In this white paper, we’ll look at how adaptive routing from NVIDIA plays such an important role, eliminating congestion and increasing data center performance. InfiniBand adaptive routing technology ...

It was a fortuitous coincidence that Nvidia was already working on massively parallel GPU compute engines for doing calculations in HPC simulations and models when the machine learning tipping point ...

Try as it may, Ethernet cannot kill InfiniBand. For the foreseeable future, the very high-end of the server, storage, and database cluster spaces will need a network interconnect that can deliver the ...

Dan Hanson is director of AI fabric product management at Supermicro Computer Inc. A comparison of InfiniBand and Ethernet in AI cluster networks, exploring their strengths, trade-offs, and how each ...

Artificial intelligence (AI) workloads and the backend network infrastructure needed to support those applications will expand data center switch spending by 50%, according to research from Dell’Oro ...

The high-performance networking market has long been dominated by two primary architectures: Ethernet, originally designed for general-purpose networking more than 50 years ago, and InfiniBand, ...

The InfiniBand spec is designed to support three full-duplex, bidirectional link speeds of 1´ (2.5-Gbps, four-pin interface), 4´ (10-Gbps, 16-pin interface), or 12´ (30-Gbps, 48-pin interface) across ...

Large-scale AI workloads, with their high-bandwidth and low-latency requirements, are reshaping data center network architecture, Nvidia says. Nvidia’s networking ...

Arista Networks excels in cloud networking with high-performance Ethernet solutions, positioning itself advantageously in the AI and data center markets. Competing with Nvidia's InfiniBand, Arista's ...

In this white paper, “NVIDIA InfiniBand Adaptive Routing Technology,”we’ll look at how adaptive routing from NVIDIA plays such an important role, eliminating congestion and increasing data center ...