Gigabyte 2U G262-ZL0-G00 AMD EPYC™ 7003 processors DP SXM4 A100 4 GPU Server Liquid Cooling Solution

G262-ZL0 (rev. A00)

HPC Server - 2U DP SXM4 A100 4 GPU Server Liquid Cooling Solution  | Application: AI ,  AI Training ,  AI Inference  &  HPC 

• Liquid cooling GPU server solution
• Supports NVIDIA HGX™ A100 with 4 x SXM4 GPU
• Supports NVIDIA® NVLink® technology
• Up to 600GB/s GPU to GPU interconnection
• AMD EPYC™ 7003 processors with AMD 3D V-Cache™ Technology
• Dual AMD EPYC™ 7003 series processor family
• 8-Channel RDIMM/LRDIMM DDR4 per processor, 16 x DIMMs
• 2 x 1Gb/s LAN ports (Intel® I350-AM2)
• 1 x dedicated management port
• 4 x 2.5" Gen4 U.2 NVMe/SATA/SAS hot-swappable HDD/SSD bays
• Ultra-Fast M.2 with PCIe Gen4 x4 interface
• 5 x Low profile Gen4 x16 expansion slots
• 1 x OCP 3.0 Gen4 x16 mezzanine slot
• 3000W 80 PLUS Platinum redundant power supply

Nothing Stacks Up To EPYC™

AMD EPYC™ 7003 Processors with AMD 3D V-Cache™

AMD EPYC 7003 Series Processors with AMD 3D V-Cache™ technology are raising the bar once more for breakthrough performance on targeted technical computing workloads like Electronic Design Automation, Computational Fluid Dynamics, and Finite Element Analysis software and solutions. Delivering breakthrough performance per core and performance per watt, the Zen 3 architecture maintains leadership in number of cores – up to 64, amount of L3 cache – 768MB, and 128 PCIe 4.0 lanes, while maintaining socket compatibility with existing 3rd Gen AMD EPYC

High Performance

Supports NVIDIA HGX™ A100 4-GPU

Massive datasets, exploding model sizes, and complex simulations require multiple GPUs with extremely fast interconnections. NVIDIA HGX A100 combines NVIDIA A100 Tensor Core GPUs with high-speed interconnects to form the world’s most powerful servers. With A100 80GB GPUs, a single HGX A100 has up to 1.3 terabytes (TB) of GPU memory and over 2 terabytes per second (TB/s) of memory bandwidth, delivering unprecedented acceleration.

Hardware Security

Optional TPM 2.0 Module

For hardware-based authentication, the passwords, encryption keys, and digital certificates are stored in a TPM module to prevent unwanted users from gaining access to your data. GIGABYTE TPM modules come in either a Serial Peripheral Interface or Low Pin Count bus.

Power Efficiency

Automatic Fan Speed Control

GIGABYTE servers are enabled with Automatic Fan Speed Control to achieve the best cooling and power efficiency. Individual fan speeds will be automatically adjusted according to temperature sensors strategically placed in the servers.

High Availability

Smart Crises Management and Protection (SCMP)

SCMP is a GIGABYTE patented feature which is deployed in servers with non-fully redundant PSU design. With SCMP, in the event of faulty PSU or overheated system, the system will force the CPU into an ultra-low power mode that reduces the power load, which prevents the system from unexpected shutdown and avoids component damage or data loss.

Smart Ride Through (SmaRT)

To prevent server downtime and data loss as a result of loss of AC power, GIGABYTE implements SmaRT in all our server platforms. When such an event occurs, the system will throttle while maintaining availability and reducing power load. Capacitors within the power supply can supply power for 10-20ms, which is enough time to transition to a backup power source for continued operation.

User Friendly

Certified Ready with Software Partners

Being a member of key software alliance partner programs enables GIGABYTE to rapidly develop and validate joint solutions, enabling our customers to modernize their data centers and implement IT infrastructure and application services with speed, agility, and cost optimization.

OCP 3.0 Ready

GIGABYTE offers servers that feature an onboard OCP 3.0 slot for the next generation of add on cards. Advantages of this new type include:

• Easy Serviceability:
  Simply slot in or pull out the card, without opening the server or using tools
• Improved thermal design:
  Horizontal position and optimal heat sink design allow for air cooling to eliminate the heat efficiently

GIGABYTE Management Console

For management and maintenance of a server or a small cluster, users can use the GIGABYTE Management Console, which is pre-installed on each server. Once the servers are running, IT staff can perform real-time health monitoring and management on each server through the browser-based graphical user interface. In addition, the GIGABYTE Management Console also provides:

• Support for standard IPMI specifications that allows users to integrate services into a single platform through an open interface
• Automatic event recording, which can record system behavior 30 seconds before an event occurs, making it easier to determine subsequent actions
• Integrate SAS/SATA/NVMe devices and RAID controller firmware into GIGABYTE Management Console to monitor and control Broadcom® MegaRAID adapters.

