SuperMicro offers architecture for new generation air and cooled by liquid for the NVIDIA Blackwell platform
San Jose, California.,, February 5, 2025 / Prnewswire / – Supermicro, Inc. (Nasdaq: SMCI), a total supplier of computer solutions for AI / ml, HPC, Cloud, storage and 5G / Edge, announces the full availability of the production of its AI -end -to -end data building solutions® Accelerated by the NVIDIA Blackwell platform. The SuperMicro construction block portfolio provides the basic infrastructure elements required at the Blackwell solutions for an exceptional time for deployment. The portfolio includes a wide range of air -cooled systems and cooled by liquid with several CPU options. These include a higher thermal design supporting traditional air cooling, liquid liquid cooling (L2L) and air liquid cooling (L2A). In addition, a series of complete data center management software, integration into the rack level, including the complete switching of the network and the wiring and the validation of the L12 solution at the level of the cluster can be offered as ‘Circleanner offer with overall delivery, professional support and service.
“In this AI transformer moment, when the ladder laws postpone the limits of the data center capacities, our latest solutions fueled by Nvidia Blackwell, developed by close collaboration with Nvidia, offer an exceptional calculation power” , said Charles LiangPresident and chief executive officer of Supermicro. “NVIDIA Blackwell GPU offers in Supermicro in scalable plug-and-play units with advanced liquid cooling and cooling, allow customers to deploy an infrastructure that supports the workloads of AI increasingly complex all By maintaining exceptional efficiency.
For more information, please visit www.supermicro.com/ai
NVIDIA HGX B200 8-GPU systems of Supermicro use liquid cooling and new generation air cooling technology. The newly developed cold plates and the new 250 kW cooling liquid distribution unit (CDU) double than double the cooling capacity of the previous generation in the same 4u shape factor. Available in 42U, 48U or 52U configurations, rack level design with new vertical coolant distribution collectors (CDM) no longer occupies precious rack units. This allows 8 systems, including 64 NVIDIA Blackwell GPU in a Rack 42U, and up to 12 systems with 96 NVIDIA Blackwell GPU in a 52U rack.
The new NVIDIA HGX B200 system, air -cooled, has a redesigned chassis with extended thermal margin to accommodate eight GPU Blackwell TDP 1000W. Up to 4 of the new air -cooled 10U systems can be installed and fully integrated into a rack, the same density as the previous generation, while offering up to 15x inference and 3x training performances.
The new SuperCluster conceptions integrate Nvidia Quantum-2 Infiniband or Nvidia Spectrum-X Ethernet Networking in a centralized rack, allowing an evolutionary unit of 256-GPU non-blocking in five racks or an extended evolutionary unit of 768-GPU in nine racks. This architecture-purposes-built for nvidia hgx B200 system with native support for the nvidia ai enterprise software platform for development and deploying production-grade, end-tond agentic ai pipelines-combined with supermicro’s expertise in deploying the world’s wide liquid-coolded Data centers offer exceptional efficiency and line time for the most ambitious AI data centers projects today.
Liquid or air cooled by air: NVIDIA HGX B200 Supermicro Systems
The new NVIDIA HGX B200 8U NVIDIA HGX B200 system offers newly developed cold plates and an advanced tube design that further improves the predecessor’s efficiency and ease of service that has been used for the NVIDIA HGX H100 / H200 8-GPU system . Completed by a new 250 kW cooling unit, double the cooling capacity of the previous generation while maintaining the same 4u form factor, the new design on a rack scale with the new liquid distribution collectors Vertical cooling (CDM) allows dense architecture with flexible configuration scenarios used for various data center environments. SuperMicro offers Rack 42U, 48U or 52U configurations for liquid -cooled data centers. The 42U or 48U configuration provides 8 systems and 64-GPU in a rack and a scalable unit of 256-GPU in five racks. The configuration of the Rack 52U allows 96-GPU in a rack and allows a 768-GPU scalable unit in nine racks for the most advanced AI data center deployments. SuperMicro also offers a CDU option in row for large deployments, as well as a liquid air cooler solution that does not require installation water.
