Nvidia and the Acceleration of AI to Exaflops and 144 Terabyte LLM

Generative AI lets us learn the structure of any kinds of information. Nvidia CEO Jensen Huang’s gives the keynote address at #COMPUTEX2023. He unveils platforms companies can use to ride a historic wave of generative #AI that’s transforming industries — from advertising to manufacturing to telecom.

The Nvidia Grace Hopper superchip can see 600 Gigabytes of data at a time. 256 of the Grace Hopper chips is a one exaflop supercomputer with 144 Terabytes of universally available memory.

NVIDIA announced NVIDIA Spectrum-X™, an accelerated networking platform designed to improve the performance and efficiency of Ethernet-based AI clouds. This is a new network built for AI that will enable all data centers to run generative AI efficiently.

NVIDIA Spectrum-X is built on networking innovations powered by the tight coupling of the NVIDIA Spectrum-4 Ethernet switch with the NVIDIA BlueField®-3 DPU, achieving 1.7x better overall AI performance and power efficiency, along with consistent, predictable performance in multi-tenant environments. Spectrum-X is supercharged by NVIDIA acceleration software and software development kits (SDKs), allowing developers to build software-defined, cloud-native AI applications.

NVIDIA is now supporting 4000 GPU enterprise software. This will be make it enterprise grade for security and support. This will enable enterprise software companies to access the 20X speed improvement and 5% cost for more of their applications.

NVIDIA Omniverse™ is a computing platform that enables individuals and teams to develop Universal Scene Description-based 3D workflows and applications. This enables ray-traced realistic simulations of factories or other simulations with multiple global users at the same time.