Jensen Huang Founder, President and CEO at NVIDIA | Official website
NVIDIA announced the widespread adoption of its NVIDIA Spectrum™-X Ethernet networking platform and an accelerated product release schedule at COMPUTEX. CoreWeave, GMO Internet Group, Lambda, Scaleway, STPX Global, and Yotta are among the first AI cloud service providers to adopt NVIDIA Spectrum-X to enhance their AI infrastructures. Additionally, several partners such as ASRock Rack, ASUS, GIGABYTE, Ingrasys, Inventec, Pegatron, QCT, Wistron and Wiwynn have announced Spectrum-based products. These companies join Dell Technologies, Hewlett Packard Enterprise, Lenovo and Supermicro in incorporating the platform into their offerings.
“Rapid advancements in groundbreaking technologies like generative AI underscore the necessity for every business to prioritize networking innovation to gain a competitive edge,” said Gilad Shainer, senior vice president of networking at NVIDIA. “NVIDIA Spectrum-X revolutionizes Ethernet networking to let businesses fully harness the power of their AI infrastructures to transform their operations and their industries.”
Spectrum-X is described as the world’s first Ethernet fabric built for AI. It accelerates generative AI network performance by 1.6 times over traditional Ethernet fabrics. To meet industry demand for this performance level, NVIDIA founder and CEO Jensen Huang announced during his COMPUTEX keynote in Taiwan that new Spectrum-X products will be launched annually. These products will feature increased bandwidth and ports along with enhanced software features and programmability.
The platform includes the NVIDIA Spectrum SN5600 Ethernet switch and the NVIDIA BlueField®-3 SuperNIC. Built with adaptive routing and congestion control for maximum bandwidth and noise isolation, it offers high-performance Ethernet networking for AI applications. This setup provides predictable outcomes for thousands of simultaneous AI jobs at various scales.
Combined with NVIDIA BlueField-3 DPUs (Data Processing Units), the platform supports advanced cloud multi-tenancy, GPU compute elasticity and zero-trust security measures. This enables cloud service providers to accelerate AI solution development while improving return on investment.
Further details about NVIDIA Spectrum-X were discussed during Huang’s keynote address at COMPUTEX.