Xiaomi unveils its first 3nm smart-driving chip
Xiaomi has introduced its first internally developed semiconductor designed specifically to power intelligent driving systems in its electric vehicles, marking a major step in the Chinese technology company's growing ambitions in the automotive sector.
Known as the Xring D100, the new chip is manufactured using a 3-nanometer process. This advanced manufacturing technology allows a greater number of transistors to be integrated into a smaller area, potentially delivering higher computing performance while improving energy efficiency.
The D100 has been developed to handle artificial intelligence tasks directly inside the vehicle. Xiaomi plans to introduce the chip in commercial vehicles from 2027, although the company has not yet announced which model will be the first to use it.
The processor reportedly features 20 high-performance CPU cores and a 16-core neural processing unit designed for artificial intelligence workloads. It also supports unified memory of up to 160 GB, allowing sophisticated AI models to run locally inside the vehicle rather than relying heavily on external data centers.
This approach could reduce response times and improve the reliability of intelligent-driving functions by limiting dependence on cloud connectivity. However, Xiaomi has not yet disclosed the chip's official TOPS rating, a standard measurement used to assess the processing capacity of AI hardware.
Some unofficial estimates have suggested performance in the range of 700 to 1,000 TOPS, but these figures have not been confirmed by Xiaomi and should therefore be treated with caution.
The move reflects a broader trend among Chinese electric vehicle manufacturers toward developing proprietary automotive chips. Companies such as BYD, Nio and XPeng have also been investing in in-house semiconductor technology as the industry increasingly focuses on advanced driver-assistance systems and software-defined vehicles.
Xiaomi's decision could give the company greater control over the relationship between hardware and vehicle software. Developing its own processor may allow engineers to tailor computing resources more closely to the company's vehicles while potentially reducing long-term dependence on external suppliers.
Xiaomi's current electric vehicles, including the SU7 and YU7, have relied on third-party semiconductor solutions, including technology from Nvidia. Moving toward proprietary chips represents a significant change in strategy and requires substantial investment in research, testing and production.
The company has reportedly invested more than 21 billion yuan in its semiconductor development programme, with a team of around 3,000 engineers involved in the effort. Such investment highlights the financial and technical resources required to develop automotive-grade processors capable of operating safely under demanding real-world conditions.
Although the D100 has completed verification and laboratory testing, its commercial deployment will require further validation. The chip must operate reliably under varying temperatures and vibrations and integrate seamlessly with sensors, software, vehicle controls and safety systems.
If Xiaomi succeeds in bringing the D100 into production vehicles in 2027, the technology could strengthen its position in China's increasingly competitive electric vehicle market. The development also reflects a broader transformation in the automotive industry, where computing power, artificial intelligence and software are becoming as important to vehicle development as traditional mechanical engineering.
-
17:35
-
17:17
-
17:00
-
16:42
-
16:21
-
16:14
-
16:05
-
15:47
-
15:33
-
15:32
-
15:29
-
15:16
-
15:15
-
15:11
-
15:07
-
15:00
-
14:43
-
14:41
-
14:38
-
14:22
-
14:15
-
14:05
-
13:43
-
13:43
-
13:40
-
13:39
-
13:25
-
13:24
-
13:19
-
13:10
-
13:09
-
13:04
-
13:01
-
12:56
-
12:50
-
12:48
-
12:35
-
12:18
-
11:58
-
11:41
-
11:38
-
11:25
-
11:11
-
11:10
-
11:06
-
11:05
-
11:01
-
10:47
-
10:30
-
10:15
-
10:08
-
10:00
-
09:55
-
09:49
-
09:42
-
09:36
-
09:28
-
09:21
-
09:15
-
09:06
-
09:05
-
08:51
-
08:47
-
08:41
-
08:32
-
08:26
-
08:16
-
08:15
-
08:00
-
07:42
-
07:41
-
07:31
-
07:20
-
07:15
-
07:08
-
07:08
-
07:05
-
19:00
-
18:45
-
18:33
-
18:15
-
18:00
-
17:43