Press release · November 11, 2026 · prnewswire.co.uk
Super Micro Computer ships H15 servers on AMD EPYC 9006 CPUs
Summary
Super Micro Computer, Inc. has begun shipping its H15 generation server portfolio, which the company links to faster deployment of AI infrastructure.
The H15 line forms a core component of the DCBBS architecture, which the company describes as modular AI infrastructure with end-to-end deployment flexibility. According to the company, this design supports fast time-to-market for data center solutions built on the latest AMD processors.
The servers use 6th Gen AMD EPYC 9006 Series processors, formerly codenamed Venice, and are optimized for next-generation GPUs, including AMD Instinct accelerators. The release cites 33% more cores, 2× PCIe bandwidth, and 2.6× higher memory bandwidth, along with 1.8× higher tokens per second for frontier-model host nodes compared to previous AMD CPU generations. The release also reports multiple SPEC CPU world records on the 2U Hyper and CloudDC platforms.
The company reports more than 20 optimized systems, including Hyper, a dual-socket platform; CloudDC, a single-socket system built on the OCP DC-MHS specification; and SuperBlade, a 6U blade platform supporting single-socket and dual-socket configurations. Helios and Helion rack-scale solutions, built on DCBBS and powered by AMD EPYC CPUs and AMD Instinct GPUs, are optimized for large-scale and agentic AI deployments.
“With the H15 portfolio now shipping, Supermicro and AMD are giving customers a faster, more efficient path to an agentic AI infrastructure,” said Michael McNerney, senior vice president, Marketing, Supermicro. “Built on our DCBBS architecture and powered by 6th Gen AMD EPYC 9006 processors, these servers deliver substantially higher core density, memory bandwidth, and PCIe throughput. Our close engineering collaboration with AMD provides customers the flexibility to scale AI, cloud, and enterprise workloads with confidence.”
“These platforms help organizations deploy AI infrastructure faster, improve utilization, reduce energy use, and lower total cost of ownership while running more concurrent agents and demanding enterprise workloads,” said Dan McNamara, senior vice president and general manager, Compute and Enterprise AI, AMD. The companies described plans to bring Helios and Helion to market.
Our summary. The original keeps its own byline.