Physics AI accelerates chip design with Vinci

Physical AI brings a new approach to semiconductor engineering, where increasingly complex designs make it difficult to predict physical behavior. Advanced accelerators combine multiple chips, memory and packaging components, creating closely related technical challenges.

Vinci4D Inc. uses physical AI to integrate simulation into engineers’ daily design work. According to Dinesh Panneerselvam (pictured), head of technical solutions at Vinci, his approach addresses a well-known technical trade-off.

“In practice, I often find that engineers have to choose between accuracy or fast physics,” he said. “They don’t have the ability to do both. Vinci gets them both up to speed at which they design.”

Panneerselvam spoke with Christophe Bertrand of theCUBE Research at SEMICON West during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed physics-based simulation, previous design investigations and protecting customer data. (*Disclosure below.)

Physics AI moves analysis upstream

Vinci combines a foundational physics model with a GPU-native physics core in an approach it calls Continuous Physics Reasoning. According to Panneerselvam, the combination delivers repeatable results with solver accuracy.

“In the world of product development, the team that understands the physics – or behavior – of their product early wins the race,” he said. “That’s exactly what Vinci offers. That means you design at your architectural level. We offer the performance.”

The model is trained using Vinci’s own data, not customer data. By deploying behind the customer’s firewall, proprietary design information remains with the customer, Panneerselvam explained.

“The way we designed our platform, it fits right into your workflow,” he said. “You don’t need to change any of your current workflows. We take your design files as-is and start building the model. There’s so much automation built in that very little manual input is required.”

Expanding physical AI beyond chips

Physical AI could also support the development of physical AI, including robots and humanoid systems. Panneerselvam said Vinci’s simulation approach could help engineers understand how these products would behave before committing to a specific design.

“Customers are able to open doors to new innovations – things they couldn’t imagine before,” he said. “For example, you have a technical feel for a product, and that’s where it ends. What Vinci and products like Vinci enable is basically [to] explore beyond. We call it the art of the impossible, and you can get into that space.”

Vinci is exploring automotive and aerospace applications while expanding beyond its semiconductor base. The $250 million Series B funding round will support the development of additional physics disciplines and industries, including planned capabilities in electromagnetics and fluid dynamics, Panneerselvam explained.

“The bottom line is that physics doesn’t change,” he said. “It’s just the applications we need to create. The physics remain the same.”

Here’s the full video interview, part of SiliconANGLE 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 theCUBE or SiliconANGLE content.)

Photo: SiliconANGLE