72, featuring a 72-graphics processing unit (GPU) NVLink domain that functions as a single, powerful GPU, enabling real-time inference for trillion-parameter large language models (LLMs) at speeds 30 times faster than previous generations. The NVLink is also a high-speed interconnect technology developed by Nvidia that allows multiple GPUs to communicate with each other and share data more efficiently.

Computing Power

So far, Huawei’s new supernode, currently deployed in the company’s data centres in Wuhu, a city in central Anhui province, has achieved 300 petaflops of computing power. That's a vast difference compared with the 180 petaflops offered by Nvidia’s NVL72, the report said, citing data from Huawei.