Socionext Expands Agentic AI to Advanced, Large-Scale SoC Physical Design
Cadence® InnoStack™ AI Super Agent to support Socionext's AI-driven physical design for large-scale 3nm SoCs
YOKOHAMA, Japan & SAN JOSE, Calif., October 20, 2026--Socionext Inc., a global leader in custom SoC design and development, is actively advancing its SoC design and development capabilities through agentic AI and expanding the application of AI-driven design to the physical design of large-scale system-on-chip (SoCs) using advanced process technologies. For the expansion into physical design, Socionext is collaborating with Cadence (Nasdaq:CDNS).
Actively Advancing Agentic AI Initiatives in SoC Design and Development
Socionext has been integrating agentic AI into front-end design to improve the efficiency of design and verification tasks, support engineering analysis and decision-making, and leverage accumulated design knowledge and expertise. Beyond improving the efficiency of individual tasks with AI, Socionext is also integrating AI agents into its design and development processes to further enhance engineering productivity and design quality. Through these initiatives, Socionext aims to create a development environment that enables engineers to focus on higher-value design decisions and innovation.
Expanding AI-Driven Design into SoC Physical Design
Socionext is expanding its AI-driven design approaches into physical design. As physical design becomes increasingly complex for large-scale SoCs using advanced process technologies, effectively integrating AI agents with advanced EDA tools and design flows is critical to addressing these challenges and further improving design efficiency. Through its collaboration with Cadence, Socionext is advancing these efforts and is applying AI-driven design to the physical design of a large-scale 3nm SoC. As part of these efforts, Socionext is applying the Cadence InnoStack AI Super Agent and plans to expand its use across SoC development projects.
Integrating Engineering Knowledge into Physical Design Workflows
Through retrieval-augmented generation (RAG), Model Context Protocol (MCP) support, customized AI skills, and AI agents, Socionext integrates internal design knowledge into practical physical design workflows. Current and planned applications include floorplanning, custom timing-analysis checks, and future checklist automation, helping make proprietary expertise more accessible and reusable across projects and teams.
"As semiconductor design complexity grows, engineering organizations need better ways to capture and reuse expertise across projects and teams," said Chin-Chi Teng, senior vice president and general manager of the Digital and Signoff Group at Cadence. "Socionext's implementation demonstrates how the open and extensible InnoStack AI Super Agent enables customers to integrate their own methodologies and proprietary engineering knowledge into AI-assisted design environments. Together, Cadence's technology and Socionext's engineering expertise make valuable design knowledge more accessible and actionable across the organization."