ThinkSystem NVIDIA L40 48GB PCIe Gen4 Passive GPU

The ThinkSystem NVIDIA L40 48GB PCIe Gen4 Passive GPU delivers unprecedented visual computing performance for the data center and provides revolutionary neural graphics, compute, and AI capabilities to accelerate the most demanding visual computing workloads. With up to twice the performance of the previous generation at the same power, the NVIDIA L40 is uniquely suited to provide the visual computing power and performance required by the modern data center.

The following figure shows the ThinkSystem NVIDIA L40 48GB PCIe Gen4 Passive GPU.

Figure 1. ThinkSystem NVIDIA L40 48GB PCIe Gen4 Passive GPU

The NVIDIA L40, based on the NVIDIA Ada Lovelace GPU architecture features new generation RT cores and Tensor cores, delivering in combination over a petaflop of inferencing performance. These new features are combined with the latest generation CUDA Cores and 48GB of graphics memory to accelerate visual computing workloads from high-performance virtual workstation instances to large-scale digital twins in NVIDIA Omniverse.

The following table shows the part numbers for the GPU.

The option part number includes the following:

• One NVIDIA L40 GPU with full-height (3U) adapter bracket attached
• Documentation

From virtual workstation application to large-scale modeling and simulation, modern visual computing and scientific workflows are growing in both complexity and quantity.

Enterprises need data center technology that can deliver extreme performance and scale with versatile capabilities to conquer the diverse computing demands of these increasingly complex workloads.

The NVIDIA® L40 GPU delivers unprecedented visual computing performance for the data center, providing next- generation graphics, compute, and AI capabilities. Built on the revolutionary NVIDIA Ada Lovelace architecture, the NVIDIA L40 harnesses the power of the latest generation RT, Tensor, and CUDA cores to deliver groundbreaking visualization and compute performance for the most demanding data center workloads.

Next-Generation Graphics and Compute Performance

• 142 third-generation RT Cores and industry-leading 48 GB of GDDR6 memory: The NVIDIA L40 delivers up to twice the real-time ray-tracing performance of the previous Ampere generation to enable high-performance ray tracing of complex geometry and the creation of beautifully detailed, photorealistic models and scenes. Accelerate high-fidelity creative workflows, including real-time, full-fidelity, interactive rendering, 3D design, video streaming, and virtual
• Faster rendering and smoother frame rates with NVIDIA Deep Learning Super Sampling 3 (DLSS 3): This breakthrough frame generation technology leverages deep learning and the latest hardware innovations within the Ada Lovelace Architecture and L40 GPU, including 4th-Generation Tensor Cores and a new Optical Flow Accelerator, to boost rendering performance, deliver higher FPS, and significantly improve
• The NVIDIA L40 includes 18,176 Ada Lovelace GPU architecture CUDA cores delivering over 2X the single-precision floating-point (FP32) performance to accelerate 3D graphics, simulation and physics
• Breakthrough media acceleration capabilities: The NVIDIA L40 takes streaming and video content workloads to the next level with three video encode and three video decode engines. With the addition of AV1 encoding, the L40 delivers up to twice the performance and improved TCO for broadcast streaming, video production, and transcription
• Incredible training and inference capabilities with 90.5 TFLOPs of FP32 performance. The NVIDIA L40 includes 568 fourth-generation Tensor Cores providing up to 2X faster AI training performance than the previous generation with FP16 precision. Support for the new FP8 data format for inferencing provides more than 4X faster performance than the previous generation and reduces data memory usage by half (compared to FP16 data format)

 Data Center-Ready

• The NVIDIA L40 is optimized for 24x7 enterprise data center operations and is designed, built, extensively tested, and supported exclusively by NVIDIA to ensure maximum
• Secure boot with root of trust (RoT) technology within the GPU provide an additional layer of security for data centers. The NVIDIA L40 meets the latest data center standards and is NEBS Level 3
• Passively cooled, full-height, full-length (FHFL), dual-slot design
• The NVIDIA L40 is capable of 300W maximum board power and driven by power-efficient hardware and components selected for optimum performance, durability, and

