NVIDIA RTX PRO™ Server - 6U DP 8 x NVIDIA RTX PRO™ 6000 Blackwell Server Edition GPUs DLC - XLS4-SX2-LAS1

1/6

XLS4-SX2-LAS1

NVIDIA RTX PRO^™ Server - 6U DP 8 x NVIDIA RTX PRO^™ 6000 Blackwell Server Edition GPUs DLC

AI Visual Computing HPC AI Training AI Inference

Liquid-cooled NVIDIA RTX PRO^™ Server with ConnectX^®-8 SuperNIC^™ switch
Configured with 8 x liquid-cooled NVIDIA RTX PRO^™ 6000 Blackwell Server Edition GPUs
Configured with 1 x NVIDIA BlueField^®-3 DPU
Onboard 400 Gb/s NVIDIA InfiniBand Ethernet QSFP ports with PCIe Gen6 switching for peak GPU-to-GPU performance
Dual Intel^® Xeon^® 6700/6500-Series processors
8-Channel liquid-cooled DDR5 RDIMM/MRDIMM per CPU with 32 x DIMMs
8 x E1.S Gen5 NVMe hot-swap bays
2 x M.2 slots with PCIe Gen5 x4
2 x FHFL PCIe x16 slots with Gen5 x16 lanes
6 x 3200 W 80 PLUS Titanium redundant power supplies

Trăsături cheie

Save

Quote

Boosting Individual Applications with On-Point Features

Intel^® Xeon^® 6 is a new generation of processors that has tailored its CPU lineup to target all uses cases such as Cloud Computing, AI, Analytics, and Edge & IOT. Whether it's high compute density that is dependent on core count and power efficiency or AI/HPC applications that heavily rely on strong single-core performance, this new platform covers them all with its Performance cores (P-cores) and Efficient-cores (E-cores). Along with flexible I/O options, integrated accelerators, and support for CXL 2.0 devices, Intel Xeon 6 fulfills customer needs across the broadest range of data center workloads, segments, and deployment models.

Core Technology Aligned with Aspirations

Accelerators

built-in*

Incredible performance and efficiency improvements with the easy adoption of on-chip accelerators

8 or 12

Channels

Increased memory frequency and throughput with DDR5 RDIMM support

PCIe 5.0

lanes

Up to 136 lanes for 1S designs, supporting all the latest drives and accelerators

CXL 2.0

support**

Flexible support between PCIe and CXL, utilizing DDR5 and CXL memory as one unified region

Up to 288

E-cores per CPU

Core dense and optimized efficiency for cloud-native and hyperscale workloads

Intel Xeon 6 Processors with E-cores

Up to 128

P-cores per CPU

Greater core performance with improved TCO, accelerating AI and compute intensive workloads

Intel Xeon 6 Processors with P-cores

MRDIMM

support

Unprecedented frequency on the advanced MRDIMM, boosting memory-intensive application to a whole new level

Intel Xeon 6 Processors with P-cores

* Different on-chip accelerators are supported depending on CPU SKUs, and they require a one-time activation. Please visit Intel's official website or contact technical support for details.

** CXL peripheral support varies by product. Please refer to the QVL list for validated configurations.

Select GIGABYTE for the latest Gen Intel Xeon Platform

High CPU Performance

The best in computational performance relies on a system well designed by our engineers to adequately dissipate heat to achieve peak performance.

Energy Efficiency

Our engineers have baked in features to achieve higher efficiency from power supplies and server fans. Along with Titanium and Platinum offerings.

Optimal Price

GIGABYTE releases multiple product models and configurations to target exactly what users want without paying for extra features that go unused.

Ease of Administration

GIGABYTE servers come with GIGABYTE Management Console for server management. Using a web based browser remotely is key to easing management.

Continuous Operation

Systems are rigorously designed and tested to ensure downtime will not occur. Customers have come to expect stable performance.

XLS4-SX2-LAS1 Block Diagram

XLS4-SX2-LAS1 Product Overview

NVIDIA RTX PRO™ Server with ConnectX^®-8 SuperNIC Switch

Universal data center platform for enterprise AI and AI factories

From breathtaking architectural and industrial design to advanced visual effects, complex scientific simulations, and cutting-edge AI workloads like fine-tuning large language models and running secure local AI agents, the NVIDIA RTX PRO™ platform is the core of the world's most powerful and efficient professional computing infrastructure.

Built on the NVIDIA MGX™ architecture, the XLS4-SX2-LAS1 is configured with eight NVIDIA RTX PRO™ 6000 Blackwell Server Edition GPUs, plus an additional single-slot x16 expansion configured with a NVIDIA^® BlueField^®-3 DPU. Up to eight GPUs can be configured in the GIGABYTE server with an integrated NVIDIA ConnectX^®-8 SuperNIC switch board debuts with four of the latest SuperNICs with 800Gb/s bandwidth and PCIe Gen6 connectivity to deliver high throughput and better scale-out capabilities.

NVIDIA RTX PRO™ 6000 Blackwell Server Edition

The NVIDIA RTX PRO™ 6000 Blackwell Server Edition is the ultimate universal data center GPU, delivering breakthrough multi-workload acceleration for the most demanding generative AI, graphics, and video applications.

With 96 GB of ultra-fast GDDR7 memory and data center-optimized design, the RTX PRO 6000 Server Edition delivers the performance, scalability, and reliability required for enterprise deployments while providing unmatched levels of compute power, memory capacity, and throughput to power mission-critical AI-enabled applications and accelerate use cases across industries.

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.

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.

User Friendly

Tool-less Drive Bays Design

Clipping mechanism secures the drive in place. Install or replace a new drive in seconds.

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.

