Supermicro Showcases the Future of HPC Clusters and AI Infrastructure at Supercomputing 2025

Rhea-AI Summary

Supermicro (NASDAQ:SMCI) announced its showcase at Supercomputing 2025 on November 17, 2025, highlighting AI, HPC, and liquid-cooled data center solutions.

Key exhibits include rack-scale NVIDIA GB300 NVL72 (72 Blackwell Ultra GPUs, 36 Grace CPUs, 279GB HBM3e per GPU), 4U HGX B300 liquid-cooled racks, 1U GB200 NVL4 nodes, Super AI Station desktops, liquid-cooled SuperBlade and FlexTwin platforms, and density-optimized MicroBlade and BigTwin systems. The company emphasized its DCBBS architecture and direct liquid cooling with Rear Door Heat Exchangers (50kW/80kW), Sidecar CDUs up to 200kW, and closed-loop water/dry towers to improve efficiency, scalability, and time-to-online for enterprise AI and HPC deployments.

Insights

HPC infrastructure strategist

Supermicro unveils rack-scale liquid-cooled systems and DCBBS at SC25, signaling product-driven push into large-scale AI/HPC deployments.

Supermicro showcases an expanded portfolio of high-density, liquid-cooled platforms built around NVIDIA GB300 and HGX B300 technologies, targeting CPU- and GPU-bound workloads at scale. The announcement describes integrated Data Center Building Block Solutions (DCBBS) that combine compute, storage, networking, and thermal management to shorten deployment time for complex AI and HPC stacks. The product set ranges from desktop AI workstations to 4U/8U/20-node rack systems and in-rack cooling, which together form a coherent hardware offering for turnkey installations.

Execution depends on customer adoption, supply chain delivery, and successful integration with partner technologies; these factors determine near-term commercial impact. Claims of specific cooling capacities and node densities are factual product specs here but do not prove revenue or market share changes. Watch for publicized customer wins, shipping start dates, capacity orders, or specification-based benchmarks within the next 12 months to assess material commercial impact. Also monitor announcements of large-scale deployments or purchase agreements disclosed at or after SC25 and any measured energy-efficiency data under real workloads.

• In-booth demos will feature new Data Center Building Block Solutions^® (DCBBS) incorporating NVIDIA GB300 NVL72 and NVIDIA HGX^™ B300 Systems
• Future-ready data centers are designed to drive energy efficiency, scalability, performance, and reduce time-to-online
• Advanced cooling products, including Rear Door Heat Exchangers and Sidecar Cooling Distribution Units will be on display

SAN JOSE, Calif. and ST. LOUIS, Nov. 17, 2025 /PRNewswire/ -- Supercomputing Conference --Super Micro Computer, Inc. (SMCI), a Total IT Solution Provider for AI/ML, HPC, Cloud, Storage, and 5G/Edge, will showcase its latest AI Factory, HPC, and liquid-cooled data center innovations at Supercomputing 2025 (SC25) in St. Louis, Missouri. This broad portfolio, ranging from desktop workstations to rack-scale solutions, demonstrates Supermicro's commitment to powering the next generation of high-performance computing, scientific research, and enterprise AI deployments.

"Supermicro continues to lead the industry in delivering complete, next-generation infrastructure solutions in close collaboration with our technology partners," said Charles Liang, president and CEO of Supermicro. "At SC25, we are demonstrating our high-performance DCBBS architecture, direct liquid cooling, and rack-scale innovations, which empower customers to deploy AI and HPC workloads faster, more efficiently, and more sustainably."

For more information, please visit: https://www.supermicro.com/en/event/sc25

Supermicro Systems will showcase new platforms designed to improve performance for both CPU- and GPU-bound workloads in large-scale HPC and AI environments.

Key highlights include:

• NVIDIA GB300 NVL72 with Liquid Cooling – Rack-scale solution with NVIDIA GB300 Grace™ Blackwell Superchips providing 72 NVIDIA Blackwell Ultra GPUs and 36 Grace CPUs per rack with 279GB HBM3e per GPU
• 4U HGX B300 Server Liquid Cooled Rack with In-Rack CDU
• 1U NVIDIA GB200 NVL4 Server (ARS-121GL-NB2B-LCC) - A high-density, liquid-cooled compute node purpose built for large-scale HPC and AI training.
• Super AI Station Based on NVIDIA GB300 (ARS-511GD-NB-LCC) - An AI and HPC development platform integrated into a desktop workstation form factor.
• Liquid-cooled 8U 20-node and 6U 10-node SuperBlade – An advanced liquid cooled platform delivering maximum CPU and GPU density, supporting Intel^® Xeon^® 6900, 6700, and 6500 Series processors up to 500W.
• Liquid-cooled 2U FlexTwin multi-node system - An advanced liquid cooled (up to 95% heat capture) platform delivering maximum CPU computing density with four independent nodes, each equipped with the highest-performance dual socket CPUs supporting either AMD EPYC™ 9005 processors or Intel^® Xeon^® 6900 Series processors up to 500W.

DCBBS and Direct Liquid Cooling Innovations

Supermicro's DCBBS integrates compute, storage, networking, and thermal management to simplify the deployment of complex AI and HPC infrastructure.

Key highlights include:

• Rear Door Heat Exchangers - Supporting cooling capacities of 50kW or 80kW
• Liquid-to-Air Sidecar CDUs (cooling distribution units)- Supporting cooling capacities up to 200kW, with no external infrastructure needed.
• Water Cooling and Dry Towers – Energy-efficient external towers which cool the liquid, in a closed loop design.

