Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

Keysight Introduces Electronic Design Automation Software Suite Amplifying Designer Productivity with AI

Keysight Technologies

  • Reduces Radio Frequency (RF) device modeling time from days to hours

  • Automated Python workflows streamline design processes

  • Accelerates predictive design of chiplet interconnects

Keysight Technologies, Inc. introduced its new Electronic Design Automation (EDA) software portfolio to transform how engineers address the demands of next-generation technologies. As the electronics industry races to develop advanced solutions for 5G/6G and data center applications, Keysight’s suite of EDA tools leverages AI, machine learning (ML), and Python integrations to dramatically reduce design time for complex RF and chiplet products.

Also Read: AI helps Data Engineers be Distinguished Data Engineers

“With this release, engineers can easily import data from measurements or swept simulations to train neural network models, which then execute very quickly in subsequent simulations. This unlocks new possibilities for abstracting and co-optimizing large parts of the RF design together, dramatically accelerating the development process.”

Keysight’s EDA 2025 software addresses critical challenges in the development lifecycle by enhancing data manipulation, integration, and control of best-in-class simulators, allowing engineers to build efficient workflows seamlessly across multiple tools. AI-enhanced workflows and high-performance computing further reduce the time-to-insight, enabling engineers to move from simulation to verification and compliance with greater confidence. For simulating fast digital interconnects, the software is equipped with end-to-end component models and measurements that conform to digital standards, providing an efficient and high-accuracy digital twin for complex digital electronic design challenges.

Also ReadSovereign Digital Identities and Decentralized AI: The Key to Data Control and the Future of Digitalization

Related Posts
1 of 41,173

Core benefits of the EDA 2025 software portfolio include:

  • RF Circuit Design: Accelerate RF design cycles through open, automatable workflows featuring Python integration and multi-domain simulation. Additionally, the Python toolkit enables engineers to quickly consolidate measured load pull data from various files and formats into a single, cohesive dataset to train fast AI/ML models.
  • High-speed Digital Design: Create precise digital twins for complex standard-specific SerDes designs, including Universal Chiplet Interconnect Express (UCIe) chiplets, memory, USB, and PCIe , with the Advanced Design System (ADS) 2025 release.
  • Device Modeling and Characterization: Reduce model re-centering time by 10X through AI/ML capabilities in the IC-CAP 2025 release, while Python integrations streamline and automate the modeling process.

Nilesh Kamdar, EDA Design & Verification General Manager at Keysight, said, “AI is transforming how engineers approach complex design challenges. Automating traditionally time-intensive tasks enables engineers to focus on innovation rather than repetitive refinements, resulting in real productivity gains. The foundation for the practical application of AI and ML is first having an open, interoperable workflow and then providing turn-key solutions tuned for specific applications. It’s a fascinating time, and AI and ML will undoubtedly be a huge driver of design innovation in the future.”

Stephen Slater, Director of Product Management at Keysight, said, “With this release, engineers can easily import data from measurements or swept simulations to train neural network models, which then execute very quickly in subsequent simulations. This unlocks new possibilities for abstracting and co-optimizing large parts of the RF design together, dramatically accelerating the development process.”

[To share your insights with us as part of editorial or sponsored content, please write to psen@itechseries.com]

Comments are closed.