Podcast EP365: How Agentrys is Revolutionizing Chip Design with Mark Ren
Daniel is joined by Mark Ren, founder and CEO of Agentrys. Mark has 26 years of EDA and AI R&D experience spanning IBM Research and NVIDIA Research, driving design automation innovations that power modern chip design. He received the IBM Corporate Award for contributions to the design closure for high-performance microprocessors. At NVIDIA, he helped establish the company as a world leader in AI for chip design and GPU-accelerated EDA. Mark has spearheaded the modern GPU-accelerated EDA movement, driving adoption of deep-learning frameworks to unlock performance and scalability for EDA workloads. He also led the first industrial LLM-for-chip-design effort, ChipNeMo.
Daniel explores the changing role of AI in chip design with Mark, who describes the substantial improvement in performance and capability that AI agents have achieved. He describes several significant accomplishments in this area and explains that these improvements led him to found Agentrys to truly harness these new capabilities in ways that significantly impact a broad range of design problems.
Dan then explores the unique capabilities Agentrys delivered at the recent Hot Chips conference. Last year, Mark presented at the conference for NVIDIA. This year, Agentry came to the show with a substantial design flow built with Agentrys tools that optimized an open-source design by reducing power by 28 percent, increasing performance by 40 percent and reducing area by 10 percent, all with an automated, agentic flow. Mark went on to describe how Agentrys took real design problems from Hot Chips 2026 attendees and developed solutions in their booth during the show. Daniel mentioned this is likely the first time any company has done this.
The views, thoughts, and opinions expressed in these podcasts belong solely to the speaker, and not to the speaker’s employer, organization, committee or any other group or individual.
Next Agentrys Webinar:
Agents Assemble: Build Your Chip Design Multi-Agent System in 30 Minutes
Comments
There are no comments yet.
You must register or log in to view/post comments.