CN5000 Omni-Path® SuperNICs
As AI and HPC workloads continue to evolve in complexity where the demand for high-performance, scalable networking solutions has never been more critical. The Cornelis CN5000 Omni-Path adapters are purpose-built to deliver industry-leading performance and scalability, accelerating time-to-results and maximizing investment in extreme-scale environments. With up to 400Gbps bidirectional bandwidth the CN5000 achieves the highest message rates and lowest latency for AI-driven workloads including training and inference. Built for highly parallelized compute, CN5000 remains the best choice for all HPC applications for its robustness, efficiency and performance.
CN5000 Omni-Path® Switch
The CN5000 Switch is engineered to scale seamlessly across thousands of nodes, leveraging advanced network routing, intelligent traffic flow management, and zero-latency packet integrity protection. Delivering up to 400Gbps of bidirectional bandwidth, the CN5000 Switch is designed to support the most demanding HPC, AI training and inference tasks. Equipped with cutting-edge telemetry capabilities, the CN5000 Switch provides consistent, reliable network performance.
CN5000 Omni-Path® Director Class Switch
As AI and HPC environments scale to thousands, or even hundreds of thousands of nodes, network infrastructure must evolve to meet the demands of modern workloads. The Cornelis CN5000 Omni-Path® DCS, with up to 576 ports of 400Gbps bi-directional bandwidth, delivers the scale and density required to eliminate architectural bottlenecks and unlock full system potential—accelerating AI model training, simulation throughput, and time-to-insight across AI and HPC workloads.
Cornelis OPX Software Suite
Cornelis OPX Software Suite provides a complete enterprise class network stack, including OpenFabrics-based host drivers, fabric management, element management, and cluster administration and diagnostics, all working seamlessly together to deliver cluster administrators and end users deterministic installation and configuration times, advanced routing algorithms and resiliency capabilities, powerful monitoring and diagnostics, and the industry’s best application performance at scale, all with an eye to ease of use.
Cornelis Blog Posts
The Token Economy: Maximizing AI Efficiency at the Edge with Cornelis Networks
As AI moves from massive data centers to local "Edge" deployments, the industry is adopting a new vocabulary. We sat down with Matt Williams from Cornelis Networks to demystify the [...]
Cornelis – Network Performance for AI Inference and Edge Computing
As AI models move closer to the data source, balancing the need for specialized performance across the network is increasingly important to the overall performance of the compute hardware. The [...]
The Rise of Cornelis Networks – Unlocking AI/HPC Performance with Omni-Path and Ultra-Ethernet
In the high-stakes world of High-Performance Computing (HPC) and AI, the network is often the unsung bottleneck. While CPUs and GPUs grab the headlines, the "plumbing" that connects them determines [...]