The US government rolled out shedloads of red tape to prevent Nvidia from selling its A100 and H100 GPUs to Chinese clients. The rules limited GPU exports with chip-to-chip data transfer rates below 600 GBps.
With the A100, Nvidia trimmed the GPU's 600 GBps interconnect down to 400 GBps and rebranded it as the A800 to commercialise it in China. Nvidia is taking an identical approach to the H100.
According to Reuters' Chinese chip industry source, Nvidia reduced the chip-to-chip data transfer rate on the H800 to approximately half of the H100. That would leave the H800 with an interconnect restricted to 300 GBps. That's a more significant performance hit than compared to the A100 and A800, where the latter suffered from a 33 per cent lower chip-to-chip data transfer rate.
The H100 is substantially faster than the A100, which could be why Nvidia imposed a more severe chip-to-chip data transfer rate limit on the former.
Nvidia already has three of the most prominent Chinese technology companies using the H800: Alibaba, Baidu, and Tencent. China has banned ChatGPT; therefore, the tech giants are competing to produce a domestic ChatGPT-like model for the Chinese market.
An H800 with half the chip-to-chip transfer rate will be slower than what is offered across the pacific it will still not be slow. It is good for Nvidia too as companies potentially using thousands of Hopper GPUs, ultimately, we have to wonder if this will mean using more H800s to accomplish the same work as fewer H100s.