NVIDIA bares CPU for giant AI, HPC jobs

Los Alamos National Laboratory
- Advertisement -

 NVIDIA has unveiled its first data centre CPU, an Arm-based processor that will deliver 10 times the performance of today’s fastest servers on the most complex artificial intelligence and high performance computing workloads. 

The NVIDIA Grace CPU is designed to address the computing needs for the world’s most advanced applications — including natural language processing, recommender systems and AI supercomputing — that analyse huge datasets which need both ultra-fast compute performance and massive memory. 

Grace — named for Grace Hopper, the American computer-programming pioneer — combines energy-efficient Arm CPU cores with a low-power memory subsystem to deliver high performance with great efficiency. 

- Advertisement -

“Leading-edge AI and data science are pushing today’s computer architecture beyond its limits, processing unthinkable amounts of data,” said Jensen Huang, founder and CEO of NVIDIA. 

“Using licensed Arm IP, NVIDIA has designed Grace as a CPU specifically for giant-scale AI and HPC,” said Huang. “Coupled with the GPU and DPU, Grace gives us the third foundational technology for computing, and the ability to re-architect the data centre to advance AI. NVIDIA is now a three-chip company.” 

Grace is a highly specialised processor for workloads such as training next-generation NLP models that have more than 1 trillion parameters. When tightly coupled with NVIDIA GPUs, a Grace CPU-based system will deliver 10 times faster performance than the NVIDIA DGX-based systems, which run on x86 CPUs. 

While the vast majority of data centres are expected to be served by existing CPUs, Grace will serve a niche segment of computing. 

The Swiss National Supercomputing Centre (CSCS) and the United States Department of Energy’s Los Alamos National Laboratory are the first to announce plans to build Grace-powered supercomputers in support of national scientific research efforts. 

CSCS and Los Alamos National Laboratory both plan to bring Grace-powered supercomputers, built by Hewlett Packard Enterprise, online in 2023.

“NVIDIA’s novel Grace CPU allows us to converge AI technologies and classic supercomputing for solving some of the hardest problems in computational science,” said CSCS director Thomas Schulthess.

Thom Mason, director of the Los Alamos National Laboratory, said that with Grace, they will be able to deliver advanced scientific research using high-fidelity 3D simulations and analytics with datasets that are larger than previously possible.