Nvidia DGX A100 Service Manual

NVIDIA DGX A100 Service Manual
Caution: Static Sensitive Devices: - Be sure to observe best practices for electrostatic discharge
(ESD) protection. This includes making sure personnel and equipment are connected to a common
ground, such as by wearing a wrist strap connected to the chassis ground, and placing components
on static-free work surfaces.
1. Power down the system.
2. Label all network, monitor, and USB cables connected to the motherboard tray for easy identi-
cation when reconnecting.
3. Unplug all power cords, and all network, monitor, and USB cables.
4. Remove the motherboard tray.
Refer to the instructions in the section Accessing the Motherboard Tray.
5. Unlock the horizontal network card.
1. Loosen the black thumbscrew that secures the PCIe card locking mechanism in place.
2. Open the locking mechanism by turning 90 degrees or more.
66 Chapter 14. Network Card Replacement

Nvidia DGX A100 Specifications

General

GPU	8 x NVIDIA A100 Tensor Core GPUs
System Memory	1 TB DDR4
Storage	15 TB NVMe SSD
GPU Memory	320 GB total (40 GB per GPU)
CPU	2 x 64-Core AMD EPYC 7742
Networking	8 x 200 Gb/s InfiniBand or Ethernet
Interconnect	NVIDIA NVLink