 |
- The total solution includes up to 1,152 NVIDIA Rubin GPUs and 576 NVIDIA Vera CPUs in a liquid-cooled rack—a 3.2MW scalable unit delivering next-generation performance for AI workloads and FP64 simulations, scalable to research clusters of any size
- DLC-2 direct liquid cooling technology supports 362 kW heat dissipation per rack, with 3 in-row CDUs (Coolant Distribution Units) per scalable unit, plus cold plates, splitter manifolds, and SMC PG25-A ultra-high resistivity coolant
- End-to-end solution accelerates AI and HPC infrastructure construction for scientific research, covering everything from project planning and site surveys, to manufacturing and testing, to on-site deployment
San Jose, California and Hamburg, GermanyJune 24, 2026 /PRNewswire/ — Super Micro Computer, Inc. (NASDAQ: SMCI), a provider of total solutions for AI, enterprise, storage, and 5G/edge computing, announced the Data Center Building Block Solutions® (DCBBS) HPC blueprint based on the NVIDIA Vera Rubin NVL4 platform at ISC 2026. Following Supermicro’s launch of DCBBS blueprints for NVIDIA Vera Rubin NVL72 and NVIDIA HGX Rubin NVL8 at Computex, this HPC and AI blueprint applies the same end-to-end methodology to scientific computing. Built on Supermicro’s DCBBS, the blueprint provides the necessary compute, networking, advanced liquid cooling, power distribution, and site infrastructure, delivered by Supermicro’s DCBBS expert team to accelerate infrastructure time-to-deployment for research institutions and supercomputing centers.
NVIDIA Vera Rubin NVL4
“Scientific discovery has always been driven by the tools available to researchers, and AI has become an integral part of the research process,” said Charles Liang, President and CEO of Supermicro. “Institutions that can accelerate infrastructure deployment will lead the next wave of breakthroughs. With our DCBBS blueprint for NVIDIA Vera Rubin NVL4, research institutions can confidently deploy HPC and AI infrastructure at any scale, backed by Supermicro’s proven experience in building the world’s largest liquid-cooled clusters.”
Click here to learn more about DCBBS.
Researchers are increasingly relying on converged computing methods that combine traditional FP64 double-precision simulations with accelerated computing and AI approaches, revolutionizing discovery cycles in fields such as climate research, drug discovery, materials science, and energy. The NVIDIA Vera Rubin NVL4 platform is built for this convergence, and the DCBBS HPC blueprint outlines the steps for successful deployment, leveraging Supermicro’s proven track record in building the world’s largest liquid-cooled supercomputing clusters with over 100,000 GPUs.
The blueprint covers the complete end-to-end process Supermicro uses to deliver large-scale liquid cooling projects at record speed. On-site facility surveys conducted by Supermicro experts assess loading dock access, data room dimensions and clearance, floor load ratings, and existing power and cooling infrastructure, tailoring the design to each project. Solution integration begins before delivery, including rack installation, equipment stacking, cabling, and system-level (L10) and cluster-level (L11) testing at Supermicro’s global manufacturing facilities. Premium “white-glove” delivery and on-site integration services include rack placement, power and cooling connections, network cabling, commissioning, and on-site solution validation, with ongoing operational support options including 4-hour on-site response times for mission-critical uptime.
Scalable AI and HPC Solutions for Modernizing Scientific Research Computing Infrastructure
The Supermicro DCBBS HPC and AI blueprint based on the NVIDIA Vera Rubin NVL4 scalable unit includes the following, enabling deployment of clusters from 3.2MW to 1GW by scaling units:
- 8 liquid-cooled compute racks, using custom 52U, 750mm-wide cabinets, each housing 36 NVIDIA Vera Rubin NVL4 nodes within a 362 kW power envelope; totaling 288 nodes, up to 1,152 NVIDIA Rubin GPUs, and 576 NVIDIA Vera CPUs per scalable unit
- Advanced direct liquid cooling stack (DLC-2), including 3 in-row coolant distribution units per scalable unit (each rated up to 1.8MW) in a 2+1 redundant configuration, with direct-to-chip copper cold plates, vertically mounted coolant distribution manifolds, and Supermicro SMC PG25-A coolant with superior chemical and thermal stability
- NVIDIA Quantum-X800 InfiniBand compute network architecture deployed across dedicated network switch racks (with full liquid cooling options), providing high-bandwidth scale-out interconnects for distributed scientific and AI workloads
- Rack power and management: 8 72 kW power shelves per compute rack, powering the rack via busbars within the 362 kW design power envelope; two ToR management switches per rack for out-of-band control
Additionally, HPC and AI configurations based on NVIDIA GB200 NVL4 are available for immediate deployment.
Supermicro DCBBS delivers complete, modular AI infrastructure built from proven components and subsystems, supporting flexible deployment from single servers and network devices to full rack-level and data center-level solutions, with accompanying software and services. Supermicro continues to lead the industry with its comprehensive AI infrastructure solution portfolio, helping organizations worldwide deploy scalable, efficient, and environmentally friendly AI data centers.
Supermicro will showcase its HPC and AI infrastructure solutions at ISC 2026 (Hall H, Booth B10). For more information, visit www.supermicro.com.
About Super Micro Computer, Inc.
Supermicro (NASDAQ: SMCI) is a global leader in application-optimized total IT solutions. Founded and operating in San Jose, California, Supermicro is committed to delivering market-first innovations for enterprise, cloud, AI, and 5G telecom/edge IT infrastructure. We are a comprehensive IT solutions provider offering servers, AI, storage, IoT, switch systems, software, and support services. Supermicro’s expertise in motherboard, power, and chassis design further drives its R&D and production, enabling next-generation innovation for global customers from cloud to edge. Our products are designed and manufactured internally in the US, Asia, and the Netherlands, achieving scale and efficiency through global operations while optimizing total cost of ownership (TCO) and reducing environmental impact (green computing). The award-winning Server Building Block Solutions® portfolio allows customers to optimize for specific workloads and application needs, selecting from a rich system family built from flexible, reusable building blocks supporting a variety of form factors, processors, memory, GPUs, storage, networking, power, and cooling solutions (air conditioning, free air cooling, or liquid cooling).
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.