Dimensions (WxHxD, mm)
2U
448 x 86.8 x 800

Motherboard
MZ62-HD5 Rev. 3.0

CPU
AMD EPYC™ 7003 processors with AMD 3D V-Cache™ Technology
AMD EPYC™ 7003 series processor family
Dual processors, 7nm
Up to 64-core, 128 threads per processor
cTDP up to 280W

NOTE: If only 1 CPU is installed, some PCIe or memory functions might be unavailable

Compatible with AMD EPYC™ 7002 series processor family

Socket
Socket SP3

Chipset
System on Chip

Memory
16 x DIMM slots
DDR4 memory supported only
8-Channel memory per processor architecture
RDIMM modules up to 128GB supported
LRDIMM modules up to 128GB supported
3DS RDIMM/LRDIMM modules up to 256GB supported
Memory speed: Up to 3200/2933 MHz

LAN
Front Side:
2 x 1GbE LAN ports (1 x Intel® I350-AM2)
1 x 10/100/1000 management LAN

Video
Integrated in Aspeed® AST2500
2D Video Graphic Adapter with PCIe bus interface
1920x1200@60Hz 32bpp, DDR4 SDRAM

Audio
N/A

Storage
4 x 2.5" Gen4 U.2 NVMe/SATA/SAS hot-swappable HDD/SSD bays

SAS card is required for SAS devices support

SAS
Depends on optional SAS Card

RAID
Depends on optional SAS Card

Peripheral Drives
N/A

Expansion Slots
4 x SXM4 sockets for NVIDIA HGX™ A100 4-GPU 40GB/80GB module

Total 5 x Low profile Gen4 x16 expansion slots
- Front Side: 1 x Low profile Gen4 x16 expansion slots
- Rear Side: 4 x Low profile Gen4 x16 expansion slots

1 x OCP 3.0 mezzanine slot with PCIe Gen4 x16 bandwidth from CPU_0

Supported NCSI function by onboard NCSI_SW

1 x M.2 slot: (Onboard)
- M-key
- PCIe Gen4 x4
- Supports NGFF-2280/22110 cards

2 x M.2 slots: (From CMTP072)
- M-key
- PCIe Gen4 x4
- Supports NGFF-2242/2260/2280/22110 cards

Internal I/O
1 x TPM header
1 x Front panel header

Front I/O
2 x USB 3.0
1 x mini-DP
2 x RJ45
1 x MLAN
1 x Power button with LED
1 x ID button with LED
1 x Reset button
1 x System status LED
1 x HDD access LED

Rear I/O
N/A

Backplane I/O
4 x 2.5" NVMe/SATA hybrid ports
Speed and bandwidth: PCIe Gen4 or SATA 6Gb/s

TPM
1 x TPM header with SPI interface
Optional TPM2.0 kit: CTM010

Power Supply
2‎ x 3000W redundant power supply
80 PLUS Platinum

AC Input:
- 115-127V~/ 14.2A, 50-60Hz
- 200-240V~/ 15.8A, 50-60Hz

DC Input:
- 240Vdc/ 14A

DC Output:
- Max 1200W/ 100-127V~
+ 54V/ 95.6A
+ 12Vsb/ 3.5A
- Max 3000W/ 200-240V~
+ 54V/ 178.1A
+ 12Vsb/ 3.5A

NOTE: The system power supply requires C19 type power cord

System Management
Aspeed® AST2500 management controller
GIGABYTE Management Console (AMI MegaRAC SP-X) web interface

Dashboard
HTML5 KVM
Sensor Monitor
(Voltage, RPM, Temperature, CPU Status …etc.)
Sensor Reading History Data
FRU Information
SEL Log in Linear Storage/Circular Storage Policy
Hardware Inventory
Fan Profile
System Firewall
Power Consumption
Power Control
LDAP / AD / RADIUS Support
Backup & Restore Configuration
Remote BIOS/BMC/CPLD Update
Event Log Filter
User Management
Media Redirection Settings
PAM Order Settings
SSL Settings
SMTP Settings

OS Compatibility
Windows Server 2016 (X2APIC/256T not supported)
Windows Server 2019
Windows Server 2022

Red Hat Enterprise Linux 8.3 (x64) or later
Red Hat Enterprise Linux 9.0 (x64) or later

SUSE Linux Enterprise Server 12 SP5 (x64) or later
SUSE Linux Enterprise Server 15 SP2 (x64) or later

Ubuntu 18.04.5 LTS (x64) or later
Ubuntu 20.04 LTS (x64) or later
Ubuntu 22.04 LTS (x64) or later

VMware ESXi 6.7 Update3 P03 or later
VMware ESXi 7.0 Update1 or later
VMware ESXi 8.0 or later

Citrix Hypervisor 8.2.0 or later

System Fans
2 x 60x60x76mm (21,700rpm)
2 x 80x80x80mm (17,000rpm)

Operating Properties
Operating temperature: 10°C to 35°C
Operating humidity: 8-80% (non-condensing)
Non-operating temperature: -40°C to 60°C
Non-operating humidity: 20%-95% (non-condensing)

NOTE: In the event that the room's relative humidity exceeds 60% then the inlet water temperature must be set between 40° to 45°C to avoid condensation and to keep the system running optimally

Packaging Dimensions
1077 x 679 x 300 mm

Packaging Content
1 x G262-ZL0
1 x Rail kit

Part Numbers
- Barebone with rail kit: 6NG262ZL0MR-00-A* (40GB module)
- Barebone with rail kit: 6NG262ZL0MR-00-G* (80GB module)
- Motherboard: 9MZ62HD5NR-00
- CPU liquid cooling kit: 25ST7-200006-C4R
- GPU liquid cooling kit: 25ST7-3000G3-C4R
- Rail kit: 25HB2-A86102-K0R
- Back plane board_2-port: 9COBP540NR-00
- Front panel board: 9CFP1000NR-00
- Fan module: 25ST2-667630-S1R/25ST2-808035-S1R
- Power supply: 25EP0-230003-D0S
- C19 type power cord 125V/15A (US): 25CP1-018000-Q0R (optional)
- C19 type power cord 250V/16A (EU): 25CP3-01830H-Q0R (optional)