NVIDIA InfiniBand Switches

Unparalleled data throughput and density

Complex workloads demand ultra-fast processing of high-resolution simulations, extreme-size datasets, and highly parallelized algorithms. As these computing requirements continue to grow, NVIDIA InfiniBand—the world’s only fully offloadable, In-Network Computing platform—provides the dramatic leap in performance needed to achieve unmatched data center performance with less cost and complexity.

Download our new NVIDIA InfiniBand Adaptive Routing Technology Whitepaper

Accelerate Research and Innovation with Greater Data Capacity and In-Network Computing

NVIDIA's family of InfiniBand switches delivers a complete switch system and fabric management portfolio for connecting cloud-native supercomputing at any scale. NVIDIA InfiniBand also provides self-healing network capabilities, enhanced quality of service (QoS), congestion control, and adaptive routing to provide the highest overall application throughput.

Fixed-Configuration Switches

NVIDIA's family of fixed-configuration switch systems provides the highest-performing fabric solutions in a 1U form factor with up to 64 ports of 400Gb/s non-blocking bandwidth and extremely low port-to-port latency. These switches are ideal for top-of-rack leaf connectivity or for building data center switch networks at any scale.

Modular Switches

NVIDIA’s InfiniBand family of modular switches provide low latency and the highest density, scaling up to 2,048 ports of 400Gb/s non-blocking bandwidth in a single enclosure. Its smart design, with hot-swappable components provides unprecedented levels of performance and simplifies the building of data centers that can scale out to over a million nodes.

Products

NDR 400Gb/s InfiniBand Switch Family

Based on the NVIDIA Quantum™-2 switch device, NVIDIA NDR 400Gb/s InfiniBand switches deliver massive throughput, In-Network Computing, smart acceleration engines, flexibility, and a robust architecture to achieve unmatched performance in high-performance computing (HPC), AI, and hyperscale cloud infrastructures—with less cost and complexity.

Learn More About NVIDIA Quantum-2 QM9700 Switches ›

LEARN MORE ABOUT NVIDIA QUANTUM-2 CS9500 MODULAR SWITCHES ›

NVIDIA Quantum InfiniBand Switch Family

NVIDIA Quantum InfiniBand switches provide high-bandwidth performance, low power, and scalability, reducing capital and operating expenses and providing the best return on investment. NVIDIA Quantum switches optimize data center connectivity with advanced routing and congestion avoidance capabilities.

Learn More About NVIDIA Quantum QM8700 Fixed-configuration Switches ›

Learn More About NVIDIA Quantum CS8500 Modular Switches ›

EDR 100Gb/s InfiniBand Switch Family

Based on the NVIDIA® Switch-IB® 2 device, the NVIDIA SB7800 switch series delivers 100Gb/s of full bidirectional bandwidth per port. The EDR 100Gb/s InfiniBand switch systems provide cost effective building blocks for deploying high-performance data centers.

Learn More About NVIDIA Switch-IB 2 SB7800 Fixed-configuration Switches ›

Learn More About NVIDIA Switch-IB 2 CS7500 Modular Switches ›

EDR 100Gb/s InfiniBand Router

The NVIDIA SB7880 InfiniBand router enables isolation and connectivity between up to six different InfiniBand subnets. The router is based on Switch-IB 2 and offers fully flexible 36 EDR 100Gb/s ports. The connected InfiniBand subnets can have different network topologies to maximize application performance.

Learn More ›

InfiniBand Switch Software

NVIDIA MLNX-OS® is an InfiniBand switch operating system for data centers with storage, enterprise, high-performance, and machine learning computing and cloud fabrics. Building networks with MLNX-OS enables scaling to thousands of compute and storage nodes with monitoring and provisioning capabilities running InfiniBand.

Learn More ›

In-Network Computing

NVIDIA InfiniBand switches include Scalable Hierarchical Aggregation And Reduction Protocol (SHARP). SHARP offloads and accelerates data reduction algorithms, increasing the performance and scalability of HPC and AI applications.

Learn More ›

Scalable HPC Software

The NVIDIA HPC-X® is a comprehensive MPI and SHMEM/PGAS software suite. HPC-X leverages InfiniBand In-Network Computing and acceleration engines to optimize research and industry applications.

Learn More ›

Unified Fabric Manager (UFM)

The NVIDIA UFM® platform empowers data center administrators to efficiently provision, monitor, manage and proactively troubleshoot their InfiniBand network infrastructure.

Learn More ›