Vertiv Codevelops with NVIDIA Complete Power and Cooling Blueprint for NVIDIA GB200 NVL72 Platform
Vertiv (NYSE: VRT) has announced the release of a complete 7MW reference architecture for the NVIDIA GB200 NVL72 platform, co-developed with NVIDIA. This architecture aims to transform traditional data centers into AI factories capable of powering enterprise-wide AI applications. The design supports up to 132kW per rack and takes an end-to-end approach to optimize deployment speed, performance, resiliency, cost, energy efficiency, and scalability.
Key benefits of the co-developed reference architecture include:
- Rapid deployment and retrofit capabilities
- Space-saving power management
- Energy-efficient cooling
- Dynamic workload management
- Comprehensive installation and operations services
This collaboration between Vertiv and NVIDIA sets a future-forward roadmap for technical co-development and enables the deployment of accelerated computing at scale.
Vertiv (NYSE: VRT) ha annunciato il rilascio di un'architettura di riferimento completa da 7MW per la piattaforma NVIDIA GB200 NVL72, co-sviluppata con NVIDIA. Questa architettura ha l'obiettivo di trasformare i tradizionali data center in fabbriche di intelligenza artificiale capaci di supportare applicazioni AI a livello aziendale. Il design supporta fino a 132kW per rack e adotta un approccio end-to-end per ottimizzare la velocità di implementazione, le prestazioni, la resilienza, i costi, l'efficienza energetica e la scalabilità.
I principali vantaggi dell'architettura di riferimento co-sviluppata includono:
- Implementazione rapida e capacità di retrofit
- Gestione energetica salvaspazio
- Raffreddamento energeticamente efficiente
- Gestione dinamica del carico di lavoro
- Servizi completi di installazione e operazioni
Questa collaborazione tra Vertiv e NVIDIA delinea una roadmap innovativa per lo sviluppo tecnico congiunto e consente l'implementazione del calcolo accelerato su larga scala.
Vertiv (NYSE: VRT) ha anunciado el lanzamiento de una arquitectura de referencia completa de 7MW para la plataforma NVIDIA GB200 NVL72, co-desarrollada con NVIDIA. Esta arquitectura tiene como objetivo transformar los centros de datos tradicionales en fábricas de IA capaces de impulsar aplicaciones de IA a nivel empresarial. El diseño admite hasta 132kW por rack y adopta un enfoque de extremo a extremo para optimizar la velocidad de implementación, el rendimiento, la resiliencia, el costo, la eficiencia energética y la escalabilidad.
Los beneficios clave de la arquitectura de referencia co-desarrollada incluyen:
- Despliegue rápido y capacidades de modernización
- Gestión de energía que ahorra espacio
- Enfriamiento energéticamente eficiente
- Gestión dinámica de la carga de trabajo
- Servicios integrales de instalación y operaciones
Esta colaboración entre Vertiv y NVIDIA establece una hoja de ruta orientada al futuro para el co-desarrollo técnico y permite la implementación de computación acelerada a gran escala.
Vertiv (NYSE: VRT)는 NVIDIA와 공동 개발한 NVIDIA GB200 NVL72 플랫폼에 대한 완전한 7MW 기준 아키텍처의 출시를 발표했습니다. 이 아키텍처는 전통적인 데이터 센터를 기업 전체 AI 애플리케이션을 지원할 수 있는 AI 공장으로 변형하는 것을 목표로 합니다. 이 설계는 랙당 최대 132kW를 지원하며, 배치 속도, 성능, 복원성, 비용, 에너지 효율성 및 확장성을 최적화하기 위해 엔드 투 엔드 접근 방식을 사용합니다.
공동 개발된 기준 아키텍처의 주요 이점은 다음과 같습니다:
- 신속한 배포 및 리트로핏 기능
- 공간 절약형 전력 관리
- 에너지 효율적인 냉각
- 동적 작업 부담 관리
- 종합적인 설치 및 운영 서비스
Vertiv와 NVIDIA 간의 이 협력은 기술 공동 개발을 위한 미래 지향적인 로드맵을 제시하며, 대규모로 가속화된 컴퓨팅을 배포할 수 있게 합니다.
Vertiv (NYSE: VRT) a annoncé le lancement d'une architecture de référence complète de 7MW pour la plateforme NVIDIA GB200 NVL72, co-développée avec NVIDIA. Cette architecture vise à transformer les centres de données traditionnels en usines d'IA capables de prendre en charge des applications d'IA à l'échelle de l'entreprise. La conception prend en charge jusqu'à 132 kW par rack et adopte une approche de bout en bout pour optimiser la rapidité de déploiement, les performances, la résilience, les coûts, l'efficacité énergétique et l'évolutivité.
