NVIDIA unveiled its first Arm Neoverse-based discrete data center CPU designed for AI infrastructure and high performance computing, called the Grace CPU Superchip. It consists of two CPU chips connected, coherently, over NVLink-C2C, a new high-speed, low-latency, chip-to-chip interconnect, and complements the company’s first CPU-GPU integrated module, the Grace Hopper Superchip, revealed last year.
The Grace CPU Superchip comes equipped with 144 Arm cores in a single socket, while providing industry-leading energy efficiency and memory bandwidth with its innovative memory subsystem consisting of LPDDR5x memory with Error Correction Code. It will run all of NVIDIA’s computing software stacks, including NVIDIA RTX, NVIDIA HPC, NVIDIA AI and Omniverse, as it offers the flexibility to be configured into servers as standalone CPU-only systems or as GPU-accelerated servers with one, two, four or eight Hopper-based GPUs.
- Powerhouse performance from AMD Ryzen 5 5500U mobile processor, 8GB DDR4 RAM, 256GB SSD storage, and AMD Radeon 7 Graphics
- The IdeaPad 3 14-inch laptop has 4-side narrow bezels that let you see more of the FHD (1920 x 1080) screen for wider viewing angles and less clutter
- Quieter and cooler with intelligent thermals, plus you can calibrate performance with Q-control, with 3 modes to match your performance needs
A new type of data center has emerged — AI factories that process and refine mountains of data to produce intelligence. The Grace CPU Superchip offers the highest performance, memory bandwidth and NVIDIA software platforms in one chip and will shine as the CPU of the world’s AI infrastructure,” said Jensen Huang, founder and CEO of NVIDIA.