Frontier | Chou Xiaoxin of AXERA: High-computing-power chips will become the main growth engine for enterprises next year

In today's automotive industry, where cost reduction is increasingly emphasized, the balance in the minds of automakers is gradually tilting towards domestic chips with higher cost - effectiveness. Aixin Yuanzhi has spotted this development opportunity. In the early stage of the Beijing Auto Show, Aixin Yuanzhi, together with companies such as Qianli Technology and Jieyue Xingchen, established the "Qianli Alliance". Meanwhile, the company will release the M97, a high - computing - power assisted driving chip, in the third quarter of this year.

Qiu Xiaoxin, the founder of Aixin Yuanzhi, publicly stated at the Beijing Auto Show that "the high - computing - power product has been successfully taped out and is entering the normal development cycle." It will be gradually introduced into multiple vehicle models in 2026, becoming an important engine for performance growth. Currently, traditional terminal computing products still account for over 80% of Aixin Yuanzhi's revenue, while the revenue from in - vehicle and edge computing businesses accounts for a relatively low proportion. Qiu Xiaoxin expects that this situation will change in the next three years.

Qiu Xiaoxin is quite confident in the performance of the M97. She said, "The current mainstream high - level assisted driving chips have a relatively big problem, which is insufficient bandwidth. After we realized this problem, we significantly increased the bandwidth when designing the M97."

The effective computing power of an assisted driving chip mainly depends on two core factors. One is the scale of the computing unit, and the other is the bandwidth efficiency of data reading and writing. Even if the theoretical computing power of a chip is at a relatively high level, if the bandwidth is insufficient, its actual performance cannot be fully released. Qiu Xiaoxin said that one of the core advantages of the M97 is that it has a relatively high bandwidth level, which can allow the computing power to be more fully utilized while keeping the power consumption at a relatively low level.

In order to maximize the computing power potential of the chip, Aixin Yuanzhi said that the goal of leading the next generation was established at the initial stage of the chip design. The consideration behind this design concept is that the process technology has a decisive impact on the chip performance.

Taking the data transmission frequency as an example, there are obvious differences in the maximum frequencies that chips of different processes can support. The more advanced the process, the higher the achievable frequency, and the higher the bandwidth upper limit. For high - computing - power assisted driving chips, a more advanced process can not only bring better performance but also effectively reduce the chip area, thereby significantly improving the chip production yield.

As for why Aixin Yuanzhi sets the computing power of high - level assisted driving chips at a relatively high level, Qiu Xiaoxin told 36Kr that it is due to the uncertainty of the current assisted driving technology route. From the early end - to - end solutions to today's various advanced models, the core of assisted driving technology has always been the accurate understanding of the surrounding physical environment, which places extremely high requirements on the computing power of the chip.

Li Hao, the general manager of Aixin Yuanzhi's in - vehicle business department, said that the core purpose of simultaneously increasing the chip's computing power and bandwidth to the industry benchmark level is to provide sufficient effective computing power support for the in - vehicle applications of various advanced models. With the evolution of assisted driving technology, various models are developing towards integration and unification, and the computing power requirements for a single chip continue to increase. Therefore, Aixin Yuanzhi believes that increasing the computing power upper limit of a single chip is the trend of the future chip industry.

While increasing the computing power, Aixin Yuanzhi also emphasizes cost control. The cost of the chip is reduced through design. "For example, in the general architecture, it is a set of architectures inherited from cloud - based training all the way to in - vehicle chips, and there is a lot of redundancy in the overall architecture design. This is not necessary for in - vehicle chips."

A company's performance growth depends not only on products but also on strategies. Aixin Yuanzhi positions itself as "a relatively neutral third - party chip supply platform". Qiu Xiaoxin explained that the advantage of this positioning is that "at this time, automakers can choose us or others. The most important thing is to return the decision - making power to the automakers." "Having choices is still very important," and "as an independent chip company, Aixin Yuanzhi needs to maintain a neutral and independent state."

In addition to the in - vehicle field, edge computing is also an area where Aixin Yuanzhi plans to make key investments. In the second half of this year, Aixin Yuanzhi will release two edge computing products to better adapt to mainstream large models such as Qianwen in the market. Qiu Xiaoxin told 36Kr that building an ecosystem is very important for adapting to large models. One of the ways for Aixin Yuanzhi to build an ecosystem is that "whenever someone opens a large model, we will immediately deploy the large model on the chip. After deployment, we will open it up and put it on GitHub for partners to download. Since the underlying architecture of current large models is basically Transformer, it is beneficial for us to deploy various models as its underlying operators are relatively unified."

Regarding the implementation scenarios of edge computing chips, Aixin Yuanzhi has observed that AI Agents will be an area where the company can make great achievements. "In the future, when AI becomes more popular, water, electricity, gas, broadband, and computing power will become necessities in people's lives. How to connect this computing power into homes requires an AI Agent box, which may be part of a router."

Since the Agent has access to all the user's core information and needs to run 24/7, it must run locally. If it is connected to the cloud, there may be risks such as latency and privacy leakage. Aixin Yuanzhi's 8850 chip and the upcoming edge computing products can support large models to run on the edge side. Qiu Xiaoxin commented that AI Agents may be a ToC product with strong explosive power, and Aixin Yuanzhi is full of expectations for this field.