Supermicro Unveils Liquid-Cooled AI Supercluster with NVIDIA GB200 NVL72 Platform

SuperMicro unveils NVIDIA GB200 NVL72 SuperCluster: liquid-cooled AI servers

SuperMicro has revealed its new NVIDIA GB200 NVL72 SuperCluster, a liquid-cooled Exascale Compute system in a single rack, ready to go. Check it out: SuperMicro details its end-to-end AI data center solutions: "In the era of AI, a unit of compute is no longer measured by just the number of servers. Interconnected GPUs, CPUs, memory, storage, and these resources across multiple nodes in racks construct today's artificial Intelligence". The company continues: "The infrastructure requires high-speed and low-latency network fabrics, and carefully designed cooling technologies and power delivery to sustain optimal performance and efficiency for each data center environment. Supermicro's SuperCluster solution provides end-to-end AI data center solutions for rapidly evolving Generative AI and Large Language Models (LLMs)". SuperMicro intros its new AI supercluster powered by the NVIDIA GB200 NVL72 AI server cabinet as the "full turn-key data center solution accelerates time-to-delivery for mission-critical enterprise use cases, and eliminates the complexity of building a large cluster, which previously was achievable only through the intensive design tuning and time-consuming optimization of supercomputing".

Supermicro's Liquid-Cooled SuperClusters for AI Data Centers Powered by NVIDIA GB200 NVL72 and NVIDIA HGX B200 Systems, Deliver a New Paradigm of Energy-Efficient Exascale Computing | Supermicro

- (NASDAQ: SMCI), a Total IT Solution Provider for AI, Cloud, Storage, and 5G/Edge, is accelerating the industry's transition to liquid-cooled data centers with the NVIDIA Blackwell platform to deliver a new paradigm of energy-efficiency for the rapidly heightened energy demand of new AI infrastructures. Supermicro's industry-leading end-to-end liquid-cooling solutions are powered by the NVIDIA GB200 NVL72 platform for exascale computing in a single rack and have started sampling to select customers for full-scale production in late Q4. In addition, the recently announced Supermicro X14 and H14 4U liquid-cooled systems and 10U air-cooled systems are production-ready for the NVIDIA HGX B200 8-GPU system. "We're driving the future of sustainable AI computing, and our liquid-cooled AI solutions are rapidly being adopted by some of the most ambitious AI Infrastructure projects in the world with over 2000 liquid-cooled racks shipped since ," said , president and CEO of Supermicro. "Supermicro's end-to-end liquid-cooling solution, with the NVIDIA Blackwell platform, unlocks the computational power, cost-effectiveness, and energy-efficiency of the next generation of GPUs, such as those that are part of the NVIDIA GB200 NVL72, an exascale computer contained in a single rack. Supermicro's extensive experience in deploying liquid-cooled AI infrastructure, along with comprehensive on-site services, management software, and global manufacturing capacity, provides customers a distinct advantage in transforming data centers with the most powerful and sustainable AI solutions." https://www.supermicro.com/en/solutions/ai-supercluster Supermicro's liquid-cooled SuperClusters for NVIDIA GB200 NVL72 platform-based systems feature the new advanced in-rack or in-row coolant distribution units (CDUs), and custom cold plates designed for the compute tray housing two NVIDIA GB200 Grace Blackwell Superchips in a 1U form factor. Supermicro's NVIDIA GB200 NVL72 delivers exascale AI computing capabilities in a single rack with Supermicro's end-to-end liquid-cooling solution. The rack solution incorporates 72 NVIDIA Blackwell GPUs and 32 NVIDIA Grace CPUs, interconnected by NVIDIA's fifth generation NVLink network. The NVIDIA NVLink Switch system facilitates 130 terabytes per second (TB/s) of total GPU communication with extremely low latency, enhancing performance for AI and high-performance computing (HPC) workloads. In addition, Supermicro supports recently announced NVIDIA GB200 NVL2 platform, 2U air-cooled system featuring tightly coupled two NVIDIA Blackwell GPUs and two NVIDIA Grace CPUs that is suited for easy deployment with diverse workloads such as large LLM inference, RAG, data processing, and HPC applications. Supermicro's leading 4U liquid-cooled systems and the new 10U air-cooled systems now support the NVIDIA HGX B200 8-GPU system and are ready for production. The newly developed cold plates and the 250kW capacity in-rack coolant distribution unit maximize the performance and efficiency of the 8-GPU systems, providing 64x 1000W NVIDIA Blackwell GPUs and 16x 500W CPUs in a single 48U rack. Up to 4 of the new 10U air-cooled systems can be installed and fully integrated in a rack, the same density as the previous generation, while providing up to 15x inference and 3x training performance. SuperCloud Composer software, Supermicro's comprehensive data center management platform, provides powerful tools to monitor vital information on liquid-cooled systems and racks, coolant distribution units, and cooling towers, including pressure, humidity, pump and valve conditions, and more. SuperCloud Composer's Liquid Cooling Consult Module (LCCM) optimizes the operational cost and manages the integrity of liquid-cooled data centers. Scaling the infrastructure for multi-trillion parameter AI models, Supermicro is at the forefront of adopting networking innovations for both InfiniBand and Ethernet, including NVIDIA BlueField®-3 SuperNICs and NVIDIA ConnectX® -7 at 400Gb/s, NVIDIA ConnectX® -8, SpectrumTM-4, and NVIDIA Quantum-3 to enable 800Gb/s networking for the NVIDIA Blackwell platform. The NVIDIA Spectrum-XTM Ethernet with Supermicro's 4U liquid-cooled and 8U air-cooled NVIDIA HGX H100 and H200 system clusters now powers one of the largest AI deployments to date. From proof-of-concept (PoC) to full-scale deployment, Supermicro is a one-stop shop, providing all necessary technologies, liquid-cooling, networking solutions, and onsite installation services. Supermicro delivers a comprehensive, in-house-designed liquid-cooling ecosystem, encompassing custom-designed cold plates optimized for various GPUs, CPUs, and memory modules, along with multiple CDU form factors and capacity, manifolds, hoses, connectors, cooling towers, and monitoring and management software. This end-to-end solution seamlessly integrates into rack-level configurations, significantly boosting system efficiency, mitigating thermal throttling, and simultaneously reducing both the Total Cost of Ownership (TCO) and environmental impact of data center operations for the era of AI. Supermicro at 2024 OCP Global Summit *New X14 4U liquid-cooled system with NVIDIA HGX B200 8-GPU system *Supermicro's SuperCluster NVIDIA GB200 NVL72 Platform 4 *H13 4U liquid-cooled system with NVIDIA HGX H200 8-GPU system

