Supermicro and Arm Unveil Next-Generation Rack-Scale AI Solutions
Super Micro Computer, Inc. (NASDAQ: SMCI), a leading provider of AI, enterprise, storage, and 5G/Edge total solutions, has announced a new class of AI-centric infrastructure featuring Arm AGI CPUs. These solutions are designed to meet the increasing compute demands of modern agentic AI, maximizing performance within the power and space constraints of enterprise data centers.
New Infrastructure for Agentic AI
The new rack-scale infrastructure from Supermicro aims to support the rapid growth of agentic AI by delivering enhanced performance, efficiency, and density. By leveraging Supermicro's Data Center Building Block Solutions (DCBBS), the company reduces time-to-online for large-scale deployments. The Arm AGI CPU is optimized for agentic AI workload orchestration, ensuring maximum compute performance density within any power envelope.
Executive Insights
Charles Liang, president and CEO of Supermicro, stated, "Supermicro continues to lead the industry when it comes to deploying new and innovative rack-scale solutions that maximize performance and efficiency. Our DCBBS technology stack delivers end-to-end data center solutions of any size, which combined with the new density and efficient performance optimized Arm AGI CPU microarchitecture, helps enterprises realize significant TCO savings on their agentic AI infrastructure investments."
Mohamed Awad, Executive Vice President, Cloud AI Business Unit at Arm, added, "Agentic AI is driving a fundamental shift in infrastructure requirements, where efficiency, scalability, and orchestration performance are becoming just as critical as raw compute. By combining Arm AGI CPUs with Supermicro's rack-scale system expertise, we're enabling infrastructure designed to deliver higher AI throughput, maximum compute density, and improved data center economics at scale."
Product Lineup and Specifications
Supermicro's new computing platforms include air-cooled dual-socket 2U compute-optimized and 5U GPU-optimized rackmount servers, as well as a liquid-cooled multi-node solution for rack-scale agentic AI deployments. These systems combine Supermicro's modular architectures with Arm Neoverse CSS V3-based CPUs to maximize performance-per-watt and reduce energy demand.
Key models include:
- 2U Hyper Server (ARS-222H-NR): Optimized for agentic AI and memory-intensive workloads, featuring two Arm AGI CPUs (up to 136 cores each), up to 6TB DDR5-8800 MT/s RDIMMs, and support for up to two GPUs.
- 5U GPU Server (ARS-522GP-NR): GPU-dense configuration for AI training and inference, with two Arm AGI CPUs, up to 6TB DDR5-8800 MT/s RDIMMs, and up to eight double-width GPUs.
- 2U4N Liquid-Cooled Server (ARS-242TP-QNR-LCC): Designed for OCP ORV3 environments, with two Arm AGI CPUs per node, four nodes in 2-OU, up to 6TB DDR5-8800 MT/s RDIMMs per node, and potential for up to 20,672 cores per ORV3 rack.
- 2U Hyper-E Server (ARS-212HE-FNR): Single-socket edge-optimized architecture with front I/O, one Arm AGI CPU (up to 136 cores), up to 3TB DDR5-8800 MT/s RDIMMs, and up to two GPUs.
- 1U 4N in OCP ORW Rack: Massive compute density with 336 Arm AGI CPUs per rack, 168 servers, and 45,696 cores per rack.
Performance and Efficiency Gains
When deployed in Supermicro solutions, the Arm AGI CPU can deliver over 2x performance per rack compared to traditional architectures. Arm estimates that enterprises could save up to $10 billion in CAPEX per Gigawatt of AI data center capacity. With over 6,000 cores in a single air-cooled rack, enterprises can efficiently deploy dedicated systems for a high volume of agentic AI tasks.
The Arm AGI CPU features a dense 136-core microarchitecture designed for performance, reducing legacy overhead and enabling sustained, unthrottled performance. It offers 6GB/s memory bandwidth per core and latency-optimized memory access for linear scaling, along with expanded memory capacity and flexible I/O for energy-efficient, scalable agentic AI infrastructure.
Availability and Demonstration
The latest rack-scale solutions will be on display at the Supermicro booth at Taipei Nangang Exhibition Center Hall 1, 4F, N0602, offering attendees a firsthand look at their design and capabilities.
About Super Micro Computer, Inc.
Supermicro (NASDAQ: SMCI) is a global leader in Application-Optimized Total IT Solutions. Founded in San Jose, California, the company provides first-to-market innovation for Enterprise, Cloud, AI, and 5G Telco/Edge IT Infrastructure. Supermicro offers server, AI, storage, IoT, switch systems, software, and support services, with products designed and manufactured in the US, Taiwan, and the Netherlands. The company's Server Building Block Solutions allow customers to optimize for exact workloads by selecting from a broad family of systems built from flexible and reusable building blocks.
