Nvidia's Blackwell GPU architecture expansion is driving server and platform update demand from manufacturer Super Micro Computer.
Super Micro Computer Inc. (NASDAQ:SMCI), one of the 10 Data Center Cooling Companies to Invest In, expanded its NVIDIA Blackwell Portfolio on December 9 by introducing new 4U and 2-OU (OCP) liquid-cooled NVIDIA HGX B300 systems. These products are designed to deliver power efficiency and exceptional GPU density for AI factory deployments and hyperscale data centers. The company developed these platforms to target customer needs for higher efficiency, lower cost, and serviceability.
Data centers leveraging the DLC-2 technology stack can save up to 40% on power consumption. Additionally, the systems reduce water usage through warm 45°C water operation, eliminating the need for compressors and chilled water in data centers. The new systems are provided as fully tested, ready-to-use L11 and L12 racks, enabling enterprise, federal, and hyperscaler customers to deploy their data centers faster.
Charles Liang, president and CEO of Supermicro, stated: "With AI infrastructure demand accelerating globally, our new liquid-cooled NVIDIA HGX B300 systems deliver the performance density and energy efficiency that hyperscalers and AI factories need today. We're now offering the industry's most compact NVIDIA HGX B300 solutions—achieving up to 144 GPUs in a single rack—while reducing power consumption and cooling costs through our proven direct liquid-cooling technology. Through our DCBBS, this is how Supermicro enables our customers to deploy AI at scale: faster time-to-market, maximum performance per watt, and end-to-end integration from design to deployment."
Super Micro Computer Inc. is a seller and developer of server and storage solutions, providing liquid and air-cooled AI servers, SuperStorage systems, MicroCloud server systems, and embedded systems for 5G, IoT, and Edge applications. The firm serves artificial intelligence, edge computing, 5G, enterprise data center, and cloud computing markets.