While its acquisition of Arm is still awaiting approval, NVIDIA has forged ahead by launching Grace, its first Arm-based data centre CPU that is said to deliver 10x the performance of today’s fastest servers on the most complex AI and high performance computing workloads.
The chip is named in honour of Grace Hopper, an American computer scientist who pioneered computer programming and invented one of the first linkers.
It took ore than 10,000 engineering years of work to develop the NVIDIA Grace CPU. Designed to address the needs of advanced applications such as natural language processing, recommender systems and AI supercomputing, the new CPU can analyse enormous datasets requiring both ultra-fast compute performance and massive memory. Plus, it combines energy-efficient Arm CPU cores with a low-power memory subsystem to deliver high performance with great efficiency.
“Leading-edge AI and data science are pushing today’s computer architecture beyond its limits – processing unthinkable amounts of data. Using licensed Arm IP, NVIDIA has designed Grace as a CPU specifically for giant-scale AI and HPC. 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,” said Jensen Huang, founder and CEO of NVIDIA, who announced the new chip at his keynote to kick off GPU Technology Conference (GTC21).
According to Simon Segars, CEO of Arm, NVIDIA’s introduction of the Grace data centre CPU illustrates clearly how Arm’s licensing model enables an important invention, one that will further support the incredible work of AI researchers and scientists everywhere.
Grace is positioned as a highly specialised processor targeting workloads that have more than one trillion parameters. When tightly coupled with NVIDIA GPUs, a Grace CPU-based system will deliver 10x faster performance than today’s state-of-the-art NVIDIA DGX-based systems, which run on x86 CPUs.
First off the block
The Swiss National Supercomputing Centre (CSCS) and the US 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 Grace is expected to be available from the beginning of 2023.