System-level 'coopetition': Why Nvidia's DGX Rubin NVL8 runs on Intel Xeon 6

"As AI shifts toward real-time inference and agentic workloads, the CPU's role becomes even more critical as managing complex workflows and feeding data efficiently to GPUs can become a bottleneck. Nvidia is optimizing for the best host CPU ecosystem-performance, compatibility, supply, and enterprise readiness-and x86 continues to dominate data center infrastructure."

"Xeon 6, with its high memory bandwidth (MRDIMM) and strong x86 compatibility, helps ensure GPUs remain fully utilized without data delays. Enterprise environments still rely heavily on x86 ecosystems for operational tooling, security frameworks, and lifecycle management."

Nvidia has selected Intel's Xeon 6776P processors as the host CPUs for its DGX Rubin NVL8 flagship AI systems, designed to accelerate agentic AI adoption. These systems combine eight Rubin GPUs with high-bandwidth memory and NVLink technology for fast GPU communication and parallel processing. The choice reflects enterprise compatibility needs and deployment requirements. As AI workloads shift toward real-time inference, the CPU's role becomes critical for managing complex workflows and efficiently feeding data to GPUs. Intel Xeon 6 provides high memory bandwidth and strong x86 compatibility, ensuring GPUs remain fully utilized without data bottlenecks. Enterprise environments rely heavily on x86 ecosystems for operational tooling, security frameworks, and lifecycle management, making x86 continuity essential for integrating these systems into existing infrastructure.

Read at Computerworld