COMUNICATO STAMPA – CONTENUTO PROMOZIONALE
SHANGHAI, Sept. 21, 2026 /PRNewswire/ — In a keynote speech on computing architecture innovation at HUAWEI CONNECT 2026, Yang Chaobin, Huawei’s Executive Director of the Board and CEO of the ICT Business Group, unveiled new details about the UnifiedBus interconnect architecture, announced a series of computing products based on this architecture, and explained how the company has collaborated with open-source communities to enable application innovation by customers, partners, and developers.
In a traditional computing architecture, resource utilization declines as a cluster scales. As little as 20% of a 100,000-NPU cluster’s computing capacity is actually utilized by models, with a vast amount of compute sitting idle during data communications. A 10 trillion-parameter model, which requires massive amounts of intermediate data to train, far exceeds the capacity of the memory on a single accelerator under traditional architectures. Interconnection and communications between components within a cluster have become a key performance bottleneck for computing systems.
According to Yang, Huawei’s solution to this bottleneck is its new computing architecture, powered by the interconnect technology called UnifiedBus, which facilitates collaboration between clusters and SuperPoDs. This architecture has been designed to support the boom in compute demand that is emerging as new agentic applications hit the market. UnifiedBus-powered computing systems have four key features:
Yang then moved on to unveil Huawei’s newest UnifiedBus interconnect products that cover interconnection within cabinets, between cabinets, and across clusters. This enables elastic scaling from a single cabinet to a million-NPU cluster.
Yang also launched Huawei’s UnifiedBus-powered agentic AI SuperCluster, which is comprised of TaiShan 950 and Atlas 960 SuperPoDs, OceanStor M900 memory storage, and a Xinghe UBG switch. This cluster enables diverse compute collaboration and tiered resource pooling.
Beyond SuperPoDs, Huawei has also applied the UnifiedBus technology to its compute appliances. The company has developed a new series of UnifiedBus-based appliances (supporting one to eight NPUs) and Kunpeng and Ascend modules, which enable small and medium-sized enterprises to run trillion-parameter models locally.
On the ecosystem front, Yang said that Ascend is collaborating with open-source frameworks like DeepSeek Harness, OpenCode, and openJiuwen to develop fully open-source intelligent management, inference acceleration, and security framework agent plugins.
Yang promised, “Huawei is committed to innovating at the system level, building a computing-foundation product portfolio, and going open source and open system. We will continue working with customers, partners, and developers to help this ecosystem thrive and offer the world a new option for compute.”
View original content to download multimedia:https://www.prnewswire.co.uk/news-releases/huawei-unveils-new-unifiedbus-computing-architecture-for-superpods-and-clusters-302884545.html
Copyright 2026 PR Newswire. All Rights Reserved.
COMUNICATO STAMPA – CONTENUTO PROMOZIONALE: Immediapress è un servizio di diffusione di comunicati stampa in testo originale redatto direttamente dall’ente che lo emette. L’Adnkronos e Immediapress non sono responsabili per i contenuti dei comunicati trasmessi
—
immediapress
