Supermicro Begins Volume Shipments of NVIDIA Blackwell Ultra Systems and Rack Plug-and-Play Data Center-Scale Solutions
Supermicro (NASDAQ: SMCI) has announced volume shipments of its NVIDIA Blackwell Ultra solutions, including NVIDIA HGX B300 systems and GB300 NVL72 racks worldwide. The company's Data Center Building Block Solutions (DCBBS) offers pre-validated, plug-and-play solutions at system, rack, and data center scale.
Key performance metrics include 1.1 exaFLOPS dense FP4 compute performance for GB300 NVL72 rack-scale systems and up to 7.5x performance gains over NVIDIA Hopper systems. The solutions feature 800 Gb/s bandwidth, 144 petaFLOPS of FP4 compute, and 270 GB of HBM3e memory per GPU.
Through DCBBS implementation, customers can achieve 40% power savings, 60% reduced data center footprint, 40% decreased water consumption, and 20% lower TCO.
Supermicro (NASDAQ: SMCI) ha annunciato spedizioni in volume delle sue soluzioni NVIDIA Blackwell Ultra, includendo sistemi NVIDIA HGX B300 e rack GB300 NVL72 in tutto il mondo. Le Data Center Building Block Solutions (DCBBS) dell'azienda offrono soluzioni pre-validate, plug-and-play su scala di sistema, rack e data center.
Le metriche chiave includono 1,1 exaFLOPS di prestazioni FP4 dense per sistemi su scala rack GB300 NVL72 e fino a 7,5x di miglioramenti delle prestazioni rispetto ai sistemi NVIDIA Hopper. Le soluzioni vantano larghezza di banda di 800 Gb/s, 144 petaFLOPS di compute FP4 e 270 GB di memoria HBM3e per GPU.
Attraverso l'implementazione DCBBS, i clienti possono ottenere risparmi energetici del 40%, un footprint del data center ridotto del 60%, un consumo idrico diminuito del 40% e un TCO inferiore del 20%.
Supermicro (NASDAQ: SMCI) ha anunciado envíos en volumen de sus soluciones NVIDIA Blackwell Ultra, incluyendo sistemas NVIDIA HGX B300 y racks GB300 NVL72 en todo el mundo. Las soluciones Data Center Building Block Solutions (DCBBS) de la empresa ofrecen soluciones con validación previa, listas para usar, a escala de sistema, rack y centro de datos.
Entre las métricas clave se incluyen 1,1 exaFLOPS de rendimiento FP4 denso para sistemas en rack GB300 NVL72 y hasta ganancias de rendimiento de hasta 7,5x frente a sistemas NVIDIA Hopper. Las soluciones cuentan con ancho de banda de 800 Gb/s, 144 petaFLOPS de compute FP4 y 270 GB de memoria HBM3e por GPU.
A través de la implementación de DCBBS, los clientes pueden lograr un 40% de ahorro de energía, un 60% menos huella de centro de datos, un 40% menos consumo de agua y un 20% menor costo total de propiedad (TCO).
??????(???: SMCI)? ? ????? NVIDIA Blackwell Ultra ???? ?? ??? ?????, ??? NVIDIA HGX B300 ???? GB300 NVL72 ?? ?????. ??? ??? ?? ?? ?? ???(DCBBS)? ???, ? ? ??? ?? ??? ?? ??? ??? ? ??? ???? ?????.
?? ?? ???? GB300 NVL72 ? ??? ???? 1.1 ?????(dense FP4) ?? ??? NVIDIA Hopper ??? ?? ?? 7.5?? ?? ??? ?????. ???? 800 Gb/s ???, FP4 ?? 144 ?????, GPU? 270 GB HBM3e ???? ???? ???.
DCBBS ??? ?? ??? ?? 40% ??, ??? ?? ?? 60% ??, ? ?? 40% ??, ??? ? ?? ??(TCO) 20% ??? ??? ? ????.
Supermicro (NASDAQ: SMCI) a annoncé des livraisons en volume de ses solutions NVIDIA Blackwell Ultra, y compris les systèmes NVIDIA HGX B300 et les racks GB300 NVL72 dans le monde entier. Les solutions Data Center Building Block Solutions (DCBBS) de l’entreprise offrent des solutions pré-validées, prêtes à l’emploi, à l’échelle du système, du rack et du centre de données.
Parmi les indicateurs clés figurent 1,1 exaFLOPS de performance FP4 dense pour les systèmes GB300 NVL72 à l’échelle rack et jusqu’à des gains de performance jusqu’à 7,5x par rapport aux systèmes NVIDIA Hopper. Les solutions présentent une large bande passante de 800 Gb/s, 144 PetaFLOPS de calcul FP4 et 270 Go de mémoire HBM3e par GPU.
Gr?ce à l’implémentation DCBBS, les clients peuvent réaliser 50% d’économie d’énergie, 40% de réduction de l’empreinte du centre de données, 40% de réduction de la consommation d’eau et 20% de co?t total de possession (TCO) en moins.
