NVIDIA Harnesses Vera CPU to Speed Up Design of Next-Generation CPUs and GPUs
NVIDIA Blog · Ivan Goldwasser · 2026-07-27
NVIDIA announces it is deploying its custom Vera CPU — featuring 88 Olympus cores with LPDDR5X memory — across its own electronic design automation workflows, achieving up to 1.5x performance improvements on Cadence Jasper and Synopsys VCS workloads to accelerate the design of its next-generation chips.
Appears in
Extraction
Topics: chip-designedacpu-architecturenvidiahardware-acceleration
Claims
- NVIDIA's Vera CPU delivers up to 1.5x performance improvement on selected EDA workloads, specifically Cadence Jasper formal verification and Synopsys VCS functional simulation, compared to prior systems.
- NVIDIA is deploying Vera in its own internal chip design workflows, creating a feedback loop where NVIDIA CPUs are used to design future NVIDIA CPUs and GPUs.
- Critical EDA stages including logic simulation, formal verification, and digital implementation remain heavily CPU-bound and cannot be fully offloaded to GPUs or AI accelerators.
- NVIDIA plans to follow Vera with a next-generation Rosa CPU built on the NVIDIA Rigel core.
Key quotes
By using NVIDIA CPUs to help design future NVIDIA CPUs and GPUs, the company is creating a continuous feedback loop between silicon design, software optimization and systems engineering, with each generation helping build the next.
Both applications showed up to 1.5x higher performance on selected workloads.
Models have broken out of sandboxes before, and we always try to patch them. But the problem is … it's impossible to patch every single thing that a creative AI can do.