4 Sources
[1]
Nvidia announces reference design for gargantuan gigawatt-scale Omniverse DSX data centers -- single data center requires a nuclear reactor's worth of power generation
Nvidia used to be a humble supplier of graphics processors, providing reference designs for its partners' graphics cards. As the company grew, it moved from data center-grade GPUs for AI and HPC to reference designs for servers, then to rack-scale solutions. At its GTC 2025 summit, the company
[2]
Nvidia's AI factory dream gets the Omniverse treatment
GPU giant teams with partners to create digital twin blueprint for next-gen datacenters Nvidia unveiled Omniverse DSX at its GTC event in Washington DC -- a blueprint for designing and operating gigawatt-scale AI datacenters using digital twin technology. The GPU giant also confirmed the
[3]
NVIDIA Launches Omniverse DSX Blueprint, Enabling Global AI Infrastructure Ecosystem to Build Gigawatt-Scale AI Factories
Your browser doesn't support HTML5 video. Here is a link to the video instead. During the GTC Washington, D.C., keynote today, NVIDIA founder and CEO Jensen Huang introduced NVIDIA Omniverse DSX, a comprehensive, open blueprint for designing and operating gigawatt-scale AI factories -- validated
[4]
Vertiv Unveils Gigawatt-Scale Reference Architectures for NVIDIA Omniverse DSX Blueprint
"The AI industrial revolution requires a complete reinvention of data center infrastructure. Vertiv's collaboration with NVIDIA is foundational to our mission of equipping our customers with the most advanced and flexible solutions to navigate this transformation," said Scott Armul, executive vice
Share
Copy Link
Nvidia announces a comprehensive blueprint for designing and operating massive AI data centers requiring nuclear reactor-level power. The Omniverse DSX combines digital twin technology with real-world engineering to create gigawatt-scale AI factories.
Nvidia has unveiled its most ambitious infrastructure project yet: the Omniverse DSX Blueprint, a comprehensive reference design for building and operating gigawatt-scale AI data centers. Announced at the company's GTC 2025 summit in Washington D.C., this blueprint represents Nvidia's evolution from a graphics processor supplier to an architect of entire AI ecosystems
1
.
Source: DT
"Nvidia started out by designing chips, and then we started to design systems, and we designed AI supercomputers. Now we're designing entire AI factories," said CEO Jensen Huang during his keynote address
2
. These facilities, which Huang positions as distinct from traditional data centers, are purpose-built for one primary function: producing AI tokens at unprecedented rates and intelligence levels.The Omniverse DSX Blueprint leverages digital twin technology, combining Nvidia's Omniverse simulation environment with open source Universal Scene Description (OpenUSD) technology
2
. This approach creates a unified digital environment where partners can plan, build, and optimize every aspect of an AI data center, from power and cooling systems to compute and networking layouts1
.
Source: NVIDIA
The blueprint has been validated at Nvidia's AI Factory Research Center in Manassas, Virginia, built in partnership with Digital Realty
3
. This facility serves as a real-world testing ground for the DSX concepts and underpins actual deployments, including the 2 GW Switch site in Georgia and the 1.2 GW Stargate facility in Abilene, Texas1
.The DSX blueprint operates on three fundamental pillars designed to maximize efficiency and scalability
3
:DSX Flex focuses on dynamic grid collaboration, balancing energy demand with real-time grid conditions using Omniverse telemetry and AI agents. This system aims to improve efficiency and grid cooperation while tapping into approximately 100 gigawatts of underutilized grid capacity.
DSX Boost applies performance-per-watt optimization at the data center level, running workloads at Max-Q efficiency—the optimal performance per watt ratio. This approach can deliver up to 30% higher GPU throughput within the same power envelope.
DSX Exchange serves as the unified IT/OT integration layer, acting as a secure data and control fabric that links operational systems for power, cooling, and safety with Nvidia's software stack and Omniverse digital twins through real-time APIs and partner integrations.

Source: The Register
Related Stories
The blueprint brings together an extensive ecosystem of industry partners. Engineering and construction partner Jacobs handles building design and optimization, while companies like Siemens, Schneider Electric, Trane, and Vertiv provide SimReady OpenUSD assets for power, electrical, and cooling equipment
3
.Vertiv has developed specific reference architectures featuring optimized power topologies through their "Grid-to-Chip" power train, advanced liquid cooling solutions, and flexible deployment methodologies that can reduce Time to First Token by up to 50% compared to traditional construction
4
.The Cadence Reality Digital Twin platform, built on top of the blueprint with integrated Omniverse libraries and CUDA acceleration, allows engineers to simulate thermals and electricals in high-fidelity 3D environments
3
.Summarized by
Navi
[2]
19 Mar 2025•Technology

19 May 2025•Technology

28 May 2025•Technology

1
Policy and Regulation

2
Technology

3
Policy and Regulation
