Huawei''s SuperNode CloudMatrix384: Networking
Huawei''s 910C expansion relies on a hybrid optical + electrical interconnect, whereas NVIDIA primarily uses electrical interconnects. As
Contact UsHuawei 384 Optical Module
Home / Huawei 384 Optical Module
Huawei is gearing up to launch its CloudMatrix 384 rack-scale AI system, leveraging 384 Ascend 910C NPUs interconnected via an all-optical mesh network. It's designed to rival NVIDIA's GB200 NVL72, and early reports suggest it may achieve ~2× the throughput in BF16 compute. In the AI era, Huawei provides a full range of GE to 800GE optical modules, featuring three major capabilities: Spanning (ultra-long transmission), Stable (ultra-high reliability), and Secure (ultra-solid security). Deep dive into Huawei's AI super-node: 384 Ascend 910C chips, 6912×400G OSFP SiPh LPO modules (1:18 ratio), 1. On May 14, 2025, the "2025 Chip and Optical Forum" hosted by HiSilicon and organized by. Huawei's CloudMatrix 384 Supernode outperforms Nvidia's 180 PFLOPs NVL72 with 300 PFLOPs, higher memory bandwidth, and sanction‑proof design, fueling China's AI infrastructure ambitions. China's latest domestically developed cloud supercomputing solution, CloudMatrix M8, was officially unveiled.
