First Generative AI tool for power integrity sign off

Find the Latest SoC Solutions
for... Automotive... IoT... Security... Audio... Video

Cadence Design Systems has developed the industry's first generative AI-driven technology to predict, root cause and resolve IR drop issues early in the design process.

www.eenewspower.com/, Nov. 03, 2023 – 

The Voltus InsightAI technology uses machine learning-generated power grid models to enable fast IR analysis of power integrity. This eliminates the need to overdesign the power grid in system on chip and chiplet designs due to early IR drop prediction and prevention capabilities.

The Voltus InsightAI tool integrates with the Cadence digital full flow and system design and analysis platform for efficient EM-IR-driven design closure, fixing up to 95% of violations prior to signoff. The tool has been used by ARM on a 3nm design as well as by MediaTek and the ASIC group at Cisco.

• Cadence launches generative AI for PCB design
• Synopsys adds generative AI data analytics across its EDA tools
• Generative AI provides 5x boost for RTL design

Power integrity is a major design challenge at advanced nodes, with designers regularly facing a significant number of EM-IR violations at signoff, making it imperative to address this challenge early in the design phase.

One of the major bottlenecks of in-design EM-IR analysis is that it is computationally very expensive due to the size and coupled nature of the power network. Using generative AI helps to overcome this bottleneck with fast incremental IR analysis.

The tool uses proprietary neural networks to build models of the power grid and can perform extremely fast incremental IR analysis to provide instant feedback on the impact of design changes. This can determine the root cause of IR drop problems and can quickly identify aggressors, victims and resistance bottlenecks. It uses electrical, spatial and timing factors for predicting IR drop issues during design.

Decision-tree methods are used for timing and design rule check (DRC)-aware fixes of IR drop, using multiple methods like placement, grid reinforcement, routing and engineering change orders (ECOs). The tool selects precise fixing methods based on the root cause of the problem, driving better utilization and improved PPA.

click here to read more...

 Back