Supermicro (NASDAQ: SMCI) hat weltweite Gro?abnahmen seiner NVIDIA Blackwell Ultra-L?sungen angekündigt, einschlie?lich NVIDIA HGX B300-Systemen und GB300 NVL72-Racks. Die Data Center Building Block Solutions (DCBBS) des Unternehmens bieten vorkonfigurierte, plug-and-play L?sungen auf System-, Rack- und Rechenzentrumsebene.
Wichtige Leistungskennzahlen umfassen 1,1 ExaFLOPS dichte FP4-Rechenleistung für rackskalierte GB300 NVL72-Systeme und bis zu 7,5-fache Leistungssteigerungen gegenüber NVIDIA Hopper-Systemen. Die L?sungen verfügen über 800 Gb/s Bandbreite, 144 PetaFLOPS FP4-Rechenleistung und 270 GB HBM3e-Speicher pro GPU.
Durch die Implementierung von DCBBS k?nnen Kunden 40% Energieeinsparungen, 60% weniger Rechenzentrumsfl?che, 40% reduzierten Wasserverbrauch und 20% geringere TCO erzielen.
????????? (??????: SMCI) ????? ?? ????? ????? ?? ?????? NVIDIA Blackwell Ultra? ??? ?? ??? ????? NVIDIA HGX B300 ????? GB300 NVL72 ??? ????? ??????. ???? ???? ???? ???????? Building Block Solutions (DCBBS) ?? ?????? ?????? ?????? ?????? ?????? ????????? ??? ????? ??????? ????? ????? ????????.
???? ???????? ???????? ???? ????? FP4 ????? 1.1 ????????? ?????? GB300 NVL72 ??? ????? ???? ???? ?????? ???? ??? 7.5x ?????? ?????? NVIDIA Hopper. ?????? ?????? ?? ??? ???? 800 Gb/s? ? 144 ???? ????? ?? ????? FP4 ? 270 GB ?? ????? HBM3e ??? ???? ?????? ??????.
?? ???? ????? DCBBS? ???? ??????? ????? ????? 40% ?? ??????? ????? ????? ???? ???????? ????? 60%? ??? ??????? ????? ????? 40%? ? ??? ??????? ????????? ??????? (TCO) ????? 20%.
厂耻辫别谤尘颈肠谤辞（纳斯达克：厂惭颁滨）宣布全球范围内发货其NVIDIA Blackwell Ultra 解决方案，其中包括 NVIDIA HGX B300 系统和 GB300 NVL72 机架。该公司的数据中心构建块解决方案（DCBBS）提供在系统、机架和数据中心尺度上经过预验证、即插即用的解决方案。
关键性能指标包括对 GB300 NVL72 机架级系统的1.1 exaFLOPS 稠密 FP4 计算性能，以及相对于 NVIDIA Hopper 系统最高可实现7.5x 的性能提升。这些解决方案具有 800 Gb/s 带宽、144 PetaFLOPS FP4 计算，以及每个 GPU 的 270 GB HBM3e 内存。
通过 DCBBS 的实现，客户可实现 40% 的电力节省、数据中心占地减少 60%、用水量减少 40%，以及 总拥有成本（TCO）降低 20%。
- New systems deliver 7.5x performance gains over previous NVIDIA Hopper systems
- Achieves 1.1 exaFLOPS dense FP4 compute performance in rack-scale systems
- Solutions enable 40% power savings and 20% lower Total Cost of Ownership
- 50% greater inferencing performance and 50% more HBM3e capacity compared to NVIDIA Blackwell
- Pre-validated, plug-and-play solutions enable rapid deployment and faster time-to-market
- Higher power requirements of up to 1400W per GPU may increase operational costs
- Complex infrastructure requirements including specialized cooling and networking systems
Insights
Supermicro's volume shipments of NVIDIA Blackwell Ultra systems position it advantageously in the rapidly growing AI infrastructure market.
Supermicro's announcement marks a significant milestone in the AI infrastructure landscape. The company is now shipping high-volume NVIDIA HGX B300 systems and NVIDIA GB300 NVL72 systems to customers worldwide, positioning itself at the forefront of next-generation AI hardware deployment.
The technical specifications are particularly noteworthy. The GB300 NVL72 rack-scale system delivers 1.1 exaFLOPS of dense FP4 compute performance, while the HGX B300 systems provide up to 7.5x performance gains over previous NVIDIA Hopper-based systems. Each GPU features 144 petaFLOPS of FP4 compute capability and 270 GB of HBM3e memory. These specifications represent substantial improvements that enable more sophisticated AI model training and inference.
What's strategically important here is Supermicro's focus on pre-validated, plug-and-play solutions at system, rack, and data center scale. This approach addresses critical deployment challenges including complex network topology, cabling, power delivery, and thermal management. By delivering turn-key solutions, Supermicro is reducing time-to-market for customers building AI factories - a significant competitive advantage in the rapidly evolving AI infrastructure space.
