Description
NVIDIA DGX™ A100 is the universal system for all AI workloads, offering unprecedented compute density, performance, and flexibility in a 5 petaFLOPS AI system. NVIDIA DGX A100 features the world’s most advanced accelerator, the NVIDIA A100 Tensor Core GPU, enabling enterprises to consolidate training, inference, and analytics into a unified, easy-to-deploy AI infrastructure that includes direct access to NVIDIA AI experts.
General Information
| Manufacturer |
NVIDIA |
| Manufacturer Part Number |
DGXA-2530F+P2CMI00 |
| Product Line |
DGX |
| Product Name |
DGX A100 |
| Product Type |
Graphics Computing System |
Processor
| Quantity Installed |
2
|
| Manufacturer |
AMD |
| Type |
EPYC |
| Model |
7742 |
| Socket |
LGA 4094 |
| Cores |
64-Core |
| Speed |
2.25 GHz |
GPU
| Quantity Installed |
8 |
| NVIDIA NVSwitches |
6 |
| Architecture |
Ampere |
| Chipset Model |
A100 |
| Processor Cores |
432 Tensor
6912 CUDA |
| GPU Memory |
640 GB (8x Ampere A100 80 GB) |
| Technology |
SXM4 NVLINK |
Memory
| Capacity |
2TB |
| Memory Voltage |
DDR4-3200/PC4-25600 |
Storage
Total Drive Capacity
|
OS: 2x 1.92TB M.2 NVMe
Internal Storage: 8x 3.84TB U.2 NVMe (30TB)
|
| Type |
Solid State Drive |
Network
Networking
|
8x Single-Port Mellanox ConnectX-6 VPI 200Gb/s HDR InfiniBand
2x Dual-Port Mellanox ConnectX-6 VPI 10/25/50/100/200Gb/s Ethernet |
Software
Operating System
|
Ubuntu Linux OS |
Power
Dimensions
| Form Factor |
Rackmount |
| Rack Height |
6U |
| Height |
10.4" (264.0 mm) |
| Width |
19.0" (482.3 mm) max |
| Depth |
35.3" (897.1 mm) max |
| Weight |
271.5 lbs (123.16 kg) max |
| Packaged Weight |
359.7 lbs (163.16 kg) max |