Super Micro Expands Liquid-Cooled AI Servers With Nvidia Power - NVIDIA (NASDAQ:NVDA), Super Micro Computer (NASDAQ:SMCI)

Supermicro's new JBOF system integrates Nvidia BlueField-3 for advanced AI storage solutions Artificial intelligence server company Super Micro Computer, Inc SMCI is accelerating the shift to liquid-cooled data centers. Supermicro's latest offering, powered by the Nvidia Corp NVDA GB200 NVL72 platform, introduces a highly energy-efficient system designed to meet the increasing energy demands of AI infrastructures. This solution, which supports exascale computing in a single rack, has shipped samples to select customers, with full-scale production slated for the late fourth quarter of 2024. Supermicro is also ready for production with its recently announced X14 and H14 liquid-cooled systems and 10U air-cooled systems, which support the Nvidia HGX B200 8-GPU system. Also Read: Marvell Showcases Next-Gen 3nm Technology, Doubling Data Speeds for AI Systems These systems are part of a broader effort by the company to expand its liquid-cooled infrastructure solutions to provide enhanced computational power and energy efficiency for AI projects. According to Supermicro's CEO, Charles Liang, the company has shipped over 2,000 liquid-cooled racks since June 2024. The Supermicro Nvidia GB200 NVL72 delivers exascale AI capabilities in a single rack, integrating 72 Nvidia Blackwell GPUs and 32 Nvidia Grace CPUs. Supermicro also launched a new high-performance storage system for AI training, inference, and HPC (High-Performance Computing) workloads. The Just a Bunch of Flash (JBOF) system integrates Nvidia BlueField-3 Data Processing Units (DPUs) into a 2U form factor, offering advanced storage and networking features that support software-defined storage workloads. This innovation includes capabilities such as encryption, compression, erasure coding, and AI storage expansion. The new dual-port JBOF architecture delivers active-active clustering, ensuring high availability for both mission-critical scale-up storage and scale-out storage systems. Last week, Supermicro deployed over 100,000 GPUs with liquid cooling solutions (DLC) for some of the largest AI factories and other Cloud Service Providers (CSPs). At the same time, the company has battled with regulatory attention from the U.S. Department of Justice following Hindenburg Research's short report. The report flagged the company's inappropriate revenue recognition policies and the re-hiring of employees charged with past accounting violations. Supermicro stock gained over 67% in the last 12 months despite losing 42% in the previous three months due to the short report. Needham analyst Quinn Bolton praised the AI server company as a pioneer in rack-level liquid cooling solutions. Investors can gain exposure to Supermicro through Invesco QQQ Trust, Series 1 QQQ and SPDR S&P 500 SPY. Price Action: SMCI stock is up 0.55% at $48.02 premarket at the last check on Wednesday. Also Read: Google Parent Alphabet Should Trade At A Premium Versus Peers: Analyst This content was partially produced with the help of AI tools and was reviewed and published by Benzinga editors. Market News and Data brought to you by Benzinga APIs