Siemens launches assistive AI solution for IC design and verification

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

Solido helps identify optimization paths to improve PPA & perform statistical yield analysis at a fraction of runtime of brute-force methods.

www.embedded.com/, Jul. 24, 2023 – 

Siemens Digital Industries Software has launched an IC (integrated circuit) design and verification solution, as part of roadmap to enable assistive AI (artificial intelligence) to help design teams meet and exceed increasingly aggressive power, performance, yield and reliability requirements while at the same time accelerating time to market.

Its new Solido Design Environment software has been developed to help circuit designers address the challenges of meeting higher design complexity across applications such as wireless, automotive, high-performance computing (HPC), and internet of things (IoT). The new software provides a single, comprehensive cockpit that handles nominal and variation-aware analysis, including SPICE-level circuit simulation setup, measurements and regressions, as well as waveforms and statistical results analysis.

Using AI technology, Solido can help users identify optimization paths to improve circuit power, performance, and area, as well as to perform production-accurate statistical yield analysis at a fraction of runtime compared to brute-force methods. It also features new additive learning technology that assists in significantly boosting performance for design and verification teams, producing smarter and faster AI decisions and analysis using retained AI models. With these advanced capabilities, the software can help to achieve verification accuracy up to 6 sigma and higher yield at speeds orders of magnitude faster than brute-force Monte Carlo, while helping to significantly improve coverage and accuracy.

In an interview with embedded.com, Amit Gupta, vice president and general manager of the custom IC verification division at Siemens Digital Industries Software, explained the roadmap for AI in EDA, with various levels of AI in EDA contributing to adaptive AI, additive AI and assistive AI at various stages of readiness. He said, "We have learned over the years [since 2005] that there are five key attributes that are critical elements of AI in EDA: verifiability, usability, generality, robustness and accuracy. Usability refers to not having to require algorithm expertise, generality means it works across any system, robustness means if something breaks, the AI is resilient."

click here to read more...

 Back