NVIDIA Vera CPU アーキテクチャの詳細発表

GIGAZINE

To address the increasing complexity of modern chip designs, NVIDIA has revealed that it is leveraging its next-generation custom CPU for data centers, Vera, to develop the next generation of CPUs and GPUs. Key validation and simulation workloads in initial testing have shown performance improvements of up to 1.5 times. NVIDIA Harnesses Vera CPU to Speed Up Design of Next-Generation CPUs and GPUs | NVIDIA Blog https://blogs.nvidia.com/blog/vera-cpu-eda/ According to NVIDIA, the complexity of the designs is becoming increasingly challenging as their engineering teams work on developing more advanced CPUs, GPUs, and AI systems. To address this issue, NVIDIA is collaborating with manufacturers such as Cadence Design Systems and Synopsys in the fields of electronic design automation (EDA) and system design and analysis (SDA), including optimizing EDA applications for Vera. Cadence and NVIDIA expand partnership to drive engineering innovation for the AI era | Cadence https://www.cadence.com/ja_JP/home/company/newsroom/press-releases/pr/2026/cadence-and-nvidia-expand-partnership-to-reinvent-engineering.html According to NVIDIA, while GPUs and AI have streamlined many aspects of chip design, a significant portion of critical EDA workloads still heavily rely on CPU performance. Therefore, CPU architecture is a crucial factor for engineering teams to quickly validate designs, explore alternatives, and move forward to test versions. Tests conducted across multiple major EDA applications revealed that Vera can accelerate the two most computationally intensive steps in modern chip design. NVIDIA unveils details of its

https://gigazine.net/gsc_news/en/20260729-nvidia-vera-cpu-to-speed-up-next-generation