Synopsys adds generative AI data analytics across its EDA and fab tools
Synopsys is extending its AI-driven chip design tools with data analytics for every stage of the development process.
The AI-driven data analytics in Synopsys.ai aggregates and analyses data across design, test, and manufacturing flow to drive more intelligent decision making with a range of different AI techniques, including generative AI frameworks.
The addition of the Ai analytics is intended to speed up closure of the physical, logical and prototype design through intelligence-guided debugging and optimization and improve fab yield for faster ramp and higher throughput for high-volume manufacturing (HVM).
This comes as several startups such as Flexciton in the UK are using AI to optimise fab flows to boost throughput and yield.
The data in the EDA, testing, and IC fabrication tools is all very different, from timing paths, power profiles, die pass/fail reports, process control, or verification coverage metrics. Using this data is critical for improving productivity, PPA, and parametric/manufacturing yield says Synopsys, which is why it has added the big data analysis tool to each part of the design flow.
This can also help designers rapidly localize and correct problem areas throughout mask, fabrication, and test processes before the problems impact product quality and yield. Companies also benefit from generative AI methods on their data sets to enable new use cases like knowledge assistants, preemptive and prescriptive what-if exploration, and guided issue resolution.
Synopsys has been moving more into the product lifecycle management (PLM) market with yield tools and sensor IP after the acquisitions of Moortec in the UK and BisTech in Korea.
Using AI uncovers silicon data outliers across the semiconductor supply chain to improve chip quality, yield, and throughput. There are several tools in the suite.
Design.da performs deep analysis of data from the Synopsys.ai design execution, providing chip designers with comprehensive visibility and actionable design insights to uncover power, performance, and area (PPA) opportunities.
Fab.da stores and analyzes large streams of fab equipment process control data that increase operational efficiencies and maximize product quality and fab yield.
Silicon.da collects petabytes of silicon monitor, diagnostic, and production test data from test equipment to improve chip production metrics, such as quality, yield, and throughput and silicon operation metrics, such as chip power and performance.
“As IC complexity grows and market windows shrink, the semiconductor industry is increasingly adopting artificial intelligence technologies to enhance the quality of results (QoR), speed verification and testing, improve fab yield, and boost productivity across multiple domains spanning the entire IC design flow,” said Sanjay Bali, vice president of Strategy and Product Management for the EDA Group at Synopsys.
“With the new data analytics capabilities within the Synopsys.ai EDA suite, companies can now aggregate and leverage data across every layer of the EDA stack from architecture exploration, design, test, and manufacturing to drive improvements in PPA, yield, and engineering productivity.”
Th e AI-enabled data analytics are already being used by customers such as sk Hynix and Marvell.
“The volume of data generated during chip manufacturing and testing is massive, making big data tools essential to analyze and extract meaningful conclusions from these data sets,” said Dr. Greg Bazan, senior principal engineer at Marvell.
“The chip data analytics tool has been vital to improve the efficiency and quality of our manufacturing process. We look forward to experiencing how the benefits of Synopsys’ next-generation analytics tool can further improve our KPIs and reduce manufacturing and test costs for our next-generation products.”
www.synopsys.com/ai/ai-powered-eda.html#da
Other EDA AI articles
- Siemens, PDF Solutions team to boost IC yield
- Generative AI provides 5x boost for RTL design
- Cadence uses AI to automate move to 3nm and 2nm
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
