The Atlas 300T A2 training card cooperates with the server to provide powerful computing power for the data center, supports FP16 computing power, and accelerates the deep learning training process. Atlas 300T A2 has the characteristics of super computing power, high degree of integration, and high-speed bandwidth, meeting the computing power needs of education, scientific research, smart cities, finance, etc. that require artificial intelligence training.
Supports FP16 and FP32 computing power
Support 8 core * 2.0 GHz CPU computing power
AI computing power, general computing power, and I/O capabilities three-in-one
Integrated AI core, 8 CPU Cores, 1*200GE RoCE
Support PCIe 5.0 and 1*200G RoCE high-speed interface
No external network card is required, and the efficiency of training data and gradient synchronization is increased by 10%-70%.
| model | Atlas 300T A2 |
|---|---|
| form | Dual-slot full-height, full-length PCIe card |
| CPU computing power | 8core*2.0GHz |
| Codec capabilities | Supports 1080p 480FPS equivalent video decoding capability. Supports 1080p 12288FPS equivalent JPEG decoding capability.Supports maximum resolution 16384 * 16384, minimum resolution 32 * 32, supports 1080p 1024FPS equivalent JPEG encoding capabilitySupport maximum resolution 8192 * 8192, minimum resolution 32 * 32 |
| network | 1*200GE QSFP interface, supporting RoCE protocol |
| PCIe interface | PCIe5.0 |
| Maximum power consumption | 350W |
| Heat dissipation method | Passive air cooling |
| Working temperature | 5℃~45℃ (41℉~113℉) |
| structure size | 266.7mm (length) × 39.04mm (width) × 111.15mm (height) |
Reviews
There are no reviews yet.