Introduction to Huawei’s Ascend Chip Line
Chinese technology giant Huawei announced its plans for the next generations of its Ascend chip line at the Huawei Connect 2025 event in Shanghai. In his keynote to the conference, deputy chair of the Huawei board, Eric Xu, said that 2025 had been a “memorable year,” and noted the debut of DeepSeek-R1 in January as a turning point for the company. He also acknowledged that China is likely to lag behind in semiconductor manufacturing process nodes, “for a relatively long time.”
Response to Tariffs and Trade Embargoes
The company’s response to tariffs and trade embargoes is to advance infrastructure design and technology, plus it’s made the decision to open-source several large swathes of its software, including the openPangu foundation AI models and the Mind series SDKs. This move is expected to help the company stay competitive in the global market.
The New Ascend Chip Line
The company plans to produce three new series of the Ascend chip, the 950, 960, and 970. The Ascend 950PR and 950TO will be cast from the same die, and provide additional support for low-precision data formats, including FP8 – where the 950 will deliver a PFLOP of performance, and MXFP8, rated at two PFLOPs. A PFLOP is one thousand trillion floating-point calculations per second.
Key Features of the Ascend 950 Chip
The Ascend 950 chips will offer 2 TB/s interconnect bandwidth, 2.5x more than the current Ascend 910C. The 950PR will be available Q1 2026, and the Ascend 950DT launches Q4 2026. The new chips will also have better vector processing, and more granular memory access, down to 128 byte chunks from 512 bytes.
Ascend 960 and 970 Chips
Available a year later in Q4 2027, the Ascend 960 will have twice the computing power, memory access bandwidth, memory capacity, and number of interconnect ports as the 950. It will support Huawei’s proprietary HiF4 data format, which, the company claims, brings greater precision than other FP4 technologies. The most capable chip will be the Ascend 970, slated for release Q4 2028. Xu said, “We’re still working on some of its specs, but our general goal is to push all of its specs much higher.”
SuperPods of NPUs
Huawei’s strategy is to offer hyperscalers clusters of raw compute in the form of SuperPoDs, which will appear begin to appear Q4 2026 in the form of the Atlas 950 SuperPoD, equipped with the new Ascend 950DT chips. Competitor NVIDIA’s NVL144 system (a SuperPod analogue) will launch mid- to late-2026, and Huawei claims that its first SuperPoD will have 56.8 times more NPUs than GPUs in the NVL144, and deliver nearly seven times the processing power.
General Computing Chips
For general computing, Huawei plans to release two models of its Kunpeng 950 processors in Q1 2026, sporting 96 cores & 192 threads, and 192 cores & 384 threads in the faster of the two models. There will also be what Xu called “the world’s first general-purpose computing SuperPoD,” the Kunpeng 950-based TaiShan 950 SuperPod, which will be available in the first quarter of 2026.
Open-Source Connectivity Protocol
The NPU and general computing SuperPoDs will use UnifiedBus 2.0, the next iteration of the existing UnifiedBus 1.0. That’s the interconnection technology used by the Atlas 900 A3 SuperPoD, which came into service in March this year, with over 300 installations to date. UnifiedBus 2.0 is to be an open protocol, with the tech specifications released immediately to the developer community.
Conclusion
Huawei’s new Ascend chip line and SuperPods are expected to revolutionize the computing industry. With their advanced features and open-source connectivity protocol, they are poised to take the lead in the global market. The company’s decision to open-source its software is also expected to drive innovation and collaboration in the industry.
FAQs
Q: What is the Ascend chip line?
A: The Ascend chip line is a series of chips developed by Huawei for artificial intelligence and machine learning applications.
Q: What is the difference between the Ascend 950, 960, and 970 chips?
A: The Ascend 950, 960, and 970 chips have different levels of computing power, memory access bandwidth, and memory capacity.
Q: What is a SuperPod?
A: A SuperPod is a cluster of raw compute that offers hyperscalers a high-performance computing solution.
Q: What is UnifiedBus 2.0?
A: UnifiedBus 2.0 is an open-source connectivity protocol that enables the connection of multiple SuperPods to form a SuperCluster.
Q: When will the new Ascend chips and SuperPods be available?
A: The Ascend 950PR will be available Q1 2026, and the Ascend 950DT launches Q4 2026. The Atlas 950 SuperPoD will appear Q4 2026, and the Atlas 960 SuperCluster will launch Q4 2027.
