Original article excerpt
Server-side extracted preview paragraphs from the original source.
NVIDIA technologies power more than 400 of the world’s 500 fastest supercomputers — 81% of the TOP500.
NVIDIA technologies power more than 400 of the world’s 500 fastest supercomputers — 81% of the TOP500 — according to the latest rankings released this week at the ISC High Performance conference in Hamburg, Germany.
That’s a gain of 17 systems from the previous list, with the momentum in new deployments: nearly nine of every 10 systems new to the ranking are built on NVIDIA technologies.
That percentage reflects a deliberate preference for machines built for AI, simulation and science together. And it’s compounding: NVIDIA systems across the TOP500 now deliver more than 2x the AI training and nearly 3x the AI inference throughput of every other platform combined.
GPU and networking adoption each hit new highs, with NVIDIA GPUs accelerating a record 238 systems and NVIDIA networking connecting a record 376 — the vast majority on NVIDIA Quantum InfiniBand, the backbone of large-scale AI and high-performance computing, and the rest on Ethernet.
The trend behind the numbers is bigger than any one list: Accelerated computing is becoming the foundation for the systems taking on the world’s most demanding work, across AI and science.
Updated twice a year, the TOP500 ranks the world’s fastest supercomputers, while the Green500 list measures how much computing each delivers per watt.