The NVIDIA L40 GPU has the following specifications:

• Form factor
  • PCIe Full Height Full Length adapter (4.4-in x 10.5-in), Double-width (dual slot)
  • NVIDIA Form Factor 5.5
• Host interface:
  • PCIe 4.0 x16
  • MSI-X interrupt messaging protocol (MSI not supported)
  • PCIe Lane Polarity Inversion and Lane Reversal
• Single Root I/O Virtualization (SR-IOV) support
  • 256 virtual functions (VFs)
  • ARI Forwarding
• Hardware Root of Trust
  • Secure boot
  • Secure firmware upgrade
  • Firmware rollback protection
  • Support for in-band firmware update disable (established after each GPU reset)
  • Secure application processor recovery

The following table lists the GPU processing specifications and performance of the NVIDIA L40.

The following tables list the ThinkSystem servers that are compatible.

The following table lists the supported operating systems.

This section lists the NVIDIA software that is available from Lenovo.

• NVIDIA vGPU Software (vApps, vPC, RTX vWS, and vCS)
• NVIDIA Omniverse Software (OVE)
• NVIDIA AI Enterprise Software
• NVIDIA HPC Compiler Software

• Virtual PC (vPC)

  This product is ideal for users who want a virtual desktop but need great user experience leveraging PC Windows® applications, browsers and high-definition video. NVIDIA Virtual PC delivers a native experience to users in a virtual environment, allowing them to run all their PC applications at full performance.

• NVIDIA RTX Virtual Workstation (RTX vWS)

  NVIDIA RTX vWS is the only virtual workstation that supports NVIDIA RTX technology, bringing advanced features like ray tracing, AI-denoising, and Deep Learning Super Sampling (DLSS) to a virtual environment. Supporting the latest generation of NVIDIA GPUs unlocks the best performance possible, so designers and engineers can create their best work faster. IT can virtualize any application from the data center with an experience that is indistinguishable from a physical workstation — enabling workstation performance from any device.

• Virtual Compute Server (vCS)

  NVIDIA Virtual Compute Server (vCS) enables data centers running on Red Hat Enterprise Linux, Red Hat Virtualization, and other supported KVM-based hypervisors to accelerate server virtualization with the latest NVIDIA data center GPUs, so that the most compute-intensive workloads, such as artificial intelligence, deep learning, and data science, can be run in a virtual machine (VM) powered by NVIDIA vGPU technology.

The following license types are offered:

• Perpetual license

  A non-expiring, permanent software license that can be used on a perpetual basis without the need to renew. Each Lenovo part number includes a fixed number of years of Support, Upgrade and Maintenance (SUMS).

• Annual subscription

  A software license that is active for a fixed period as defined by the terms of the subscription license, typically yearly. The subscription includes Support, Upgrade and Maintenance (SUMS) for the duration of the license term.

• Concurrent User (CCU)

  A method of counting licenses based on active user VMs. If the VM is active and the NVIDIA vGPU software is running, then this counts as one CCU. A vGPU CCU is independent of the connection to the VM.

The following table lists the ordering part numbers and feature codes.

NVIDIA AI Enterprise Software

Lenovo offers the NVIDIA AI Enterprise (NVAIE) cloud-native enterprise software. NVIDIA AI Enterprise is an end-to-end, cloud-native suite of  AI and data analytics software, optimized, certified, and supported by NVIDIA to run on VMware vSphere and bare-metal  with NVIDIA-Certified  Systems™.  It includes key enabling technologies from NVIDIA for rapid deployment, management, and scaling of AI workloads in the modern hybrid cloud.

NVIDIA AI Enterprise is licensed on a per-GPU basis. NVIDIA AI Enterprise products can be purchased as either a perpetual license with support services, or as an annual or multi-year subscription.

