NVIDIA CEO Jensen Hiang has announced details about the company’s next DGX supercomputer during his Computex keynote. The DGX GH200 is designed to help companies develop generative AI models, which is where the industry is heading. The supercomputer uses a new NVLink Switch System that enables 256 GH200 Grace Hopper superchips to act as a single GPU. Each of the chips has an Arm-based Grace CPU and an H100 Tensor Core GPU. NVIDIA claims that this allows the DGX GH200 to deliver 1 exaflop of performance and to have 144 terabytes of shared memory. The company says that’s nearly 500 times as much memory as you’d find in a single DGX A100 system.
For comparison, the latest ranking of the Top500 supercomputers lists Frontier at Oak Ridge National Laboratory in Tennessee as the only known exascale system, having reached a performance of nearly 1.2 exaflops on the Linmark benchmark. That’s over twice the peak…
2023-05-28 23:30:53
Original from www.engadget.com rnrn