Tagged articles
AI supernode
10 articles · Page 1 of 1
Huawei's Atlas 850E is a 14U air-cooled AI supernode integrating eight Ascend 950DT NPUs and two Kunpeng 950 CPUs, delivering 14.27 PFLOPS at mxFP4 with 768GB HBM and 13.4 TB/s internal interconnect, using VCE phase-change cooling to enable 15.6kW deployment in standard 19-inch racks without liquid cooling infrastructure.
AI supernodeAscend 950DTAtlas 850E
0 likes · 12 min read

China Mobile Cloud unveils its Open Disaggregated Supernode (ODS) architecture, addressing five core challenges of traditional AI supernodes — hardware lock-in, proprietary interconnects, power/cooling limits, scale constraints, and maintenance complexity — through hardware disaggregation, open Ethernet/RoCE/FARE protocols, and optical circuit switching, achieving 50-90% power and cost reductions while enabling multi-vendor GPU clusters up to 128 cards per pod.
AI supernodeChina Mobile CloudFARE
0 likes · 6 min read

Ruijie's RG-ETH 128 supernode uses a dual compute-switch architecture with 51.2 Tb/s switch chips to scale from 64 to 128 GPUs per cabinet via Host Tray decoupling, and up to 1024 GPUs across cabinets through 32×800G expansion ports, with a roadmap from 112G copper SerDes to 224G and LPO→NPO→CPO optical interconnects.
AI supernodeGPU clusterHost Tray
0 likes · 7 min read

This article analyzes seven emerging Scale-Up interconnect technologies—UALink, SUE, ESUN, EthLink, ETH+, ETH-X, and CLink—that aim to replace proprietary NVLink for connecting hundreds of XPUs in AI supernodes, detailing their protocol stacks, header optimizations, and industry backing.
AI supernodeCLinkETH+
0 likes · 15 min read

The WAIC 2026 showcase introduced eight domestic AI supernodes—from Huawei’s 1024‑card Atlas 950 to New H3C’s scalable UniPoD S80000—detailing their card counts, interconnect bandwidth, FP8/FP4 performance, and how China’s AI compute evaluation is shifting from single‑chip peaks to system‑level efficiency and cost.
AI supernodeBiren TechnologyHuawei
0 likes · 12 min read

The article provides a technical breakdown of Huawei's UnifiedBus (Lingqu) interconnect protocol for AI supernodes, detailing its full‑stack design that unifies chip‑, board‑, and cabinet‑level communication, its three‑layer stack (PHY, Transaction, Service), resource‑scheduling and virtualization capabilities, and its deployment in Atlas950/960 SuperPod clusters.
AI supernodeAtlas950Huawei
0 likes · 5 min read

On May 30, 2026 Huawei released the Lingqu 2.0.1 specification, tightening protocol details, expanding heterogeneous compatibility, adding firmware and OS integration guides, and optimizing large‑scale routing to make the bus‑level, unified‑protocol, full‑pooling architecture more stable and ready for massive AI supernode deployments, while positioning it as an open alternative to Nvidia’s NVLink ecosystem.
AI supernodeHardware InterconnectHuawei
0 likes · 8 min read

The article explains what AI supernodes are, how they differ from traditional server clusters, and why their bus‑level interconnect, global memory pooling, peer‑to‑peer compute and integrated liquid‑cooled racks deliver up to 15× bandwidth gains, 4× inference concurrency, and significant cost reductions, while comparing the approaches of Nvidia, Huawei and other Chinese vendors and outlining future scaling challenges.
AI supernodeHigh-Performance ComputingHuawei
0 likes · 9 min read

The article explains the concept of SuperNode (SuperPod) as a new AI‑focused compute infrastructure, outlines its high‑density integration, ultra‑fast interconnects, and unified resource management, and compares three leading implementations from NVIDIA, Huawei, and the ETH‑X project.
AI infrastructureAI supernodeDGX SuperPOD
0 likes · 11 min read

Huawei’s 2025 Full‑Connection Conference unveiled the Atlas 950 and Atlas 960 SuperPoD supernodes, detailing their massive card counts, unprecedented compute, memory and bandwidth capabilities, and explaining how their full‑stack hardware‑software design dramatically accelerates large‑model AI training and inference.
AI supernodeAtlas 950Atlas 960
0 likes · 8 min read
