Today’s modern electronics design and simulation tools can do wonders designing boards and systems, but they also face new challenges as systems speeds rise and system complexity increases. This is where artificial intelligence algorithms are on the cusp of ushering in a new generation of high-speed design tools, according to Ben Gu of Cadence.
Gu, who is Vice President of Research and Development at EDA vendor Cadence Design Systems, will deliver one of three keynote speeches at the upcoming DesignCon Conference and Exhibition in Santa Clara, CA, from January 31 through February 2, titled, “The Intelligence to Design Intelligent Machines.” He will address how AI is enabling engineers to meet the demands of next-generation electronic systems that employ advanced semiconductors and process nodes.
In a recent interview with Design News, Gu said engineers are just beginning to realize the potential AI has helping often tedious, laborious task such as simulation and board design.
“During design, engineers want to optimize a lot of design parameters. This task can be helped by AI.” He explained that intelligent AI algorithms can substantially speed simulation, including data-intensive tasks such as thermal and fluid dynamic simulations.
AI Tools Available
While the thought of incorporating AI intelligence in the design process may conjure up images of learning more coding, Gu said that does not have to be the case as more EDA vendors are incorporating AI intelligence into their design tools. For instance, Gu noted that Cadence offers a Multiphysics Analysis and Optimization tool, called Optimality Intelligent System Explorer, that replaces the traditional interactive design and test workflow with AI-driven algorithms that can optimize the design solution, without compromising accuracy. Several companion tools for analyzing key parameters, such as EMI and power and signal integrity, are available.
According to Gu, using existing AI tools frees designers not only from additional coding but also the hassles of integrating various design tools, enabling them to concentrate on design and simulation tasks. Suitable uses include pc board and packaging designs. “We have lots of customers trying to partition 3-D package designs,” Gu added.
The next few years will see even more growth in AI-based tools, according to Gu. He foresees the development of deep learning models that use a simulation run as a basis to perform board and circuit simulations at even faster speeds, which would produce even more powerful tools to handle complex engineering designs.
For complete information on this session and other DesignCon keynote and technical sessions, go here.
Spencer Chin is a Senior Editor for Design News covering the electronics beat. He has many years of experience covering developments in components, semiconductors, subsystems, power, and other facets of electronics from both a business/supply-chain and technology perspective. He can be reached at [email protected]