High Availability

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.

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.

Dual ROM Architecture

If the ROM that stores the BMC and BIOS fails to boot, the system will reboot with the backup BMC and/or BIOS replacing the primary. Once the primary BMC is updated, the ROM of the backup BMC will automatically update the backup through synchronization. For the BIOS, it can be updated based on user's choice of firmware version.

Value-added Management

GIGABYTE offers free-of-charge management applications via a specialized small processor built on the server.

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.

GIGABYTE Server Management (GSM)

GSM is a software suite that can manage clusters of servers simultaneously over the internet. GSM can be run on all GIGABYTE servers and has support for Windows and Linux. GSM can be downloaded from GIGABYTE website and complies with IPMI and Redfish standards. GSM includes a complete range of system management functions that includes the following utilities:

GSM Server: A software program that provides real-time, remote control using a graphical user interface through an administrator’s computer or through a server in the cluster. The software allows ease of maintenance for large clusters of servers.
GSM CLI: A command-line interface for monitoring and managing remotely.
GSM Plugin: An application program interface that allows users to use VMware vCenter for real-time monitoring and management of server clusters.

Specificații

Dimensions (WxHxD, mm)

6U
438 x 264 x 805

Motherboard

MSX4-MG2

CPU

Intel^® Xeon^® 6 processors
- Intel^® Xeon^® 6700-Series processors
- Intel^® Xeon^® 6500-Series processors

^[DLC]Dual processors, TDP up to 350 W

^[Note]If only 1 CPU is installed, some PCIe or memory functions might be unavailable.

Socket

2 x LGA 4710
Socket E2

Chipset

System on Chip

Memory

^[DLC]32 x DIMM slots
Support DDR5 RDIMM/MRDIMM^[1]
8-Channel memory per processor
RDIMM: Up to 6400 MT/s (1DPC), 6000 MT/s (2DPC)
MRDIMM: Up to 8000 MT/s

^[1]MRDIMMs are supported only on select Intel^® Xeon^® 6 processors with P-cores and only in a 1DPC configuration.

LAN

Front (ConnectX^®-8 SuperNIC^™ switch board):
8 x QSFP ports (400 Gb/s InfiniBand/Ethernet, for GPU networking)

Front (I/O board):
1 x 10/100/1000 Mb/s Management LAN

Video

Integrated in ASPEED^® AST2600
- 1 x Mini-DP

Storage

Front hot-swap:
8 x E1.S Gen5 NVMe
- (4 x NVMe from CPU_0, 4 x NVMe from CPU_1)

Internal M.2 (M.2 expansion card):
2 x M.2 (2280/22110), PCIe Gen5 x4, from CPU_0

PCIe Expansion Slots

ConnectX^®-8 SuperNIC^™ switch board:
- ^[DLC]8 x NVIDIA RTX PRO^™ 6000 Blackwell Server Edition GPUs

PCIe Cable x 3:
- 1 x NVIDIA BlueField^®-3 DPU, from CPU_1
- 1 x FHFL x16 (Gen5 x16), from CPU_0
- 1 x FHFL x16 (Gen5 x16), from CPU_1

Front I/O

ConnectX^®-8 SuperNIC^™ switch board:
8 x QSFP ports

I/O board:
1 x USB 3.2 Gen1 port (Type-A)
1 x Mini-DP
1 x Debug port (Micro USB)
1 x MLAN port
1 x Power button with LED
1 x ID button with LED
1 x Reset button

Rear I/O

N/A

Security Modules

1 x TPM header with SPI interface
- Optional TPM 2.0 kit: CTM012

Power Supply^[#1]

6 x 3200 W 80 PLUS Titanium redundant power supplies^[1]

AC Input:
- 100-127V~, 16A, 50-60Hz
- 200-220V~, 16A, 50-60Hz
- 220-240V~, 16A, 50-60Hz

DC Input: (Only for China)
- 240Vdc, 16A

DC Output:
- Max 1300W/ 100-127V~
+12.2V/ 106.6A
+12.2Vsb/ 3A
- Max 3000W/ 200-220V~
+12.2V/ 246A
+12.2Vsb/ 3A
- Max 3200W/ 220-240V~ or 240Vdc Input
+12.2V/ 262.3A
+12.2Vsb/ 3A

^[1]The system power supply requires C19 power cord.

System Fans

6 x 60x60x56mm

Operating Properties

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

^[Note]To ensure system stability and prevent condensation, when the relative humidity exceeds 50%, the coolant inlet temperature must be higher than the dry-bulb temperature and it should not exceed 45°C.

Weight

Net Weight: 108 kg
Gross Weight: 117 kg

Packaging Dimensions

1200 x 800 x 444 mm

Packaging Content

1 x XLS4-SX2-LAS1
4 x CPU carriers
1 x 3-Section Rail kit

Part Numbers

- Barebone package: 6NXLS4SX2DR000LAS1*
- Motherboard: 9MSX4MG2NR-000*
- 3-Section Rail kit: 25HB2-U9DH00-K0R
- Backplane board - CBPX081: 9CBPX081NR-00*
- I/O board - CBG7J: 9CBG7JNR-00*
- DC-SCM board - CDCX102: 9CDCX102NR-00*

[#1] Power cords are not included with server packages. Customers are responsible for selecting appropriate power cords from the optional accessories or contacting sales for customization.

[#2] All materials provided herein are for reference only. GIGABYTE reserves the right to modify or revise the content at any time without prior notice.

[#3] Advertised performance is based on maximum theoretical values as specified by the respective chipset vendors or standards organizations. Actual performance may vary depending on system configuration.

[#4] All trademarks and logos are the property of their respective owners.

Suport

Description	Version	Size	Date