After interconnecting powerful AI GPUs, NVIDIA has now presented a solution that connects multiple datacenters to bring massive compute power onboard.
NVIDIA’s Spectrum-XGS Ethernet Technology Is a Powerful Interconnect, Designed For AI Clusters
Scaling up AI computing power through architectural advancements isn’t the right move because there will be a point when limitations will come into play. That’s why NVIDIA has introduced a new interconnect platform that allows firms to combine ‘distributed data centers into unified, giga-scale AI super-factories’. According to NVIDIA, the Spectrum-XGS eliminates the limitations present in scaling up a single datacenter, especially when it comes to geographical concerns, and the cost to cool such large systems in a single facility. Instead, interconnect multiple AI clusters to achieve significantly higher AI performance.
With NVIDIA Spectrum-XGS Ethernet, we add scale-across to scale-up and scale-out capabilities to link data centers across cities, nations and continents into vast, giga-scale AI super-factories.
– NVIDIA’s CEO Jensen Huang
Spectrum-XGS is claimed to be a derivative of the company’s original Spectrum technology and a foundational pillar for AI computation. According to the company’s blog post, Spectrum-XGS doubles performance relative to NCCL, a similar implementation for interconnecting multiple GPU nodes. More importantly, the technology comes with features like auto-adjusted distance congestion control and latency management, to ensure the longer distances between interconnected data centers don’t result in performance loss.
Interestingly, Coreweave will become the first company to integrate its hyperscalers with Spectrum-XGS Ethernet, and this move is claimed to “accelerate breakthroughs across every industry, ” meaning that we’ll see compute levels that were deemed impossible before. NVIDIA isn’t stopping with the AI hype yet, and after the debut of technologies like silicon photonics network switches, we will definitely see interconnect mechanisms going to new levels.