NVIDIA RTX Server Lineup Expands to Meet Growing Demand for Data Center and Cloud Graphics Applications

Delivers new capabilities for rendering, collaboration, cloud gaming and VR.
by Bob Pette

From Hollywood studios under pressure to create amazing content faster than ever, to the emerging demand for 5G-enabled cloud gaming and VR streaming — the need for computational horsepower has never been greater.

Previously, running servers powerful enough to deliver visually rich content in real time was too expensive. Not anymore.

NVIDIA RTX Servers — which include fully optimized software stacks available for Optix RTX rendering, gaming, VR and AR, and professional visualization applications — can now deliver cinematic-quality graphics enhanced by ray tracing for far less than just the cost of electricity for a CPU-based rendering cluster with the same performance.

RTX Blade Servers: A Leap in Cloud-Rendered Density, Efficiency and Scalability

NVIDIA founder and CEO Jensen Huang unveiled the latest RTX Server configuration at our annual GPU Technology Conference today. It comprises 1,280 Turing GPUs on 32 RTX blade servers, which offer a monumental leap in cloud-rendered density, efficiency and scalability.

Each RTX blade server packs 40 GPUs into an 8U space and can be shared by multiple users with NVIDIA GRID vGaming or container software. Mellanox technology is used as the backbone storage and networking interconnect to deliver the apps and updates instantly to thousands of concurrent users.

We’ve optimized RTX servers for use by cloud gaming operators, enabling them to render and stream games at the performance levels of GeForce RTX 2080 GPUs to any client device.

AR and VR Applications Now a Cloud Reality

With low-latency access to RTX Servers at the network edge, cloud-rendered AR and VR applications become a reality. We’re showcasing AR/VR demos running on cloud-based hardware at GTC, including an RTX Server-powered demo from Envrmnt, the XR arm of Verizon.

We’re collaborating with AT&T and Ericsson to bring these experiences to life on mobile networks. At AT&T Foundry, using NVIDIA CloudVR software, we were able to play an interactive VR game, over a 5G radio streamed from an RTX Server. The result was a great end user experience, with only 5ms of network delay and no observable performance loss. Cloud-based VR over 5G will be demonstrated next week at the AT&T and Ericsson 5G Designing the Edge event.

Global Telcos Join NVIDIA GeForce NOW Alliance to Deploy Cloud Gaming on 5G

The advent of 5G networks with high bandwidth and ultra-low latency has made rendering and streaming even the most complex applications from the cloud viable. With RTX Servers on 5G Edge networks, users will have access to cloud gaming services like GeForce NOW and AR and VR applications on just about any device.

Applying edge computing to cloud gaming benefits both fixed-line and mobile broadband networks by eliminating the physical distance between network hubs and game servers that can add to latency.

Telecommunications operators deploying optimized RTX Servers with NVIDIA-managed GeForce NOW software in their data centers get an easy-to-deploy, turnkey solution to deliver computationally demanding content. Softbank (Japan) and LG Uplus (Korea) will be among the first partners to deploy RTX cloud gaming servers later this year.

We’re working with HTC to bring cloud gaming and VR wirelessly into homes. The HTC 5G Hub — a 5G hotspot, Android entertainment device and battery pack all-in-one — is ideal for fixed wireless access (FWA) for 5G broadband homes. The GeForce NOW app is being optimized for the HTC Hub to provide a low latency cloud gaming experience over 5G. We’re also working together to support CloudVR, enabling virtual reality apps to be rendered on RTX servers in cloud data centers and streamed to the HTC VIVE headset without a local PC or cables to enable a mobile, high-end VR experience.

Virtualized Production, Rendering, and Collaboration

Whether working on content creation on the desktop or batch and final frame rendering in the data center, users of NVIDIA RTX Servers can tap into GPU-accelerated rendering and performance at a fraction of the cost, space and power requirements of a CPU render farm. And they get the processing power artists need to explore more creative options and create even higher quality effects that might otherwise take too long to attempt.

Production processes for animation, visual effects and industrial design often require many people across multiple continents. But complex 3D pipelines make global collaboration challenging. NVIDIA’s Omniverse allows artists to see and interact in real time with changes made by other artists or colleagues working on the same content in a different application. Changes are reflected in multiple tools at the same time.

Support for Quadro Virtual Data Center Workstation Software (Quadro vDWS) provides another efficient and powerful option for artists and designers to run their content creation applications and design tools virtually for greater mobility and increased collaboration without compromising performance. Studios can have one, easy-to-manage server with multiple virtual workstations, so employees can share GPU resources and securely access their work from any location.

World’s Leading OEMs Unveil Latest RTX Servers

System makers worldwide, including Dell, HPE, Lenovo, ASUS and Supermicro have unveiled newly validated NVIDIA RTX Servers for highly configurable, on-demand rendering and virtual workstation solutions from the data center.

“NVIDIA RTX Server provides benefits to users and organizations with the best performing and most efficient end-to-end rendering solutions, from batch rendering to interactive rendering in a design viewport. With the flexibility of ASUS solutions such as ASUS ESC4000 G4 and ESC8000 G4, designers can leverage the new AI and ray tracing features of NVIDIA’s enhanced RTX platform, enabling them to create impressive, stunning designs and visual effects faster than ever before.” — Jackie Hsu, corporate vice president at ASUS

“NVIDIA RTX Server combines the ground-breaking Quadro RTX 8000 and RTX 6000 GPUs with Quadro vDWS to deliver a powerful and flexible architecture to meet the demands of creative professionals. Supermicro is proud to be an inaugural partner for the NVIDIA RTX Server program with the Supermicro SYS-4029GP-TRT.” — Michael McNerney, vice president of Marketing and Network Security, Supermicro

Scalability and Availability

The NVIDIA RTX platform comes in 2U, 4U and 8U form factors and supports multiple NVIDIA GPU options from Quadro RTX GPUs and Quadro vDWS software for professional apps to NVIDIA GPUs with GRID vGaming software for cloud gaming and consumer AR/VR.

2U and 4U RTX servers are available from our OEM partners today. The new 8U RTX blade server will initially be available from NVIDIA in Q3.

Learn more about NVIDIA RTX.