Editor’s take: The Trump administration tried to curb China’s capacity to advance its computing capabilities by means of tariffs and different commerce restrictions. Nevertheless, this unprecedented commerce struggle might have as a substitute pushed Beijing to speed up its efforts in growing highly effective new AI programs.
As newly appointed US tech czar David Sacks predicted only a month in the past, Trump’s tariffs look like backfiring in spectacular style. Chinese language tech large Huawei is reportedly growing a robust AI system that may already compete with Nvidia’s most superior infrastructure within the race for the world’s quickest AI platforms.
Huawei publicly unveiled its new system, the CloudMatrix 384, on the current World Synthetic Intelligence Convention in Shanghai. The three-day occasion was filled with firms showcasing their newest AI improvements, and in accordance with Reuters, Huawei’s sales space was among the many most crowded and talked-about on the present.
Many attendees have been wanting to be taught extra in regards to the CloudMatrix 384, however Huawei officers declined to offer additional particulars. Whereas the system might have been on show primarily to generate buzz, sufficient info has emerged to offer us a clearer sense of the place Huawei – and China’s broader AI business – is likely to be heading.
In keeping with a current research by SemiAnalysis, Huawei’s CloudMatrix 384 is the corporate’s reply to Nvidia’s GB200 NVL72 – a flagship AI supersystem designed to run trillion-parameter fashions in actual time. Nvidia’s answer contains 36 Grace CPUs and 72 Blackwell GPUs, working collectively in a unified rack to perform as a single large GPU that dramatically accelerates massive language mannequin inference.
Whereas Huawei lags behind Nvidia and different Western corporations in superior silicon design, its engineers selected to compensate with scale and innovation somewhat than uncooked velocity. The CloudMatrix 384 incorporates 384 Ascend 910C chips, interconnected in an all-to-all topology to maximise efficiency. The Ascend 910C, designed by Huawei’s personal fabless semiconductor arm HiSilicon, successfully combines two Ascend 910B processors to ship efficiency on par with Nvidia’s H100 GPU.
A completely configured CloudMatrix 384 can attain 300 petaFLOPs of dense BF16 compute, almost double the compute capability of Nvidia’s GB200 NVL72. It additionally boasts 3.6× better complete reminiscence capability and a pair of.1× extra reminiscence bandwidth.
SemiAnalysis famous in April that with additional yield enhancements, Huawei might quickly outpace Nvidia – and by extension, the USA – within the AI race. The foremost caveat? Energy consumption. The CloudMatrix 384 requires greater than 4 occasions the power wanted to run a GB200 NVL72 at full capability.
Nevertheless, not like many Western international locations, China has been aggressively increasing its energy era infrastructure utilizing coal, photo voltaic, hydro, wind, and different sources.
