당사는 당사 사이트 및 사용자 경험을 개선하는 쿠키를 사용합니다. 당사 사이트를 계속 탐색하시면 쿠키 정책에 동의하는 것입니다.자세히 보기 >
If you need help, please click here:
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%.