In a surprising development, NVIDIA Founder and CEO Jensen Huang announced the next-generation NVIDIA GH200 Grace Hopper platform at his keynote address at SIGGRAPH.
Based on a new Grace Hopper Superchip with the world’s first HBM3e processor, the platform is built for the era of accelerated computing and generative AI. The superchip comprises a GPU and a CPU.
With AI being all the rage, GH200 Grace Hopper can tackle complex generative AI workloads, spanning large language models, recommender systems and vector databases.
The move takes NVIDIA even further ahead of its competitors in providing the grunt needed for AI workloads.
“To meet surging demand for generative AI, data centres require accelerated computing platforms with specialised needs. 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 centre,” said Huang.
System manufacturers are expected to deliver systems based on the platform in Q2 of 2024.
Entelechy Asia 