This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies. Read our privacy policy>
This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies. Read our privacy policy>
Atlas 800 is best suited for real-time inference and training that demands high efficiency at low power consumption. It is perfect for video and image analytics and deep learning training. Configure it with up to eight Atlas 300 AI accelerator cards or AI accelerator module for any scenario and any inference requirement.
Provides 2 PFLOPS at FP16 in a 4U chassis, 2.5x the computing density of industry counterparts
Supports any combination of SAS/SATA/NVMe/M.2 SSD drives
Supports LAN on motherboard (LOM) and FlexIO cards, for more network interface options
Leverages the Atlas 300 dedicated decoding engine, for real-time transcoding and inference of up to 512 video streams
| Model | Atlas 800 AI Server Model: 3000 |
| Form Factor | 2U 2-socket rack server |
| Processors | 2 Kunpeng 920 processors |
| AI Accelerator Card | Up to eight Atlas 300 cards for 256-channel intelligent video analytics of people, vehicles, and things |
| Memory | 32 DDR4 DIMM slots with 2,933 MT/s |
| Internal Storage |
12-drive model: • Front: 12 x 3.5-inch SAS/SATA HDDs or SSDs • Rear: 4 x 3.5-inch SAS/SATA HDDs or SSDs 25-drive model: • Front: 25 x 2.5-inch SAS/SATA HDDs or SSDs,or 16 x 2.5-inch NVMe SSDs • Rear: 2 x 2.5-inch SAS/SATA HDDs or SSDs |
| RAID |
RAID 0, 1, 5, 6, 10, 50, or 60 (Optional) Supercapacitor for power failure protection |
| LOM Network Ports |
2 flexible LOM cards, supporting up to: 8 x GE electrical ports, or 8 x 25 GE/10 GE optical ports, or 4 x GE electrical ports + 4 x 25GE/10GE optical ports |
| PCIe Expansion |
Up to 8 PCIe 4.0 x8, or 3 PCIe 4.0 x16 + 2 PCIe 4.0 x8 slots |
| Power Supply Units | 2 x 1500/2000 W hot-swappable AC PSUs with 1+1 redundancy |
| Power Supply |
100–240 V AC 240 V DC |
| Fan Modules | 4 hot-swappable fan modules with N+1 redundancy |
| Operating Temperature | 5ºC to 40ºC (41ºF to 104ºF) |
| Dimensions (H x W x D) | 86.1 mm x 447 mm x 790 mm (3.39 in. x 17.60 in. x 31.10 in.) |
| Model | Atlas 800 AI Server Model: 3010 |
| Form Factor | 2U 2-socket rack server |
| Processors | 1 or 2 Intel® Xeon® Scalable Skylake or Cascade Lake processors, up to 205 W |
| AI Accelerator Card | Up to seven Atlas 300 or NVIDIA T4 AI accelerator cards for 448-channel intelligent video analytics of people, vehicles, and things |
| Memory | 24 DDR4 DIMM slots with 2,933 MT/s |
| Internal Storage |
Hard drive configurations: • 8 x 2.5-inch SAS/SATA HDDs or SSDs • 12/16/20 x 3.5-inch SAS/SATA HDDs • 4/8/12/24/28 NVMe SSDs • 31 x 2.5-inch SAS/SATA HDDs or SSDs Flash storage: • 2 M.2 SSDs |
| RAID |
RAID 0, 1, 10, 1E, 5, 50, 6, or 60 (Optional) Supercapacitor for cache power failure protection RAID level migration, drive roaming, self-diagnosis, and web-based remote configuration |
| Network Ports |
LOM: 2 x 10GE + 2 x GE ports FlexIO card: 2 x GE, 4 x GE, 2 x 10GE, 2 x 25GE, or 1/2 x 56G FDR IB ports |
| PCIe Expansion | Up to 10 PCIe 3.0 slots, including 1 for a RAID controller card and 1 for a FlexIO card |
| Fan Modules | 4 hot-swappable fan modules with N+1 redundancy |
| Power Supply Units |
2 hot-swappable PSUs with 1+1 redundancy Configurations: • 550 W AC Platinum PSUs • 900 W AC Platinum/Titanium PSUs • 1500 W AC Platinum PSUs • 1500 W 380 V HVDC PSUs • 1200 W –48 V to –60 V DC PSUs |
| Operating Temperature | 5ºC to 35ºC (41ºF to 95ºF) |
| Dimensions (H x W x D) |
Chassis with 3.5-inch hard drives: 86.1 mm x 447 mm x 748 mm (3.39 in. x 17.60 in. x 29.45 in.) Chassis with 2.5-inch hard drives: 86.1 mm x 447 mm x 708 mm (3.39 in. x 17.60 in. x 27.87 in.) |
| Model | Atlas 800 AI Server Model: 9000 |
| Form Factor | 4U 4-socket rack server |
| Processors | 4 Kunpeng 920 processors |
| AI Compute Power | 2 PFLOPS@FP16 |
| Encoding/Decoding Capability | Built-in 32 hardware decoders and is capable to decode 16384 1080P images per second in parallel with training |
| Cooling Mode | Air cooling and liquid cooling |
| Power Consumption | 2 PFLOPS/5.6 kW |
If you are already a Partner, please click here to get more marketing resources.
Click here to visit the Partner zone to check enquiry status, manage orders, get support, or learn more about Huawei Partners.
