KEY FEATURES Powerful performance: Powered by 6th Gen Intel® Xeon® Scalable processors unleash up to 21%-greater general-purpose performance per watt, significantly improving AI inference and training Scale-up stor

KEY FEATURES

• Powerful performance: Powered by 6th Gen Intel® Xeon® Scalable processors unleash up to 21%-greater general-purpose performance per watt, significantly improving AI inference and training
• Scale-up storage and expansion design: Up to 12 all-flash NVMe drives on the front panel, and 4 PCIe 5.0 slots for higher bandwidth and system upgrade
• Flexible networking module design: Optional two 10 Gbps or four 1 Gbps on-board LAN module, and OCP 3.0 module with PCIe 5.0 slot in rear panel for faster connectivity
• Advanced air cooling solution: Features enhanced volume air cooling (EVAC) heatsink for processors with higher TDP
• Enhanced IT-infrastructure management: ASMB11-iKVM remote control with ASPEED AST2600, ASUS Control Center IT management software and hardware-level Root-of-Trust solution
• Ready for AI and HPC workloads: Supports 1 dual-slot GPU, including Intel Data Center GPU Flex series and NVIDIA A100 H100 H100NVL 

PCIe 5.0 Ready

Faster storage, graphics and networking capabilities

PCI Express® (PCIe®) 5.0 delivers 32GT/s bandwidth, which is twice the speed of PCIe 4.0, and offers lower power consumption, better land scalability and backwards compatibility. These servers are PCIe 5.0 ready with scalability design to satisfy the increasing workloads for modern data center.

System Layout

Panel Layout 

Front Panel

Rear Panel 

Block Diagram

Scalable modular architecture for seamless integration

This server features a modular DC-MHS architecture that ensures seamless integration and high performance in data center environments. Its scalable design allows businesses to adapt to changing IT workloads by adding or removing modules without disruption. This flexibility improves operational efficiency, simplifies system management and supports phased upgrades. The architecture optimizes capital expenditure and resource use, reducing upfront costs. Additionally, modular components can be replaced or upgraded quickly, minimizing downtime and ensuring continuous operations. The DC-MHS architecture also incorporates advanced cooling and power management systems, improving energy efficiency, reducing operational costs, and supporting sustainability efforts.

Accelerating performance for AI workloads

Up to one dual-slot GPUs

This server features multiple PCIe 5.0 slots to meet the demands of AI and high-performance computing (HPC) workloads, including supporting up to one dual-slot active or passive GPUs, and Xilinx Alveo accelerators. The scalable configurations in one 2U system provide optimized acceleration for workloads across cloud and on-premises data centers, and for hybrid cloud environments in financial computing, machine learning, computational storage, and data search and analytics.

* The total number of NVMe drives installed will affect the total number of GPUs that can be installed.

* FPGA Xilinx verification is available on request.

* Refer to GPU compatible list by models.