Server Platform Specs: NVIDIA_DGX_SuperPOD_GB200
Server and compute platform specifications for AI/HPC systems — NVIDIA DGX A100/H100/H200/B200/GB200 NVL72, NVIDIA DGX SuperPOD GB200, HPE ProLiant DL380 Gen11, and HPE ProLiant DL380a Gen11 GPU server. Includes GPU/CPU configuration, memory, storage, networking, power, physical dimensions, and thermal operating range.
| platform | spec category | ai performance desc | cpu model | gpu count | gpu model | network mgmt desc | network scale out desc | network scale up desc |
|---|---|---|---|---|---|---|---|---|
| NVIDIA_DGX_SuperPOD_GB200 | system_config | 8 compute racks; 1152 GPUs per SuperUnit (SU) | NVIDIA Grace CPU (in GB200 modules) | 576 | NVIDIA Blackwell GB200 GPU | NVIDIA SN2201 OOB management switch (48x 1Gbps) | 8x DGX GB200 NVL72 racks; NVIDIA Quantum QM9700 InfiniBand rail-optimized fat-tree; Spectrum-4 SN5600 Ethernet | NVLink 5 within rack; 8x NDR400 connections per system for cross-rack GPU comms |
This is a sample. Search the full server platform specs dataset and 350+ more by creating a free account and accessing the database.
Get started for FREE