NVIDIA Grace Hopper
NVIDIA Grace Hopper
NVIDIA Grace Hopper is a new class of superchips built from the ground up to accelerate hybrid CPU and GPU workloads. It brings together the groundbreaking performance of the NVIDIA Hopper™ GPU with the versatility of the NVIDIA Grace™ CPU in a single superchip, connected with the high-bandwidth, memory-coherent NVIDIA® NVLink® Chip-2-Chip (C2C) interconnect.
- Transformer Engine designed specifically to accelerate AI inference and training
- Unified cache coherence with a single memory address space that combines CPU and GPU memory for simplified programmability
- Leading per-thread CPU performance with higher energy efficiency than traditional CPUs.
- Optimal balance of bandwidth, energy efficiency, capacity, and cost for large-scale AI and HPC workloads.
More information can be found at https://www.nvidia.com/en-us/data-center/grace-hopper-superchip/
Certifications
Red Hat certified hardware is proven to incorporate Red Hat's best practices and provides customers tested interoperability, known life cycle management, and trusted support.
| Compare | Product | Level | |
|---|---|---|---|
Red Hat Enterprise Linux 10.0 - 10.x Architecture: aarch64 | Certified | ||
Red Hat Enterprise Linux Architecture: aarch64 | Certified |