Optimized Product Families for HPC Workloads and AI Infrastructure

Supermicro's high-density, liquid-cooled systems address use cases across financial services, manufacturing, climate and weather modeling, oil and gas, and scientific research. Each distinct product family is designed with an optimized combination of density, performance, and efficiency.

SuperBlade ^® - The award-winning SuperBlade systems have been winning HPC customers worldwide for over 18 years. The latest generation X14 SuperBlade systems offer maximum performance and the highest density with both CPU and GPU for the most demanding HPC and AI workloads. Both air-cooling and direct-to-chip liquid cooling can be supported. With integrated InfiniBand and Ethernet switches, SuperBlade is ideal for HPC and AI applications. 

FlexTwin^™- The Supermicro FlexTwin architecture is purpose-built for HPC and is cost-efficient, designed to deliver maximum compute power and density in a multi-node configuration, with up to 24,576 performance cores in a 48U rack. Optimized for HPC and other compute-intensive workloads, each node features direct-to-chip liquid cooling to maximize efficiency and reduce CPU thermal throttling, enabling low latency front and rear I/O with a range of flexible networking options up to 400G per node.

BigTwin^® - Versatile Supermicro BigTwin is available as a 2U –4-Node or 2U 2-Node system. The Supermicro BigTwin shares power supplies and fans, which reduces power consumption. The BigTwin is available with the Intel^® Xeon^® 6 processor.

MicroBlade ^®  - The Supermicro 6U 40-node and 6U 20-node MicroBlade systems offer customers the highest density and a cost-effective single-socket x86 server solution. They have been used by leading semiconductor companies to design and develop ICs for over 10 years. MicroBlade systems support a wide range of CPUs including Intel Xeon 6300, Xeon D, and AMD EPYC 4005 Series. The latest generation MicroBlade systems can support up to 20 AMD EPYC 4005 Series CPUs and 20 GPUs in a 6U enclosure.

MicroCloud - Industry-proven design, scalable up to 10 CPU nodes or up to 5 CPU + GPU nodes per chassis. With up to 10 server nodes in only 3U of rack space, customers can increase their computing density by over 3.3x compared to industry-standard 1U rackmount servers.

Petascale Storage – Density-maximized all-flash storage systems optimized for scale-out and scale-up software-defined storage, with easy-to-deploy 1U and 2U form factors supporting industry standard EDSFF media.

Workstation - Workstation performance and flexibility in a rackmount form factor, offering increased density and security for organizations looking to utilize centralized resources.

Supermicro at SC25

Visit Supermicro at booth #3504 to check out the latest innovations and visit the in-booth theater to hear directly from experts, customers, and partners.

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 first to market innovation for Enterprise, Cloud, AI, and 5G Telco/Edge IT Infrastructure. We are a Total IT Solutions provider with server, AI, storage, IoT, switch systems, software, and support services. Supermicro's motherboard, power, and chassis design expertise further enables our development and production, enabling next generation innovation from cloud to edge for our global customers. Our products are designed and manufactured in-house (in the US, Taiwan, and the Netherlands), leveraging global operations for scale and efficiency and optimized to improve TCO and reduce environmental impact (Green Computing). The award-winning portfolio of Server Building Block Solutions® allows customers to optimize for their exact workload and application by selecting from a broad family of systems built from our flexible and reusable building blocks that support a comprehensive set of form factors, processors, memory, GPUs, storage, networking, power, and cooling solutions (air-conditioned, 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.

 

View original content to download multimedia:https://www.prnewswire.com/news-releases/supermicro-showcases-the-future-of-hpc-clusters-and-ai-infrastructure-at-supercomputing-2025-302616668.html

SOURCE Super Micro Computer, Inc.

FAQ

What did Supermicro (SMCI) announce at Supercomputing 2025 on November 17, 2025?

Supermicro showcased AI/HPC systems including NVIDIA GB300 NVL72 racks, 4U HGX B300 liquid-cooled racks, SuperBlade, FlexTwin, MicroBlade, and DCBBS cooling innovations.

What are the cooling capacities Supermicro highlighted at SC25 for SMCI data center products?

Supermicro highlighted Rear Door Heat Exchangers at 50kW and 80kW, and Sidecar CDUs supporting up to 200kW with closed-loop water/dry towers.

What are the GPU and CPU counts in the NVIDIA GB300 NVL72 rack showcased by SMCI?

The GB300 NVL72 rack configuration provides 72 NVIDIA Blackwell Ultra GPUs and 36 Grace CPUs per rack with 279GB HBM3e per GPU.

How does Supermicro’s DCBBS (Data Center Building Block Solutions) affect deployment time for SMCI customers?

DCBBS integrates compute, storage, networking, and thermal management to simplify deployments and reduce time-to-online for AI and HPC infrastructure.

Which Supermicro systems are optimized for highest density HPC in SMCI’s SC25 lineup?

FlexTwin, SuperBlade, MicroBlade, and BigTwin were presented as high-density options, with FlexTwin supporting up to 24,576 performance cores in a 48U rack.

Where can investors see Supermicro’s Supercomputing 2025 demonstrations for SMCI?

Supermicro exhibited at booth #3504 with in-booth demos and a theater featuring experts, customers, and partners.