The features of NVIDIA AI Enterprise Software are listed in the following table.

Note: Maximum 10 concurrent VMs per product license

The following table lists the ordering part numbers and feature codes.

Find more information in the NVIDIA AI Enterprise Sizing Guide.

NVIDIA HPC Compiler Software

The L40 option part number does not ship with auxiliary power cables. Cables are server-specific due to length requirements and the connector on the server end of the cable. For CTO orders, auxiliary power cables are derived by the configurator. For field upgrades, cables will need to be ordered separately as listed in the table below.

Table 13. Auxiliary power cables for NVIDIA L40

Auxiliary power cable needed with the SE455 V3 and SE450

450mm 16-pin (2x6+4) cable Option: SE455 V3: 4X97A89288, ThinkEdge NVIDIA L40 GPU Power Cable Kit (contains 2 cables) SE450: 4X97A89288, ThinkEdge NVIDIA L40 GPU Power Cable Kit (contains 2 cables) Feature: BVVG SBB: SBB7A74096 Base: SC17B36330 FRU: 03LE760 Additional components may be required when installing the GPU. See the SE455 V3 product guide for details.

Auxiliary power cable needed with the SR665, SR650 V2, SR650 V3, SR655 V3, SR665 V3

400mm 16-pin (2x6+4) cable Option: SR665: 4X97A85028, ThinkSystem 400mm 2x6+4 GPU Power Cable SR650 V2: 4X97A85028, ThinkSystem 400mm 2x6+4 GPU Power Cable SR650 V3: 4X67A82883, ThinkSystem SR650 V3 GPU Full Length Thermal Option Kit* SR655 V3: 4X67A86438, ThinkSystem SR655 V3 GPU Enablement Kit* SR665 V3: 4X67A85856, ThinkSystem SR665 V3 GPU Full Length Thermal Option Kit* Feature: BRWK SBB: SBB7A66338 Base: SC17B33047 FRU: 03KM846 * The option part number is for the thermal kit and includes other components needed to install the GPU. See the respective server product guide details.

Auxiliary power cable needed with the SR675 V3

235mm 16-pin (2x6+4) cable Option: 4X97A84510, ThinkSystem SR675 V3 Supplemental Power Cable for H100 GPU Option Feature: BSD2 SBB: SBB7A65299 Base: SC17B39301 FRU: 03LE554

Auxiliary power cable needed with the SR670 V2

215mm 16-pin (2x6+4) cable Option: 4X97A85027, ThinkSystem SR670 V2 H100/L40 GPU Option Power Cable Feature: BRWL SBB: SBB7A66339 Base: SC17B33046 FRU: 03KM845

Auxiliary power cable needed with the SR850 V3, SR860 V3

200mm 16-pin (2x6+4) cable Option: 4X97A88016, ThinkSystem SR850 V3/SR860 V3 H100 GPU Power Cable Option Kit Feature: BW28 SBB: SBB7A72759 Base: SC17B40604 FRU: 03LF915

The NVIDIA L40 GPU has the following regulatory approvals:

• RCM
• BSMI
• CE
• FCC
• ICES
• KCC
• cUL, UL
• VCCI

The NVIDIA L40 GPU has the following operating characteristics:

• Ambient temperature
  • Operational: 0°C to 50°C (-5°C to 55°C for short term*)
  • Storage: -40°C to 75°C
• Relative humidity:
  • Operational: 5-85% (5-93% short term*)
  • Storage: 5-95%

* A period not more than 96 hours consecutive, not to exceed 15 days per year.

One year limited warranty. When installed in a Lenovo server, the GPU assumes the server’s base warranty and any warranty upgrades.

The following sales training courses are offered for employees and partners (login required). Courses are listed in date order.

