To have a better experience, please upgrade your IE browser.upgrade
National Research and Education Network
Education Cloud Data Center
Government Service and Infrastructure
Digital Urban Rail
Enterprise Data Center
Server - Intelligent Computing
Enterprise Cloud Communications
Network Management System
Tackling the Emergency Together
Letting technology help in a time of need
Ubiquitous Connectivity Makes Digital Transformation Possible
Economical and Powerful AI Computing
Horizon Digital Platform
Connecting the Physical and Digital Worlds to Help Customers Achieve Successful Digital Transformation
F5G, Fibre to Everywhere
F5G and 5G Will Change Society
Leading New ICT
228 Fortune Global 500 Companies Choose Huawei as Digital Transformation Partner
Secure And Resilient Solutions
Buy from Huawei
If you want to get more information about your project, you can submit your information and we will contact you as soon as possible.
If your company has signed an eDeal contract with Huawei, please buy your required product/solution via the link below.
Buy from resellers
Search for a nearby reseller and get direct contact information.
Become a Partner
Resources and Support
Huawei Authorized Learning Partner
Huawei ICT Academy
Huawei ICT Competition
Enterprise Training Service
Atlas 900 AI Cluster
Representing the pinnacle of computing power, the Atlas 900 AI cluster consists of thousands of Ascend 910 AI processors. Leveraging the Huawei cluster communication library and job scheduling platform, it also integrates HCCS, PCIe 4.0, and 100G RoCE interfaces to fully unlock the computing power of the Ascend 910.
Atlas 900 delivers up to 256–1024 PFLOPS at FP16, equivalent to the computing power of 500,000 PCs. Test results show that Atlas 900 can complete model training based on ResNet-50 within 60 seconds, 15% faster than the next best product. This means faster AI model training with images and speech, more efficient astronomical and oil exploration, weather forecast, and faster time to market (TTM) for autonomous driving.
256–1024 PFLOPS at FP16, interconnecting thousands of Ascend 910 AI processors for the industry's fastest ResNet-50@ImageNet training (60s).
Integrates HCCS, PCIe 4.0, and 100G RoCE high-speed interfaces, and vertically integrates the communication library, topology, and low-latency network, achieving over 80% linearity.
Supports a hybrid cooling system capable of 50 kW heat dissipation per cabinet, with over 95% liquid cooling, and PUE < 1.1, reducing equipment room space by 79%.