Physics AI pushes chip design beyond traditional simulation

Physics AI pushes chip design beyond traditional simulation

Vinci4D Inc. is bringing a new approach to semiconductor design grounded in fundamental physics equations.

The company provides simulation software for chip designers, offering an alternative to traditional simulation methods, including finite element analysis, a technique engineers use to study the physical behavior of objects. Instead, Vinci4D’s technology uses pretrained physics models to accelerate simulations and analyze multiple physical phenomena simultaneously.

“Vinci is changing how design and analysis is being done from the ground up,” said Karthik Aravamudhan (pictured), global client director at Vinci4D. “The whole industry is talking about agentic AI and how the workflow automation, the orchestration, happens. That means more simulations, more analysis, a lot more that needs to happen under the hood. Vinci is trying to attack that problem.”

Aravamudhan spoke with theCUBE’s Christophe Bertrand at SEMICON West, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed Vinci’s approach to physics-based simulation and its implications for semiconductor design and agentic AI. (* Disclosure below.)

Physics foundation models reshape semiconductor design

Physics foundation models could play a growing role in semiconductor engineering, according to Aravamudhan. He highlighted the strategic shift from Design Technology Co-Optimization to System Technology Co-Optimization, which involves thinking of chip design as one part of a larger system.

“[Vinci] fundamentally tries to solve the problem from the foundational physics level,” Aravamudhan said. “When you’re designing, you’re trying to understand what the package looks like. While you’re designing the package, you’re trying to understand what the board looks like. So, you’re designing a whole system; you’re not just designing one portion of it anymore.”

Vinci trains its models on physics equations rather than customer data, reducing the need to expose proprietary design information during model training. Its technology also aims to reduce the time and cost of simulations by analyzing multiple physical phenomena simultaneously.

“An average customer today in the whole semiconductor ecosystem tries to solve for a certain physics,” Aravamudhan explained. “It could be thermal, it can be mechanical and it can by any[thing]. They try to solve one physics at a time because that’s the only way it has been known to be possible. That takes a whole long time. What Vinci tries to do with these foundational physics models is try to solve these physics true to what it is and to solve multiple of these at the same time.”

Vinci recently closed a $250 million Series B funding round at a $1.5 billion valuation, co-led by Advent International, Temasek and Xora. The startup now plans to expand its reach beyond semiconductors into other hardware industries, including automotive and aerospace applications.

“The funding gives us … the foundation to go after bigger [things],” Aravamudhan said. “From the different physics that we can solve, from having a go-to-market team and a go-to-market approach, it gives us so many different dimensions we can start focusing on. With these big names backing us, it certainly helps a lot and it shows their belief not only in Vinci, but their belief in the technology.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of SEMICON West:

(* Disclosure: TheCUBE is a paid media partner for the SEMICON West event. Neither Vinci, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE