Listen to this story
NVIDIA has just shared some big news about making AI work faster for big companies. Dell Technologies, Hewlett Packard Enterprise, and Lenovo will be the first to use NVIDIA’s new Ethernet Networking Platform in their servers. This will help businesses speed up their AI tasks.
NVIDIA’s networking technology for AI, called Spectrum-X, is made just for AI. It makes the computer communication for AI tasks 1.6 times faster than the usual way. These new systems will use Spectrum-X along with NVIDIA’s other technologies like Tensor Core GPUs, AI Enterprise software, and AI Workbench software.
Subscribe to our Newsletter
Join our editors every weekday evening as they steer you through the most significant news of the day, introduce you to fresh perspectives, and provide unexpected moments of joy
“Generative AI and accelerated computing are driving a generational transition as enterprises upgrade their data centers to serve these workloads,” stated Jensen Huang, founder and CEO of NVIDIA in the official statement shared with AIM. “Accelerated networking is the catalyst for a new wave of systems from NVIDIA’s leading server manufacturer partners to speed the shift to the era of generative AI.”
Spectrum-X works by combining different technologies, like the Spectrum-4 Ethernet switch and the NVIDIA BlueField-3 SuperNIC. The latter is a special piece that helps connect different parts of the computer. It makes sure they communicate better with each other in the best way, making AI tasks run smoother. It’s also designed to be energy-efficient, fitting well into regular business servers.
All of this is powered by software from NVIDIA, like Cumulus Linux, Pure SONiC, NetQ, and NVIDIA DOCA™ software framework. In simple terms, NVIDIA is giving these companies a powerful toolbox for pushing forth their use of AI.