Xeon 6 will serve as the main CPU for NVIDIA's DGX Rubin, and Intel's stock price rises by 3.3%

At NVIDIA GTC 2026, Intel announced that its Intel Xeon 6 processor has been selected as the main processor for NVIDIA DGX Rubin NVL8 systems. The company stated that this development highlights the critical role of Xeon in GPU-accelerated AI systems, especially as the industry shifts from large-scale training to real-time inference, with CPUs increasingly important in system architecture.

This news caused Intel’s stock price to rise by up to 3.3% on Monday.

Jeff McVeigh, Vice President and General Manager of Intel Data Center Strategic Projects, said, “Artificial intelligence is shifting from large-scale training to ‘ubiquitous real-time inference,’ driven by proxy AI and inference systems.”

In this new phase, host CPUs have become key components responsible for system scheduling, memory access, model security, and overall throughput management. He pointed out that Xeon 6 offers leading advantages in performance, energy efficiency, and compatibility with the x86 software ecosystem, enabling customers to scale inference workloads.

Lynx Equity Strategies responded positively to this news, stating that with this development,

“Intel and NVIDIA’s collaboration now has a tangible form; future evaluations can be made based on product release timelines and potential revenue opportunities.”

Intel: Xeon 6 Excels in Multiple Key Metrics

The company said that Intel Xeon was chosen as the main CPU for the DGX Rubin NVL8 system mainly due to its multiple system-level advantages, including support for high-speed memory, balanced performance across various workloads, lower total cost of ownership over the long term, and a mature, reliable enterprise software ecosystem. Additionally, Xeon’s capabilities in PCIe and I/O have been further strengthened, allowing stable operation in high-bandwidth, low-latency scenarios.

Intel stated that Xeon 6 is competitive across several key metrics, including higher performance per watt, comprehensive optimization for AI software stacks (including support for NVIDIA Dynamo to enable heterogeneous inference between CPU and future GPUs), high reliability in mission-critical environments, and efficient scheduling for GPU-accelerated heterogeneous systems.

In terms of collaboration, the DGX Rubin NVL8 system will integrate the Xeon 6 processor. This architecture continues the design of the previous Blackwell platform based on Intel Xeon 6776P (such as the DGX B300 system). Intel noted that this continuity helps smoothly transfer existing performance advantages and system experience to the new generation of AI systems.

On a technical level, Xeon 6 optimizes data transfer to GPUs through features like Priority Core Turbo, and with its strong single-thread performance, it handles critical tasks such as scheduling, task management, and data flow, maintaining system stability and efficiency even as inference tasks become more complex.

Regarding hardware specifications, Xeon 6 includes several AI-optimized features, such as support for up to 8TB of system memory to meet large model and KV cache needs; a threefold increase in memory bandwidth via MRDIMM technology, significantly improving data supply to GPUs; industry-leading PCIe 5.0 channels to support AI accelerators; and encrypted buffers to secure data paths between CPU and GPU. Its hardware-based isolation mechanisms also protect AI data and models during operation.

Risk Warning and Disclaimer

Market risks are present; investments should be made cautiously. This article does not constitute personal investment advice and does not consider individual users’ specific investment goals, financial situations, or needs. Users should consider whether any opinions, viewpoints, or conclusions herein are suitable for their particular circumstances. Investment is at your own risk.