Chip maker Nvidia has unveiled a new AI chip built for accelerated computing and to handle the world’s most complex generative AI workloads, spanning large language models, recommender systems, and vector databases.
The next-generation GH200 Grace Hopper platform is based on a new Grace Hopper Superchip with the world’s first HBM3e processor, which will be available in a wide range of configurations, the company said.
“The new GH200 Grace Hopper Superchip platform delivers this with exceptional memory technology and bandwidth to improve throughput, the ability to connect GPUs to aggregate performance without compromise, and a server design that can be easily deployed across the entire data center,” Jensen Huang, founder, and CEO of Nvidia, said in a statement.
The new platform uses the Grace Hopper Superchip, which can be connected with additional Superchips by Nvidia NVLink, allowing them to work together to deploy the giant models used for generative AI.
This high-speed, coherent technology gives the GPU full access to the CPU memory, providing a combined 1.2TB of fast memory when in a dual configuration, according to the company. “HBM3e memory, which is 50 percent faster than current HBM3, delivers a total of 10TB/sec of combined bandwidth, allowing the new platform to run models 3.5x larger than the previous version while improving performance with 3x faster memory bandwidth,” Nvidia said.
Leading system manufacturers are expected to deliver systems based on the platform in Q2 of the calendar year 2024.
