NVIDIA Grace CPU is the first data center CPU developed by NVIDIA. By combining NVIDIA expertise with Arm processors, on-chip fabrics, System-on-Chip (SoC) design, and resilient high-bandwidth low-power memory technologies, the NVIDIA Grace CPU was built from the ground up to create the world’s first superchips for computing. By Jonathon Evans, Ian Finder, Ivan Goldwasser, John Linford, Vishal Mehta, Daniel Ruiz and Mathias Wagner.
The NVIDIA Grace Hopper Superchip pairs a power efficient, high-bandwidth NVIDIA Grace CPU with a powerful NVIDIA H100 Hopper GPU using NVLink-C2C to maximize the capabilities for strong-scaling high performance computing (HPC) and giant AI workloads. More information is available in the NVIDIA Grace Hopper Superchip Whitepaper.
Further in the article:
- A superchip built for HPC and AI workloads
- Alleviate bottlenecks with NVLink-C2C Interconnect
- NVIDIA Grace CPU core architecture
- NVIDIA Grace CPU software
The NVIDIA Grace Superchip Architecture Whitepaper expands on the details covered in this post. It provides an in-depth explanation of how the NVIDIA Grace CPU delivers the superior performance shown in Figure 1, as well as the technology innovations behind the performance.
[Read More]