With the new SuperPoDs and SuperClusters, Huawei’s rotating Chairman Eric Xu said the company has what it takes to provide abundant computing power for rapid advancements in AI
In sum – what to know:
Huawei outlines AI roadmap with SuperPoDs and SuperClusters – The company plans to launch its Atlas 950 in 2026 and Atlas 960 in 2027, scaling up to over one million Ascend chips.
UnifiedBus tackles interconnect bottlenecks – Huawei claims its proprietary protocol enables reliable, low-latency connections across massive SuperPoD deployments, addressing cable limitations in large-scale AI infrastructure.
SHANGHAI — Chinese vendor Huawei rotating chair Eric Xu unveiled the company’s roadmap for AI computing platforms, with plans to release what it claims to be the world’s most powerful single system in the last quarter of 2026 and double the performance with a new launch a year later.
In his opening keynote at the Huawei Connect event, taking place this week in Shanghai, China, Xu unveiled the company’s newest SuperPoD products: the Atlas 950 SuperPoD — with 8,192 Ascend chips, and the Atlas 960 SuperPoD with 15,488 Ascend chips. He explained that SuperPoDs are designed to operate as single logical machines, combining multiple physical units for large-scale AI workloads.
The executive said that the Atlas 950 SuperPoD will be available in the last quarter of 2026, while the Atlas 960 SuperPoD will hit the market in the last quarter of 2027.
Xu also stressed the importance of computing power for future AI development. “Computing power is, and will continue to be key to AI. This is especially true in China,” the executive said, adding that Huawei aims to meet long-term demand using semiconductor process nodes available on the Chinese market.
During the event, Xu also revealed Atlas 950 SuperCluster — with over 500,000 Ascend chips and Atlas 960 SuperCluster — with over one million Ascend chips, built from multiple SuperPoDs. The Atlas 950 SuperClusters will be available in the fourth quarter of 2026, while the Atlas 960 SuperCluster will be launched in the last quarter of 2027, Xu said.
“SuperPoDs and SuperClusters powered by UnifiedBus are our answer to surging demand for computing, both today and tomorrow. Our goal is to keep pushing advancements in AI to create greater value,” the executive added.
With the new SuperPoDs and SuperClusters, Xu said Huawei has what it takes to provide abundant computing power for rapid advancements in AI, adding that he believes that the two systems will set global benchmarks in key performance areas and remain the most powerful super nodes worldwide for years to come. He emphasized that Huawei sees their influence extending beyond AI, with the potential to deliver major benefits for general-purpose computing demand in China.
The Chinese company also noted that a major bottleneck for large-scale AI computing infrastructure is interconnect technology, namely the physical limitations of existing cable technology to link up massive numbers of chips and SuperPoDs over long distances while maintaining a reliable, high-speed, and low-latency connection. Huawei said it has overcome these challenges with UnifiedBus, an interconnect protocol for SuperPoDs.
“SuperPoDs and SuperClusters powered by UnifiedBus are our answer to surging demand for computing, both today and tomorrow,” said Xu.