Les principaux avantages de l'architecture de référence co-développée comprennent :
- Déploiement rapide et capacités de retrofit
- Gestion de l'énergie optimisée pour l'espace
- Refroidissement économe en énergie
- Gestion dynamique de la charge de travail
- Services complets d'installation et d'exploitation
Cette collaboration entre Vertiv et NVIDIA établit une feuille de route tournée vers l'avenir pour le co-développement technique et permet le déploiement de l'informatique accélérée à grande échelle.
Vertiv (NYSE: VRT) hat die Veröffentlichung einer vollständigen 7-MW-Referenzarchitektur für die NVIDIA GB200 NVL72-Plattform bekannt gegeben, die gemeinsam mit NVIDIA entwickelt wurde. Diese Architektur zielt darauf ab, traditionelle Rechenzentren in KI-Fabriken umzuwandeln, die in der Lage sind, unternehmensweite KI-Anwendungen zu unterstützen. Das Design unterstützt bis zu 132 kW pro Rack und verfolgt einen End-to-End-Ansatz zur Optimierung der Bereitstellungsgeschwindigkeit, der Leistung, der Resilienz, der Kosten, der Energieeffizienz und der Skalierbarkeit.
Die wichtigsten Vorteile der gemeinsam entwickelten Referenzarchitektur umfassen:
- Rasche Implementierung und Nachrüstungsmöglichkeiten
- Platzsparendes Energiemanagement
- Energieeffiziente Kühlung
- Dynamisches Lastmanagement
- Umfassende Installations- und Betriebsdienste
Diese Zusammenarbeit zwischen Vertiv und NVIDIA schafft eine zukunftsorientierte Roadmap für technische Co-Entwicklung und ermöglicht die Implementierung von beschleunigtem Computing in großem Maßstab.
- Co-development of 7MW reference architecture with NVIDIA for GB200 NVL72 platform
- Support for high-density computing up to 132kW per rack
- Potential for 50% faster deployment than onsite builds
- ~40% space savings in power management compared to legacy offerings
- Up to 20% lower annual cooling costs compared to fixed screw solutions
- Global service capability with ~4,000 field service engineers
- None.
Insights
This collaboration between Vertiv and NVIDIA marks a significant advancement in AI infrastructure. The co-developed 7MW reference architecture for the NVIDIA GB200 NVL72 platform addresses critical challenges in deploying high-density AI computing environments. Key highlights include:
- Support for up to 132kW per rack, enabling extreme compute density
- Hybrid liquid- and air-cooling infrastructure for efficient heat management
- Potential for 50% faster deployment using preconfigured modules
- Up to 20% lower annual cooling costs compared to traditional solutions
- ~40% space savings for power management equipment
This partnership positions Vertiv as a key enabler in the rapidly growing AI data center market. The reference design's focus on scalability, energy efficiency and rapid deployment aligns well with the urgent demand for AI computing infrastructure. For Vertiv, this represents a significant opportunity to capture market share in the high-growth AI sector, potentially driving substantial revenue growth in the coming years.
Vertiv's collaboration with NVIDIA is a game-changer for AI data center infrastructure. The reference architecture addresses several critical pain points:
- Power density: Supporting 132kW per rack is exceptional and meets the demands of next-gen AI hardware.
- Cooling efficiency: The hybrid approach combining liquid and air cooling is important for managing extreme heat loads.
- Deployment speed: Preconfigured modules could significantly reduce time-to-market for new AI facilities.
- Flexibility: The design accommodates both retrofits and new builds, important in a rapidly evolving market.
The inclusion of OCP-inspired systems like DC power shelves also shows forward-thinking adaptability. This comprehensive approach, combining power, cooling and services, positions Vertiv as a one-stop solution provider for AI infrastructure. It's likely to strengthen Vertiv's competitive position and drive growth in the high-margin data center infrastructure market.
End-to-end critical power and cooling reference designs for NVIDIA Blackwell architectures up to 7MW, with OCP infrastructure options
Vertiv and NVIDIA collaborative reference design for power and cooling infrastructure to enable NVIDIA Blackwell architectures up to 7MW (Photo: Business Wire)
The reference architecture will accelerate the deployment of the NVIDIA GB200 NVL72 liquid-cooled rack-scale platform and supports up to 132kW per rack. The architecture takes an end-to-end approach to infrastructure design to optimize deployment speed, performance, resiliency, cost, energy efficiency and scalability for current- and future-generation data centers.
“We are proud to deepen our collaboration with NVIDIA to enable AI-driven data centers of today and tomorrow,” said Giordano (Gio) Albertazzi, CEO of Vertiv. “As a leader in critical power and cooling infrastructure, Vertiv is uniquely positioned to support the NVIDIA GB200 NVL72 platform. Our portfolio of high-performance power and cooling solutions, combined with our global scale, will enable customers to deploy AI data centers faster, more efficiently and with greater flexibility to address densification, dynamic workloads, retrofits and enable future-ready designs.”
