Success Story

To prepare AI-ready data centers for the demands of next-generation workloads, Dell Technologies and Siemon needed to prove that high-speed network fabrics could deliver deterministic, lossless performance before deployment. With Keysight, they validated SONiC-based switching and Siemon high-speed connectivity under realistic AI traffic conditions, demonstrating how end-to-end emulation and validation can reduce risk and help AI infrastructure scale toward 1.6T and beyond.

Dell - Siemon Case Study - Building AI Network Fabrics with Keysight

Proving AI Data Center Fabrics at Scale

Case Study Highlights: Dell Technologies - Siemon

Leaders in AI Infrastructure

Dell Technologies, Siemon, and Keysight represent three essential layers of AI data center infrastructure: switching architecture, physical connectivity, and performance validation. Dell delivers high-density switching platforms and SONiC-based network operating systems optimized for AI fabrics. Siemon provides high-speed copper, optical interconnects, and structured cabling systems. Keysight enables system-level validation through advanced traffic emulation and benchmarking.

Scaling AI Networks

As AI networks scale, Dell and Siemon need to help customers deploy higher-speed fabrics with confidence. Next-generation AI workloads create massive East-West traffic, tightly synchronized GPU communication, latency-sensitive collective operations such as All-Reduce, and stateful RoCEv2 behavior. These demands increase the risk of congestion hot spots, lower GPU utilization, and unpredictable performance across switching, optics, and cabling. The challenge for Dell and Siemon is proving that the fabric can deliver deterministic, lossless performance under realistic AI workload conditions before customers deploy it at scale.

End-to-End Fabric Validation

Using Keysight AI Data Center Builder, Dell, Siemon, and Keysight built and validated an end-to-end AI fabric that integrated switching, connectivity, and workload emulation. Dell PowerSwitches with Enterprise SONiC enabled AI-aware features such as adaptive routing, enhanced hashing, and congestion management, while Siemon delivered the high-performance copper and optical infrastructure required for lossless transport. Powered by the AresONE Network Traffic Generator, Keysight emulated multi-GPU environments and collective operations over stateful RoCEv2, enabling full-system benchmarking, congestion analysis, and precise tuning before deployment.

AI-Ready Performance

The validated AI-ready network fabric delivered stable, deterministic performance under realistic AI workloads. Using stateful RoCEv2 traffic, the fabric was able to maintain performance, even under congestion. Completion times stayed within microseconds across the rail topology. Together, this demonstration confirmed that integrated switching, connectivity, and benchmarking can reduce deployment risk, improve GPU utilization, and prepare next-generation AI fabrics to scale to 1.6T and beyond.
James Wynia, Dell Technologies

"AI fabrics must move massive East-West traffic, keep GPUs fully utilized, and handle synchronized workloads without congestion or delay."

James Wynia, Senior Product Manager, Dell Technologies

AresONE-M 800GE

Validate equipment interoperability and performance.

Keysight AI Data Center Builder

Design and deploy AI network infrastructure​ and emulate AI workloads.

Explore Related Resources

White Paper

White Paper

7 Lessons for Designing and Validating AI Networks at Scale

Explore key considerations for designing, connecting, and validating AI network fabrics, from traffic behavior and topology choices to cabling, optics, load balancing, and full-system emulation at 800G, 1.6T, and beyond.

White Paper

White Paper

Scaling AI Data Centers for Real-World Performance

Technical insight on emulation, validation, and cluster behavior at AI infrastructure scale.

Report

Report

AI Cluster Networking Bottlenecks, Scale, and What Comes Next

Survey-based insights on infrastructure investment, emulation gaps, interconnect adoption, and optimization priorities in AI data centers.

×

Please have a salesperson contact me.

*Indicates required field

Select a preferred method of communication*Required Field
Preferred method of communication? Change email?
Preferred method of communication?

By continuing, you are providing Keysight with your personal data. See the Keysight Privacy Statement for information on how we use this data.

Thank you

A sales representative will contact you soon.