Atlas 800 Inference Server (Model: 3010)
Flexible configuration for various workloads
Flexible configuration for various workloads
Atlas 800 Inference Server (Model: 3010)
Powered by the Intel processors, the Atlas 800 inference server (model: 3010) supports up to 7 Atlas 300I inference cards for 560-channel real-time HD video analytics. It is widely used for AI inference in data centers.
Flexible configuration for various workloads
• Supports any combination of SAS/SATA/NVMe/M.2 SSD drives
• Supports LAN on motherboard (LOM) and FlexIO cards, providing rich network interface options
Smart video analysis
• Supports up to 7 Atlas 300I inference cards and 560-channel real-time HD video analytics (1080p 25 FPSs)
Specifications
| Parameters | Atlas 800 Inference Server Model: 3000 |
| Form Factor | 2U AI server |
| Processor | 1 or 2 Intel® Xeon® Skylake or Cascade Lake Scalable processors, 205 W TDP |
| Processor Memory | 24 DDR4 DIMM slots, up to 3200 MT/s |
| AI Accelerator Card | Up to 7 Atlas 300I inference cards |
| Local Storage | • 8 x 2.5'' SAS/SATA drives • 12 x 3.5'' SAS/SATA drives • 8 x 2.5'' SAS/SATA + 12 x 2.5'' NVMe • 24 x 2.5'' SAS/SATA drives • 24 x 2.5'' NVMe • 25 x 2.5'' SAS/SATA drives |
| RAID | RAID 0, 1, 5, 6, 10, 1E, 50, or 60 |
| PCIe | 10 PCIe Gen3.0 (including 1 RAID controller card and 1 FlexIO) |
| Power Supply | 2 hot-swappable PSUs, with support for 1+1 redundancy. Supported options include: 550 W AC Platinum PSUs, 900 W AC Platinum/Titanium PSUs, and 1500 W AC Platinum PSUs 1500 W 380 V HVDC PSUs, 1200 W -48 V to -60 V DC PSUs |
| Fan Modules | 4 hot-swappable fan modules, supporting N+1 redundancy |
| Operating Temperature | 5°C to 45°C (41°F to 113°F) |
| Dimensions (H x W x D) | Chassis with 3.5'' drives: 748 mm x 86.1 mm x 447 mm Chassis with 2.5'' drives: 708 mm x 86.1 mm x 447 mm |