“New data centers are built for accelerated computing and generative AI with architectures that are significantly more complex than those for general-purpose computing,” said Jensen Huang, founder and CEO of NVIDIA. “With Vertiv's world-class cooling and power technologies, NVIDIA can realize our vision to reinvent computing and build a new industry of AI factories that produce digital intelligence to benefit every company and industry.”
With Vertiv™ power and cooling infrastructure matched to, and closely coupled with, the NVIDIA Blackwell platform, the reference architecture simplifies and accelerates deployment of AI workloads in new and existing data centers while reducing risk and enabling standardization across sites. The architecture’s complete critical power infrastructure is designed to significantly reduce stranded power by aligning AI clusters to data center capacity blocks. The hybrid liquid- and air-cooling infrastructure leverages the interdependent impact of the two approaches to efficiently manage high-density heat removal. In addition, the design includes guidance for optional Open Compute Project-inspired systems, such as DC power shelves.
The reference architecture is part of the Vertiv™ 360AI portfolio of reference designs for retrofit and greenfield data centers, designed to help customers navigate integrated solutions for power and cooling for AI and other high-performance computing applications. Key benefits of the co-developed reference architecture for the NVIDIA GB200 NVL72 design include:
-
Rapid Deployment and Retrofit: Enabling the use of preconfigured modules and factory integration, Vertiv™ MegaMod™ CoolChip delivers turnkey AI critical infrastructure up to
50% faster than onsite builds. -
Space-Saving Power Management: Using Vertiv’s advanced power technologies, including Vertiv™ Trinergy™ uninterruptible power supply system (UPS) and Vertiv™ EnergyCore lithium battery cabinet, the design delivers industry-leading reliability and energy-efficient power management in ~
40% less space compared to legacy offerings. -
Energy-Efficient Cooling: Integrating liquid and low-GWP (Global Warming Potential) air cooling technologies at scale - including Vertiv™ AFC chiller, Vertiv™ Liebert® CW chilled water-based room cooling system and Vertiv™ XDU coolant distribution units - offers up to
20% lower annual cooling costs compared to fixed screw solutions. - Dynamic Workload Management: Integrated load averaging via lithium-ion battery and next generation UPS provides support for dynamic GPU workloads.
- Installation and Operations Services: With an industry-leading scale, scope, and reach of ~4,000 field service engineers globally, Vertiv is the trusted lifecycle service partner and complex system-level expert for retrofit and newbuild.
As enterprises embrace AI at an unprecedented pace, Vertiv is reshaping the future of critical power and cooling to support accelerated computing, with the most complete portfolio of critical digital infrastructure that enables AI-ready infrastructure capable of managing the unique requirements of AI and other accelerated compute applications.
Vertiv’s collaboration with NVIDIA sets a future-forward roadmap for technical co-development and enables deployment of accelerated computing at scale. To access the reference designs, visit Vertiv.com. Vertiv experts are also available to discuss details of the new design at OCP Summit, October 15-17, at booth #C5.
About Vertiv
Vertiv (NYSE: VRT) brings together hardware, software, analytics and ongoing services to enable its customers’ vital applications to run continuously, perform optimally and grow with their business needs. Vertiv solves the most important challenges facing today’s data centers, communication networks and commercial and industrial facilities with a portfolio of power, cooling and IT infrastructure solutions and services that extends from the cloud to the edge of the network. Headquartered in
Forward-Looking Statements
This release contains forward-looking statements within the meaning of the Private Securities Litigation Reform Act of 1995, Section 27 of the Securities Act, and Section 21E of the Securities Exchange Act. These statements are only a prediction. Actual events or results may differ materially from those in the forward-looking statements set forth herein. Readers are referred to Vertiv’s filings with the Securities and Exchange Commission, including its most recent Annual Report on Form 10-K and any subsequent Quarterly Reports on Form 10-Q for a discussion of these and other important risk factors concerning Vertiv and its operations. Vertiv is under no obligation to, and expressly disclaims any obligation to, update or alter its forward-looking statements, whether as a result of new information, future events or otherwise.
View source version on businesswire.com: https://www.businesswire.com/news/home/20241014494536/en/
Sara Steindorf
E Sara.Steindorf@fleishman.com
Source: Vertiv Holdings Co
FAQ
What is the power capacity of Vertiv's new reference architecture for NVIDIA's GB200 NVL72 platform?
How much power can each rack support in Vertiv's new NVIDIA-collaborative design?
What are the key benefits of Vertiv's reference architecture for NVIDIA's GB200 NVL72 platform?
How does Vertiv's new design improve cooling costs for AI infrastructure?
What is the potential deployment speed improvement for Vertiv's AI infrastructure solution?
