Data Center
NVIDIA Supercharges Ethernet Networking for Generative AI
for Generative AI
Experience end-to-end high-speed Ethernet and InfiniBand connectivity
Contact us
NVIDIA Supercharges Ethernet Networking for Generative AI
Spectrum-X Adopted by Cloud Service Providers, GPU Cloud Providers and Enterprises; Broad
System-Maker Support Extends NVIDIA Networking’s Reach to Every Market
NVIDIA Spectrum Ethernet Switches
10/25/40/50/100/200 and 400G Ethernet Network Adapters
The industry-leading NVIDIA ConnectX family of network interface cards (NICs)
offers advanced hardware offloads and accelerations. NVIDIA Ethernet adapters
enable the highest ROI and lowest Total Cost of Ownership for hyperscale, public
and private clouds, storage, machine learning, AI, big data, and telco platforms.
Accelerated Ethernet Switching for AI and the Cloud
NVIDIA offers cloud-scale efficient switches for data centers of all sizes, with an operational model built for automation, best-in-class performance, and hardware-accelerated network visibility.
InfiniBand for AI and Scientific Computing
The seventh generation of the NVIDIA InfiniBand architecture gives AI developers and scientific researchers the fastest networking performance available to take on the world’s most challenging problems.
NVIDIA Quantum-X800 InfiniBand for Highest-Performance
AI-Dedicated Infrastructure
Spectrum-X Adopted by Cloud Service Providers, GPU Cloud Providers and Enterprises; Broad System-Maker Support Extends NVIDIA Networking’s Reach to Every Market
Spectrum Switch Systems
The NVIDIA Spectrum Ethernet switch family includes a comprehensive switch and software portfolio spanning 1GbE to 800GbE. NVIDIA Spectrum switches are ideal for both building AI fabrics connecting NVIDIA GPUs and connecting end-to-end cloud data center networks. Combining Spectrum switches with the NVIDIA Cumulus Linux, NVIDIA Pure SONiC as well as the NVIDIA NetQ validation toolset and NVIDIA Air simulation platform, delivers the performance and features that every data center needs.
BlueField DPUs
The NVIDIA BlueField DPU ignites unprecedented innovation for modern data centers, delivering a broad range of advanced networking, storage, and security services for complex compute and AI workloads, virtual machines (VMs), containers, and bare-metal servers in enterprise and cloud. By combining the industry-leading NVIDIA ConnectX network adapter with an array of Arm cores, BlueField offers purpose-built hardware acceleration engines with full programmability through NVIDIA DOCA.
InfiniBand Switches
InfiniBand switch systems deliver the highest performance and port density available. Innovative capabilities such as NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP) and advanced management features such as self-healing network capabilities, quality of service, enhanced virtual lane mapping, and NVIDIA In-Network Computing acceleration engines provide a performance boost for industrial, AI, and scientific applications.
InfiniBand Adapters
NVIDIA ConnectX InfiniBand host channel adapters (HCAs) provide ultra-low latency, extreme throughput, and innovative NVIDIA In-Network Computing engines to deliver the acceleration, scalability, and feature-rich technology needed for today's modern workloads.
Data Processing Units (DPUs)
The NVIDIA BlueField® DPUs combine powerful computing, high-speed networking, and extensive programmability to deliver software-defined, hardware-accelerated solutions for the most demanding workloads. From accelerated AI and scientific computing to cloud-native supercomputing, BlueField redefines what’s possible.
InfiniBand Switches
InfiniBand switch systems deliver the highest performance and port density available. Innovative capabilities such as NVIDIA Scalable Hierarchical Aggregation and Reduction Protocol (SHARP) and advanced management features such as self-healing network capabilities, quality of service, enhanced virtual lane mapping, and NVIDIA In-Network Computing acceleration engines provide a performance boost for industrial, AI, and scientific applications.
NVIDIA Supercharges Ethernet Networking for Generative AI
NVIDIA Supercharges Ethernet Networking for Generative AI
Ethernet Switches
NVIDIA offers a complete range of Ethernet solutions—with 10, 25, 40, 50, 100, 200,400, and 800 gigabits per second (Gb/s) options—for your data center, giving you flexibility of choice and a competitive advantage. These end-to-end solutions deliver industry-leading performance, scalability, reliability, and value across a wide range of applications such as cloud, enterprise, financial, storage, big data, machine learning, telecommunications, and more.
The NVIDIA Spectrum Ethernet Switch product family includes a broad portfolio of Top-of-Rack and aggregation switches. Mellanox Spectrum Ethernet switches come in flexible form-factors with 16 to 128 physical ports supporting 1GbE through 400GbE. Based on ground-breaking silicon technology that is optimized for performance and scale, Spectrum switches are ideal to build high performance, cost-effective and efficient Cloud Data Center Networks, Ethernet Storage Fabric, and Deep Learning Interconnects.
NVIDIA Spectrum-4 SN5000 Series
Purpose-built for AI, the SN5000 family is the world’s only Ethernet switch portfolio suitable for deep learning workloads, connecting cloud-scale GPU compute at speeds up to 800 gigabits per second (Gb/s).
NVIDIA Spectrum-3 SN4000 Series
Built for cloud-scale networking, the SN4000 family combines industry-leading features with groundbreaking performance to support modern scale-out distributed data center applications for all speeds up to 400Gb/s.
NVIDIA Spectrum-2 SN3000 Series
Ideal for leaf and spine data center network solutions, the SN3000 series delivers maximum flexibility with port speeds up to 200Gb/s per port and port density that enables full-rack connectivity to any server at any speed.
NVIDIA Spectrum SN2000 Series
With speeds up to 100Gb/s, the SN2000 series provides unique switch form factors that integrate into hyperconverged Infrastructure and software-defined storage management systems for ease of deployment and administration.