ThinkSystem SD650-I V3 High-Density Server
Exascale performance for your AI & HPC workloads
ThinkSystem SD650-I V3 High-Density Server
Exascale performance for your AI & HPC workloads
-
Tech Specs
ATTRIBUTE SPECIFICATION Form Factor/Height 6U rack-mount with 6 trays Processor 2x 4th Gen Intel® Xeon® Scalable processors per tray or 2x Intel® Xeon® CPU Max processors per tray Memory Up to 2.0TB using 16x 128GB 4800 MHz TruDDR5 RDIMMs per tray Storage Up to 4x 7mm or 2x 15mm U.2/SATA, no drive/backplane choice and 1 x liquid cooled M.2 NVMe SSD, providing both the boot drive and storage function SW RAID and Intel VROC for Intel drives only NIC - 2 x SFP28 25Gb LOM, NCSI (10Gb capable)
- 1x RJ45 1GbE, NCSI
PCIe 2x x16 PCIe Gen5 LP per tray Power Support for ThinkSystem PCIe RAID/HBA cards Power Up to 9x air CFF v4 (2400W PT, 2600W TT) /
Up to 3x Direct Water Cooled Power Supply (7200W) 80+ TitaniumCooling Direct Water Cooling with up to 45°C inlet water temperature Management Lenovo XClarity Controller (XCC) and Lenovo Intelligent Computing Orchestration (LiCO) OS Support Red Hat Enterprise Linux, SUSE Linux Enterprise Server Acceleration Four Intel Data Center GPU Max <=600W TDP -
Features and Benefits
Lenovo Neptune™ is accelerated innovation
A decade of experience in direct water-cooling technology brings you our latest ThinkSystem SD650-I V3 server. Experience the combination of Intel acceleration technology with a market-leading water-cooling solution from Lenovo.
Advanced applications processing
The ThinkSystem SD650-I V3 can handle deep learning frameworks such as TensorFlow, PyTorch, and Apache. It easily processes Molecular Dynamics codes like GROMACS, NAMD, and OpenMM while providing a host of other functions.
Solutions that scale
The ThinkSystem SD650-I V3 is a fully-integrated Lenovo Scalable Infrastructure (LeSI) solution, providing Best Recipe guides to warrant interoperability of hardware, software, and firmware. With Lenovo intelligent Computing Orchestration (LiCO), you can support multiple users and scaling within a single cluster environment.
