Synopsys expands use of AI

1 min read

Synopsys has revealed that its AI-based design system has been used by Samsung to successfully complete a state-of-the-art, high-performance design at an advanced process technology.

This is the most recent of several products that have been designed using Synopsys artificial intelligence (AI).

"For decades, autonomous chip design existed only in science fiction," said Aart de Geus, chairman and co-CEO, Synopsys. "This pivotal moment in semiconductor history will breathe new life into Moore's law. We congratulate Samsung on this remarkable achievement, and we look forward to catalyzing its next 1000x."

The AI-designed product will be manufactured on Samsung's advanced manufacturing process. Samsung used Synopsys' autonomous AI system, (Design Space Optimization AI), driving the Synopsys Fusion Compiler RTL-to-GDSII solution. uses reinforcement learning, an AI technology similar to that used in self-driving vehicles, to achieve better performance, power and area (PPA). Applied at every stage of design implementation, was able to push the operating frequency over 100 MHz beyond target and considerably reduced overall power consumption – saving weeks of manual design effort.

An early development partner of Synopsys' autonomous design technology, Samsung began deploying to multiple projects in the fall of 2020.

"This is a remarkable milestone for our programme to successfully introduce AI into the chip design process in collaboration with Synopsys," said Thomas Cho, EVP of Infrastructure & Design Technology Center, System LSI Business, Samsung Electronics. "Not only have we demonstrated that AI can help us achieve PPA targets for even the most demanding process technologies, but through our partnership we have established an ultra-high-productivity design system that is consistently delivering impressive results." introduces a novel approach to searching vast problem spaces of chip design for optimal solutions, enabled by the latest advancements in AI and machine-learning.

Traditional design space exploration is usually very labour-intensive, typically requiring months of experimentation, guided by past experiences and institutional knowledge.

"This breakthrough marks the beginning of a journey where AI applications and reinforcement learning will help architects with physical design and even logic design," said Karl Freund, principal analyst at Cambrian AI Research. "The possibilities are endless and very promising, with substantial reduction in applied resources, faster time to market and better power, performance and cost."

Using AI technology, can autonomously search design spaces for better solutions, massively scaling the exploration of choices in chip design workflows, while automating a high volume of less consequential decisions. is seen as being able to unleash architectural innovation with AI-grade productivity, driving faster growth in the semiconductor industry and paving a path to 1000x more powerful silicon applications.