1. Generative AI Overview Foundational
   2024-02-16 | 17 minutes | Employees Only
   Details
   Generative AI Overview Foundational
   
   

   It seems the whole world is excited about Generative AI, and while some of it is just hype, it has become clear that Generative AI has the potential to revolutionize many aspects of our personal and professional lives. In this brief NVIDIA course, we'll explore one aspect of the Generative AI excitement, the value you get from Generative AI technology. We will discuss what Generative AI is, how it works, and how enterprises are planning to use this technology.
   
   By the end of this course, you will be able to discuss the Generative AI market trends and the challenges in this space with your customers. And you will be able to explain what Generative AI is and how the technology works to help enterprises unlock new opportunities for business.

   Published: 2024-02-16
   Length: 17 minutes
   Employee link: Grow@Lenovo
   Course code: DAINVD106
2. Industry Use Cases in Modern Computing Foundational
   2024-02-16 | 9 minutes | Employees Only
   Details
   Industry Use Cases in Modern Computing Foundational
   
   

   As GPU powered computing continues to improve exponentially, applications that were once science fiction are becoming best practice. This is an introductory NVIDIA course that explores some exciting industry focused use cases that are providing companies with faster time to insight, productivity at scale and a great ROI.
   
   By the end of this course, you will be able to explain how companies in a few key industry verticals are benefiting from a variety of accelerated compute use cases.

   Published: 2024-02-16
   Length: 9 minutes
   Employee link: Grow@Lenovo
   Course code: DAINVD105
3. Introduction to Artificial Intelligence Foundational
   2024-02-16 | 10 minutes | Employees Only
   Details
   Introduction to Artificial Intelligence Foundational
   
   

   This NVIDIA course aims to answer questions such as, what is AI and why are enterprises so interested in it? and how does AI happen, why are GPUs so important for it, and what does a good AI solution look like?
   
   By the end of this training, you should be able to describe AI and relate it to some common enterprise use cases. You'll know the difference between training and inference and be able to visualize a typical AI workflow. More importantly, you'll understand the difficulties of traditional CPU-based AI and appreciate why businesses would benefit greatly by adopting GPU-accelerated workflows. Finally, you'll also understand what features contribute to an awesome AI solution and why customers respect and enjoy NVIDIA's solutions.

   Published: 2024-02-16
   Length: 10 minutes
   Employee link: Grow@Lenovo
   Course code: DAINVD104
4. GPU Fundamentals Foundational
   2024-02-16 | 10 minutes | Employees Only
   Details
   GPU Fundamentals Foundational
   
   

   This NVIDIA course introduces you to two devices that a computer typically uses to process information, the CPU and the GPU. We'll discuss their differences and look at how the GPU overcomes the limitations of the CPU. Once you understand the power and advantages of GPU processing, we will talk about the value GPUs bring to modern-day enterprise computing.
   
   By the end of this course, you should know the difference between serial and parallel processing. You will be able to explain what a GPU is in very simple terms and explain the value that GPUs bring to enterprises. Additionally, you'll become familiar with the typical GPU-accelerated enterprise workloads and list one or two use cases under them. By the time you exit this course, you should be able to target various GPU-accelerated computing opportunities with the right NVIDIA GPU.

   Published: 2024-02-16
   Length: 10 minutes
   Employee link: Grow@Lenovo
   Course code: DAINVD103
5. Partner Technical Webinar – NVidia
   2023-12-11 | 60 minutes | Employees and Partners
   Details
   Partner Technical Webinar – NVidia
   
   

   In this 60-minute replay, Brad Davidson of Nvidia will help us recognize AI Trends, and Discuss Industry Verticals Marketing.

   Published: 2023-12-11
   Length: 60 minutes
   Employee link: Grow@Lenovo
   Partner link: Lenovo Partner Learning
   Course code: 120823

For more information, refer to these documents:

• ThinkSystem and ThinkAgile GPU Summary:
  https://lenovopress.lenovo.com/lp0768-thinksystem-thinkagile-gpu-summary
• ServerProven compatibility:
  http://www.lenovo.com/us/en/serverproven
• NVIDIA L40 product page:
  https://www.nvidia.com/en-us/data-center/l40/