 |
- Arm AGI CPU is purpose-built for orchestrating agentic AI workloads, designed to maximize performance.
- Supermicro’s rack-scale Arm AGI CPU design enhances agentic AI compute performance density at any power level.
- Supermicro’s Data Center Building Block Solutions (DCBBS) and global manufacturing scale shorten the time-to-online for large-scale AI infrastructure.
San Jose, California and TaipeiJune 8, 2026 /PRNewswire/ — Super Micro Computer, Inc. (NASDAQ: SMCI), a total solution provider for AI, enterprise, storage, and 5G/edge, and a provider of optimized Data Center Building Block Solutions (DCBBS), today announced a series of AI solutions powered by the Arm® AGI CPU. As the computing demands of today’s agentic AI continue to grow, enterprise data centers require new rack-scale infrastructure to maximize compute performance within limited power budgets and deployment space. Supermicro’s new solutions are designed to support the rapid expansion of agentic AI, delivering exceptional performance, energy efficiency, and compute density through Supermicro’s end-to-end DCBBS, maximizing the economics of rack-scale deployments and further reducing time-to-online.
Charles Liang, President and CEO of Supermicro, said: “Supermicro continues to lead the industry in deploying new, innovative rack-scale solutions to maximize performance and efficiency. Our DCBBS technology stack delivers end-to-end data center solutions at any scale. Combined with the optimized new high-density and high-performance microarchitecture of the Arm AGI CPU, we can help enterprises achieve a significantly beneficial total cost of ownership (TCO) on their agentic AI infrastructure investments.”
Learn more about Supermicro’s Arm server product line.
Supermicro’s New Rack Scale AI Solutions
Mohamed Awad, Executive Vice President of Arm’s Cloud AI Business, said: “Agentic AI is driving a fundamental shift in infrastructure requirements, where efficiency, scalability, and orchestration performance are now as critical as raw compute power. By combining the Arm AGI CPU with Supermicro’s rack-scale system technology, computing facilities can deliver higher AI throughput, maximized compute density, and better economics for large-scale data centers.”
Supermicro’s latest computing platforms include an air-cooled dual-socket 2U server optimized for compute performance, a GPU-optimized 5U rackmount server, and a liquid-cooled multi-node solution designed for rack-scale agentic AI deployments. By integrating Supermicro’s proven modular, high-density architecture with the energy-efficient Arm Neoverse® CSS V3 CPU, these solutions deliver scalable and resilient infrastructure that maximizes performance per watt and significantly reduces energy demands, accelerating AI adoption in modern data centers.
According to Arm’s estimates, combining the Arm AGI CPU with Supermicro solutions can deliver more than double the performance per rack compared to traditional architectures, helping enterprises save up to $10 billion in capital expenditure (CAPEX) per gigawatt of AI data center capacity. These solutions leverage Supermicro’s industry-leading rack density and performance per watt to ensure maximum utilization of data center space and power resources.
The Arm AGI CPU features a high-density 136-core microarchitecture designed for performance, minimizing overhead from traditional architectures and completing more work per cycle for sustained, throttling-free performance. With 6GB/s of memory bandwidth per core and latency-optimized memory access supporting linear scaling, along with increased memory capacity and flexible I/O configurations, it provides an energy-efficient, scalable architecture for agentic AI infrastructure to coordinate thousands of parallel processes across distributed infrastructure.
A single air-cooled rack can be configured with over 6,000 cores, enabling enterprises to efficiently deploy numerous specialized systems to handle large volumes of agentic AI tasks. Currently, Supermicro’s Arm architecture servers include five models:
2U Hyper Server – Optimized for agentic AI, cloud computing, and memory-intensive workloads
https://www.supermicro.com/en/products/system/hyper/2u/ars-222h-nr
- Dual Arm AGI CPUs, each supporting up to 136 cores
- Supports up to two GPUs
5U GPU Server – High-density GPU configuration designed for AI training and inference
https://www.supermicro.com/en/products/system/gpu/5u/ars-522gp-nr
- Dual Arm AGI CPUs, each supporting up to 136 cores
- Supports up to eight dual-width GPUs
2U 4N Liquid-Cooled Server – Suitable for OCP ORV3 environments
https://www.supermicro.com/en/products/system/hyper/2-ou/ars-242tp-qnr-lcc
- Dual Arm AGI CPUs per node, each supporting up to 136 cores
- Four nodes in a 2-OU architecture, with up to 20,672 cores per single ORV3 rack
2U Hyper-E Server – Single-socket edge computing optimized architecture with front I/O
https://www.supermicro.com/en/products/system/hyper/2u/ars-212he-fnr
- Single Arm AGI CPU, supporting up to 136 cores
- Supports up to two GPUs
OCP ORW Rack 1U 4N Configuration – Provides extreme compute density
- ORW – 48U rack specification
- 336 Arm AGI CPUs per rack
- 168 servers per rack, totaling 45,696 cores
Supermicro continues to lead the industry with comprehensive AI infrastructure solutions, helping global enterprises deploy scalable, high-performance, and environmentally responsible AI data centers.
About Super Micro Computer, Inc.
Supermicro (NASDAQ: SMCI) is a global leader in application-optimized total IT solutions. Headquartered and operating out of San Jose, California, Supermicro is committed to delivering market-leading innovative technologies for enterprise, cloud, AI, and 5G telecom/edge IT infrastructure. We are a total IT solutions manufacturer providing servers, AI, storage, IoT, switch systems, software, and support services. Supermicro’s expertise in motherboard, power, and chassis design further optimizes 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, Asia, and the Netherlands), reducing total cost of ownership (TCO) through product design optimization, minimizing environmental impact through green computing technology, and achieving exceptional manufacturing scale and efficiency through global operations. Our award-winning Server Building Block Solutions® portfolio allows customers to select optimal models from a highly diverse system product line to achieve best-in-class performance for their workloads and applications. This diverse system product line is built from highly flexible, reusable building blocks that support a wide range of hardware form factors, processors, memory, GPUs, storage, networking, power, and cooling solutions (air conditioning, natural 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.