Supermicro's Data Center Building Block Solutions (DCBBS) offering also highlights the company's focus on operational efficiency, claiming to help customers save up to 40% power, reduce 60% data center footprint, and decrease 40% water consumption, leading to a 20% lower TCO (Total Cost of Ownership). These efficiency gains are crucial differentiators as data centers face increasing power constraints and sustainability pressures.
The announcement of volume shipments indicates Supermicro has successfully navigated supply chain challenges to secure components for these high-demand systems, positioning it to capture significant market share in the current AI hardware upgrade cycle.
- Now delivering high volume NVIDIA HGX B300 systems and NVIDIA GB300 NVL72 in volume to customers worldwide
- Enabling turn-key day-one operation by delivering pre-validated solutions at system, rack, and data center-scale through Supermicro Data Center Building Block Solutions? (DCBBS)
- Complete portfolio of 10+ SKUs now available featuring NVIDIA Blackwell and Blackwell Ultra to create diverse AI Factory environments at any scale
"Supermicro has the best track record of fast and successful deployments of new NVIDIA technologies," said Charles Liang, president and CEO of Supermicro. "Through Supermicro Data Center Building Block Solutions with our expertise in on-site deployment, we enable turn-key delivery of the highest-performance AI platform — critical for customers seeking to invest in cutting-edge technology. Data center customers face many AI infrastructure challenges: complex network topology and cabling, power delivery, and thermal management. Supermicro delivers pre-validated, plug-and-play solutions at system, rack, and data center scale, enabling AI factories to deploy rapidly and helping our customers lead in AI."
For more information, please visit
Supermicro integrates Blackwell Ultra generational advancements with system-level and rack-level engineering to create a solution that maximizes efficiency and performance at scale. At the system level, Supermicro's NVIDIA Blackwell Ultra systems feature advanced air and liquid cooling design optimized for the increased GPU power utilization. Blackwell Ultra's GB300 and B300 can be configured to use up to 1400W per GPU while offering
Supermicro's complete Blackwell Ultra portfolio leverages breakthrough innovations including the company's direct liquid cooling (DLC) technology stack, advanced air cooling, and I/O design optimization. Validated by market-proven deployments, Supermicro delivers at volume the industry's broadest portfolio of NVIDIA Blackwell systems. These Supermicro NVIDIA Blackwell Ultra solutions are specifically engineered as the building blocks for AI factories of the future and doubling compute network bandwidth to achieve new benchmarks in AI factory productivity.
Breakthroughs in AI, including the development of foundation models now with trillions of parameters, are forged at the cluster and data center-level with enormous AI factories interconnected with high-bandwidth networking. Supermicro offers NVIDIA Blackwell Ultra reference architecture solutions for enterprises seeking plug-and-play deployment of NVIDIA Quantum-X800 InfiniBand or NVIDIA Spectrum-X? Ethernet compute fabrics with bandwidth up to 800 Gb/s. From a single rack to cluster level configurations as fully scalable plug-and-play units, with a choice of air or liquid cooling, these reference architecture-based solutions allow customers to take full advantage of Blackwell Ultra integration of 800 Gb/s NVIDIA ConnectX-8 SuperNICs into the NVIDIA GB300 NVL72 and NVIDIA HGX B300. Supermicro's GB300 NVL72 rack-scale system achieves 1.1 exaFLOPS dense FP4 compute performance, while NVIDIA HGX B300 systems in 8U air-cooled and 4U liquid-cooled configurations provide up to 7.5x performance gains over NVIDIA Hopper? accelerator based systems, with 144 petaFLOPS of FP4 compute and 270 GB of HBM3e memory per GPU.
Supermicro's total solution with NVIDIA Blackwell Ultra is fully integrated to combine the hardware with infrastructure software and application software, including NVIDIA AI Enterprise, NVIDIA Blueprints, and NVIDIA NIM to bring optimized AI performance to these powerful systems. In addition, Supermicro's DCBBS offers a range of services, including on-site deployment of cluster cabling and other critical data center components, including power and thermal equipment, to ensure fast time-to-market and time-to-online. Combined with its DLC-2 (direct liquid cooling) technology, DCBBS helps customers save up to
About Super Micro Computer, Inc.
Supermicro (NASDAQ: SMCI) is a global leader in Application-Optimized Total IT Solutions. Founded and operating in
Supermicro, Server Building Block Solutions, and We Keep IT Green are trademarks and/or registered trademarks of Super Micro Computer, Inc.
All other brands, names, and trademarks are the property of their respective owners.
?
View original content to download multimedia:
SOURCE Super Micro Computer, Inc.
FAQ
What performance improvements do Supermicro's NVIDIA Blackwell Ultra systems offer?
How much can customers save with Supermicro's DCBBS implementation?
What is the power consumption of Supermicro's new NVIDIA Blackwell Ultra GPUs?
What networking capabilities do Supermicro's NVIDIA Blackwell Ultra solutions offer?
What cooling options are available for Supermicro's NVIDIA Blackwell Ultra systems?
