Vinci says physics-driven AI cuts chip simulation time from two weeks to one day

Vinci co-founder and CEO Hardik Kabaria discussed the technology with Christophe Bertrand at SEMICON West in an interview broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. Kabaria said Vinci trained an AI model on physics equations and packaged it in software with a harness that gets deployed. When customers start using the product, he said, it works out of the box accurately.

“Can I ship my product faster while making it slightly better performing? We started from there,” Kabaria said. He described Vinci’s goal as making physics calculations run at the speed of AI. “AI moves at light speed, and our goal is to make the physics move at the same speed that the AI is moving so we can enable our customers, our partners to design the best hardware possible,” he said. “The job for us is to ship physics software at the speed of light so that anybody who has a physics question, they get their answer at the inference speed.”

Before founding Vinci, Kabaria pursued doctoral work at Stanford University that helped solve automating high-fidelity meshing for complex, real-world geometries, according to the report. Vinci says it combines deep physics-based simulation with production-grade AI.

The company is working with Advanced Micro Devices Inc. Kabaria said AMD designs some of the best hardware on which AI is inferred and trained, and Vinci’s software also runs on AMD hardware as an inference platform. He said a user can now use AMD’s MI355x to perform an inference of Vinci software to better understand printed circuit boards, chip packages, and the back end of the line in a 3D stacked integrated circuit. “The loop for AI is not future; it’s happening,” he said.

AMD is also an investor in Vinci through its venture arm. Earlier this month, Vinci closed a $250 million funding round at a $1.5 billion valuation. Advent, Temasek and Xora jointly led the Series B deal, which included several venture capital firms, along with AMD Ventures.

Kabaria tied Vinci’s work to broader changes in semiconductor manufacturing, where facilities are becoming more technically demanding and chipmakers are increasingly focused on the engineering expertise and infrastructure needed to support complex manufacturing environments. Asked what he expected for his company and the industry over the next year, he said advances in AI and simulation tools will depend on more than one firm.

“It’s not just one team or one company’s job,” Kabaria said. “I still go back to hardware is an ecosystem. The whole set of us will come together to create a next level of pace at which the innovation will push out.”