Never miss a story from Corporate and Culture. Subscribe for in-depth analysis and articles.
When it comes to accelerated computing, NVIDIA is an industry pioneer, particularly so in the field of AI technology. The tremendous amount of power that is required to tackle AI algorithms and workloads is inherent in NVIDIA’s graphical processing units (GPUs). However, as chip sizes double every two years, the software complexities continue to build up and pose a huge challenge for engineers.
To address these challenges, NVIDIA employs a number of tools, with system emulation and prototyping technologies playing a pivotal role—namely, Cadence’s Dynamic Duo, Palladium Z2 and Protium X2. The Dynamic Duo provides a comprehensive solution for intellectual property (IP) and system-on-chip (SoC) verification, hardware and software regressions, and early software development.
In NVIDIA’s case, the Dynamic Duo helps their engineers move from the Palladium Z2 emulator to the FGPA-based Protium system and vice versa with ease and confidence. Their congruent nature ensures that the chip design behaves exactly the same way in both platforms.
The Dynamic Duo’s incredibly fast compile times also mean that a multi-billion gate design can take just four hours to complete. Not too long ago, the same process could take up to 72 hours. Narendra Konda, Director of Hardware Engineering at NVIDIA, described it as a game-changer: “I would say this is a groundbreaking technology in the field of emulation technology. Now, this is what innovation is.”
“Designed with Cadence” is a series of videos that showcases creative products and technologies that are accelerating industry innovation using Cadence tools and solutions. Learn how more about how NVIDIA uses the Cadence Dynamic Duo to accelerate their product development.
For more Designed with Cadence videos, check out the Cadence website and YouTube channel.