skip to main content

Lenovo ThinkSystem SD650-N V2

Exascale technology made available at every scale.

Datasheet (withdrawn product)

28 Jun 2021
Form Number
PDF size
3 pages, 371 KB

Lenovo Neptune™ accelerated

Lenovo ThinkSystem SD650-N V2 is based on our fourth generation Lenovo Neptune™ direct water cooling platform based on two 3rd Gen Intel® Xeon® Scalable processors with NVIDIA HGX™ A100 4-GPU acceleration and NVIDIA HDR InfiniBand networking.

The combination of market leading NVIDIA acceleration technology with the market leading water cooling solution from Lenovo results in extreme performance in an extreme dense packaging. A single rack of Lenovo ThinkSystem SD650-N V2 provides up to 2.8 PetaFLOPS High Performance Computing (HPC) or 45 PetaFLOPS Artificial Intelligence (AI) peak performance on just 0.72m² - less than 8 ft² - footprint.

Accelerating your applications

On the SD650-N V2 four NVIDIA A100 Tensor Core GPU are interconnected through NVLink delivering substantial performance improvements for HPC, AI training, and inference workloads. The A100 supports the Lenovo HPC philosophy to enable customers From Exascale to Everyscale™. Together with NVIDIA InfiniBand networking it scales efficiently to thousands of GPUs or, with NVIDIA Multi-Instance GPU (MIG) technology, can be partitioned into seven GPU instances to accelerate smaller workloads.

Top View of ThinkSystem SD650-N V2

With NVIDIA® CUDA® the most widely used parallel computing platform and programming model for GPUs is available free of charge to help you accelerate the more than 700 supported HPC applications and every major deep learning framework, for example:

  • Chemistry like Gaussian and GROMACS
  • Finite Elements like LS-DYNA and Simulia Abaqus
  • Fluid Dynamics like OpenFOAM and ANSYS Fluent
  • Molecular Dynamics like NAMD and AMBER
  • Weather and Climate like WRF and ICON

The Lenovo ThinkSystem SD650-N V2 also supports NVIDIA® NGC™ providing pre-trained models, training scripts, optimized framework containers and inference engines for popular deep learning models.

Lenovo Neptune™: Leading water cooling technology

A decade of experience in direct water cooling sets Lenovo apart. With a meticulous focus on low-pressure drop and highest quality materials Lenovo achieves the best-in-class reliability. The SD650-N V2 leverages copper and brazed connections guaranteeing leak-free operations at extreme scale even at high pressure.

Another important differentiation is superior water loop design enabling up to 50°C inlet temperatures for the highest energy reuse efficiency. The new water loop design allows to optimize performance with increased frequency while ensuring temperature uniformity preventing Thermal Jitter for consistent application performance.

Water Cooling is an end to end process that already starts at manufacturing. Through Helium and Nitrogen pressure tests from the node to the full rack build the SD650-N V2 provides consistent quality at the highest standards. This approach also allows Lenovo to ship the systems pressurized without needing to send hazardous antifreeze-components to our customers.

Solutions That Scale

Lenovo ThinkSystem SD650-N V2 is delivered as fully integrated Lenovo Scalable Infrastructure (LeSI) solution. LeSI provides Best Recipe guides to warrant interoperability of hardware, software and firmware among a variety of Lenovo and third-party components. In addition to interoperability testing, LeSI hardware is pre-integrated, pre-cabled, pre-loaded with the best recipe and optionally an OS-image and tested at the rack level in manufacturing, to ensure a reliable delivery and minimize installation time in the customer data center.

Enabled with Lenovo intelligent Computing Orchestration (LiCO), you can support multiple users and scaling within a single cluster environment. LiCO is a powerful platform that manages cluster resources for HPC and AI applications. LiCO provides workflows for both AI and HPC, and supports multiple AI frameworks, allowing you to leverage a single cluster for diverse workload requirements.

Data Center Reliability Leader

At Lenovo, we take a customer-centric approach, which is why ThinkSystem servers consistently rank #1 in reliability. Also, Lenovo is the leading provider of Supercomputers in the TOP500. The ThinkSystem SD650-N V2 provides the latest in performance and reliability in a scalable solution for enterprise and research.


Form Factor/Height 6U rack-mount with 6 trays
Processor 2x 3rd Gen Intel® Xeon® Scalable processors per node
Memory Up to 2.0TB using 16x 128GB 3200MHz TruDDR4 RDIMMs per tray
Storage 2x 2.5-inch slim SATA / NVMe U.2 SSD and 2x M.2 SATA SSD
SW RAID and Intel VROC for Intel drives only
1x RJ45 1GbE, NCSI
PCIe 2x x16 PCIe Gen4 LP per tray
Power 6/9 N+1 redundant hot-swap PSUs (up to 2400W Platinum)
Cooling Direct Water Cooling with up to 50°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
Tested on CentOS
Acceleration NVIDIA HGX™ A100 4-GPU with 4x NVLink connected SXM4 GPUs

For More Information

To learn more about the Lenovo ThinkSystem SD650-N V2, contact your Lenovo representative or Business Partner or visit

Learn more about Lenovo Storage
Learn more about Lenovo Services

Related product families

Product families related to this document are the following:

© 2024 Lenovo. All rights reserved.
Availability: Offers, prices, specifications and availability may change without notice. Lenovo is not responsible for photographic or typographic errors. Warranty: For a copy of applicable warranties, write to: Lenovo Warranty Information, 1009 Think Place, Morrisville, NC, 27560. Lenovo makes no representation or warranty regarding third-party products or services.

Trademarks: Lenovo, the Lenovo logo, From Exascale to Everyscale, Lenovo Neptune®, ThinkSystem®, TruDDR4, and XClarity® are trademarks or registered trademarks of Lenovo. Intel® and Xeon® are trademarks of Intel Corporation or its subsidiaries. Linux® is the trademark of Linus Torvalds in the U.S. and other countries. Other company, product, or service names may be trademarks or service marks of others.

Document number DS0124, published June 28, 2021. For the latest version, go to

NVIDIA (Primary)