CHICAGO, Nov. 10, 2026 /PRNewswire/ -- The next frontier of AI infrastructure is moving beyond raw compute performance toward high-speed interconnects and seamless coordination across computing nodes. Compal Electronics (Compal; TWSE: 2324) will showcase its AI infrastructure solutions integrating NVIDIA's next-generation computing and networking technologies at Supercomputing 2026 (SC26), the annual international conference for high-performance computing, taking place November 17–19. Leveraging its system engineering and integration expertise spanning silicon, server platforms, and AI network fabrics, Compal will highlight key technologies designed to support large-scale distributed AI computing at Booth #5008 at McCormick Place in Chicago.

As AI applications evolve toward agentic AI and distributed computing, effective CPU-GPU coordination, high-bandwidth data movement, and low-latency network connectivity are becoming essential to scaling AI infrastructure. The extreme codesign approach behind the NVIDIA Rubin platform reflects this architectural evolution, bringing computing and networking technologies into closer alignment to support increasingly complex AI workloads.

In response to this technological shift, Compal continues to expand its portfolio of NVIDIA-based server platforms, including the SGX30-2 air-cooled and OG430-2-L1 direct liquid-cooled servers powered by NVIDIA HGX™ B300, as well as the OG231-2-L1 accelerated computing server featuring NVIDIA HGX™ Rubin NVL8. These systems provide flexible deployment options to address varying compute density and cooling requirements. NVIDIA MGX™ modular architecture and NVIDIA RTX PRO™ acceleration technologies further extend these capabilities to enterprise AI and visual computing applications. Beyond GPU acceleration, Compal will also showcase the NVIDIA Vera CPU Compute Tray, demonstrating its system engineering expertise spanning compute modules, server platforms, and rack-scale infrastructure to support high-density AI computing and inter-node collaboration.

For multi-node AI clusters, minimizing data transfer latency, increasing network throughput, and improving resource coordination are critical to overall system performance. NVIDIA BlueField^®-4 DPU offloads selected networking, storage, and infrastructure management tasks to reduce the processing burden on host CPUs. NVIDIA ConnectX^®-9 SuperNIC delivers high-performance, low-latency connectivity to support high-volume data exchange between compute nodes, while NVIDIA Spectrum™-6 Ethernet switches enhance cluster-level networking and data transfer efficiency, providing the high-speed network foundation for large-scale distributed AI computing.

By integrating these networking technologies with NVIDIA's advanced computing platforms, Compal continues to extend its system engineering capabilities beyond individual servers toward AI network fabrics. Its system-level approach brings together CPU and GPU computing resources, network interfaces, inter-node connectivity, rack-level integration, and the power and cooling infrastructure required for high-density deployments. Through its cross-platform engineering and integration expertise, Compal helps customers build scalable AI clusters with efficient data movement and flexible expansion capabilities, supporting distributed AI, scientific computing, and large-scale high-performance computing (HPC) workloads.

To support real-world deployment of these advanced computing and networking technologies, Compal continues to strengthen its global AI server manufacturing and system delivery capabilities. The opening of its Daxi AI Server Manufacturing Center in Taiwan in August 2026 has expanded its server manufacturing and rack integration capabilities. Meanwhile, investments in its Texas manufacturing operations and Vietnam production capacity are enhancing regional manufacturing flexibility and supply chain resilience. Together, these resources enable Compal to support customers across server platform adoption, system integration, and large-scale AI infrastructure deployment.

"High-speed interconnects and integrated system architectures are essential to scaling AI infrastructure efficiently," said Alan Chang, Vice President of the Infrastructure Solutions Business Group (ISBG) at Compal. "By combining NVIDIA's advanced computing and networking technologies with our system engineering expertise and global manufacturing capabilities, we help customers build highly scalable AI infrastructure, accelerate system deployment, and translate technological innovation into tangible business value."

About Compal

Established in 1984, Compal has grown into a leading global manufacturer of computers and smart devices, partnering with top-tier brands worldwide. Compal was recognized by CommonWealth Magazine as one of Taiwan's top 7 manufacturers and has consistently ranked among the Forbes Global 2000 companies. Compal has actively expanded into new growth areas, including cloud servers, automotive electronics, smart medical and healthcare, and advanced communication solutions. Headquartered in Taipei, Taiwan, Compal operates design and production facilities in the United States, Taiwan, China, Vietnam, Mexico, Brazil, and Poland. Learn more at https://www.compal.com

View original content to download multimedia:https://www.prnewswire.com/news-releases/from-silicon-to-fabric-compal-unites-nvidia-compute-and-networking-at-sc26-302931834.html

SOURCE Compal Electronics, Inc.