Intel Xeon 6 used as Host CPUs in NVIDIA DGX Rubin NVL8 Systems
Intel Xeon is used as host CPU, underscoring its role to orchestrate, scale and secure modern AI infrastructure
What’s New: At NVIDIA GTC 2026, Intel announced that Intel Xeon 6 is being used as the processor for NVIDIA DGX Rubin NVL8 systems. This highlights Xeon’s role in providing architectural continuity and scalability for GPU-accelerated AI systems as workloads shift toward massive, real-time inference.
“As AI moves toward real-time, everywhere inference, the host CPU becomes mission-critical,” said Jeff McVeigh, corporate vice president and general manager, Data Center Strategic Programs at Intel. “Intel Xeon 6 delivers performance, efficiency, and compatibility with the x86 ecosystem to scale inference workloads.”
Why It Matters: As AI adoption grows, inference performance increasingly depends not only on GPUs but also on CPU-driven system efficiency. The host CPU plays a central role in memory management, task orchestration, workload distribution, and ensures security, reliability, and operational continuity across AI infrastructure.
Intel Xeon 6 is selected as the host CPU for DGX Rubin NVL8 systems thanks to:
- High memory speeds and balanced performance across workloads
- Lower long-term total cost of ownership (TCO)
- Mature, enterprise-proven x86 software ecosystem
- Advanced PCIe and I/O capabilities for high-bandwidth, low-latency performance
Additional benefits include:
- Efficient performance per watt
- Optimized support across the AI software stack, including NVIDIA Dynamo for heterogeneous inference
- Proven reliability for mission-critical environments
- Strong orchestration of GPU-accelerated systems
This selection reinforces Xeon as a cornerstone of modern AI infrastructure, enabling scalable deployments across data centers, cloud, and edge. With AI inference scaling rapidly, end-to-end confidential computing becomes essential and Intel TDX provides hardware-based isolation and attestation to secure AI workloads.
Intel & NVIDIA Collaboration:
NVIDIA DGX Rubin NVL8 systems integrate Intel Xeon 6, building on the foundation established with Intel Xeon 6776P in current NVIDIA Blackwell-based platforms, including NVIDIA DGX B300 systems..
Intel Xeon 6 is engineered to maximize GPU performance, leveraging features like Priority Core Turbo and strong single-thread performance to efficiently handle orchestration, scheduling, and data movement in complex inference workloads.
Key Features of Intel Xeon 6:
- Up to 8 TB system memory for large models and KV caches
- Up to 3× higher memory bandwidth (gen-on-gen) with MRDIMM technology
- Industry-leading PCIe 5.0 lanes for AI accelerators
- Confidential computing across CPU–GPU data paths with Encrypted Bounce Buffer
- Hardware-based isolation to protect AI data and models in use