Supermicro NVIDIA HGX B200 systems support NVIDIA AI Enterprise software to accelerate AI production time. NVIDIA NIM microservices allow organizations to access the latest AI models for rapid, secure and reliable deployment on NVIDIA accelerated infrastructure anywhere – whether in data centers, cloud or posts work.
For traditional data centers, the new NVIDIA B200 NVIDIA B200 10u cooling system is also available, with a redesigned modular gpu tank to house NVIDIA Blackwell GPU in an air -cooled environment. The design of the air -cooled rack follows the proven architecture and leader of the previous generation industry, four systems and 32 GPU in a Rack 48U, while providing Nvidia Blackwell performance. All NVIDIA HGX B200 SuperMicro HGX systems are equipped with a GPU / NIC 1: 1 report, taking charge of the NVIDIA Bluefield-3 Supernics or NVIDIA Connectx-7 NICS for the scale through a high performance calculation fabric.
SuperMicro provides management of systems included in the NVIDIA certified systems program. This program incorporates NVIDIA GPUs, CPUs and high -speed secure networking technologies in the systems of the main NVIDIA partners, guaranteeing validated configurations for optimal performance, reliability and scalability. By choosing an NVIDIA certified system, companies can select hardware solutions with confidence to feed their accelerated IT workloads. NVIDIA certified supermicro systems with NVIDIA H100 and H200 GPUs.
End -to -end cooling solution for NVIDIA GB200 NVL72
The SuperMicro SuperClusiveter solution, based on the NVIDIA GB200 NVL72 system, represents a breakthrough in the IT infrastructure AI, combining the liquid cooling technology from start -to -end of supermicro. The system incorporates 72 CPU NVIDIA Blackwell and 36 CPU NVIDIA GRACE in a single rack, offering exascal IT capacities via a most extensive NVLINK network in NVIDIA to date, reaching 130 TB / S of GPU communications.
The versatility of the 48U solution supports the air and liquid liquid cooling configurations, to adapt to various data center environments. In addition, supermicro Supercloud Composer The software provides management tools to monitor and optimize the infrastructure cooled by liquid, offering a complete solution of proof of concept to large -scale deployment.
End -to -end data center and deployment services for Nvidia Blackwell
From proof of concept (POC) to large -scale deployment, SuperMicro serves as a complex one -shop solutions supplier with a global manufacturing scale, offering all the necessary components, design of solutions at the level of the data center, coloring technologies Liquid, networking solutions, cabing, management software, tests and validation and on -site installation services. Its internal liquid cooling ecosystem offers a complete and custom -designed thermal management solution, with cold plates optimized for GPUs, processors and memory modules, as well as versatile formal coolant distribution factors and Capacities, collectors, pipes, connectors, cooling the cooling liquid towers and sophisticated surveillance and management software. With production facilities through San Jose,, EuropeAnd AsiaSuperMicro offers an unrivaled manufacturing capacity for rack -cooled rack systems, guaranteeing a timely delivery, reduces the total cost of possession (TCO) and the environmental impact and coherent quality.
About Super Micro Computer, Inc.
Supermicro (Nasdaq: SMCI) is a world leader in total IT solutions optimized by applications. Founded and operating in San Jose, CaliforniaSuperMicro undertakes to first deliver to market innovation for the IT infrastructure of the company, the cloud, the AI and the 5G. We are a total supplier of computer solutions with server, AI, storage, IoT, switching systems, software and support services. The design of the design of the motherboard, energy and supermicro chassis also allows our development and production, allowing new generation of the cut -off generation for our global customers. Our products are designed and manufactured internally (in the United States, TaiwanAnd The Netherlands), Take advantage of global operations for scale and efficiency and optimized to improve TCO and reduce the environmental impact (Green IT). The award -winning portfolio of Building Block Solutions® servers allows customers to optimize their accurate workload and application by selecting from a wide family of systems built from our flexible and reusable construction elements that take care of a complete set of form factors, processors, memory, GPU, 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 commercial brands and / or registered trademarks of Super Micro Computer, Inc.
All other brands, names and brands are the property of their respective owners.
Super micro Computer source, Inc.
