Artificial Intelligence

Synopsys.ai unveiled as industry's full-stack, AI-driven EDA suite for chipmakers

30th March 2023
Sheryl Miles
0

At its annual Synopsys Users Group (SNUG) Silicon Valley Conference, Synopsys has launched Synopsys.ai, a suite of AI-driven solutions for the design, verification, testing and manufacturing of the most advanced digital and analogue chips.

For the first time, engineers can use AI at every stage of chip design, from system architecture to design and manufacturing, and access the solutions in the Cloud. Renesas, a specialist in the automotive space, is already using Synopsys.ai to shave weeks off product development times with enhanced silicon performance and cost reduction.

The Synopsys.ai EDA suite includes AI-driven solutions:

Digital design space optimisation to achieve power, performance and area (PPA) targets, and boost productivity (used in 100 production tape-outs by January 2023).

Analogue design automation for rapid migration of analogue designs across process nodes.

Verification coverage closure and regression analysis for faster functional testing closure, higher coverage, and predictive bug detection.

Automated test generation resulting in fewer, optimised test patterns for silicon defect coverage and faster time to results.

Manufacturing solutions to accelerate development of lithography models with high accuracy to achieve the highest yield.

"Increased complexity, engineering resource constraints and tighter delivery windows were challenges crying out for a full AI-driven EDA software stack from architectural exploration to design and manufacturing – and we've delivered it," said Shankar Krishnamoorthy, GM of Synopsys EDA Group. "With Synopsys.ai solutions, our customers' ability to search design solution spaces across multiple domains is in hyperdrive. They're finding optimal results far faster as the .ai learns run-to-run, and it's transforming their ability to meet and beat tough design and productivity targets."

Industry leadership in AI-driven semiconductor design

Synopsys.ai tools are now in use by nine of the top 10 semiconductor companies, establishing Synopsys as one of the early leaders in this space. With each design project, the solutions' AI engines continually train on data sets, allowing them to become more adept at optimising results over time.

Here's what some industry leaders are saying about the AI-driven EDA design suite:

"Meeting quality and time-to-market constraints is fast becoming difficult using traditional human-in-the-loop techniques due to the ramp in design complexity," said Takahiro Ikenobe, IP Development Director, Shared R&D Core IP Division at Renesas. "Using AI-driven verification with Synopsys VCS, part of Synopsys.ai EDA suite, we've achieved up to 10x improvement in reducing functional coverage holes and up to 30% increase in IP verification productivity demonstrating the ability of AI to help us address the challenges of our increasingly complex designs."

"Achieving the highest quality silicon is essential given our increasingly complex chips that power many of the world's devices," Xian Lu, Director, MediaTek. "We must constantly improve methodologies and deploy new technologies to quickly deliver test programs that provide high defect coverage while minimising testing cost. AI-driven enhancements for automatic test pattern generation are critical to achieving our future silicon testing goals."

"TSMC works closely with our Open Innovation Platform (OIP) partners like Synopsys to enable our customers to improve productivity and accelerate design closure when performing process-to-process design migration of custom and analogue blocks," said Dan Kochpatcharin, Head of Design Infrastructure Management Division at TSMC. "With the latest Synopsys AI-driven analogue design migration flow and TSMC enhanced PDKs, we now enable efficient reuse of designs that are migrating from one of our widely used processes to another and benefit from the power, performance, and area improvements of our latest technologies."

"At advanced technology nodes it is critical to have accurate lithography models for optical proximity correction," Huiming Bu, VP, Global Semiconductor R&D and Albany Operations at IBM Research. "Utilising AI/ML accelerates the development of highly accurate models that yield the best results during silicon fabrication. We are excited to collaborate with Synopsys on AI-driven mask synthesis solutions that can help our partners reach market faster." 

"AI has the potential to reshape virtually every field, and its benefits for the semiconductor industry are hard to overstate," said Vivek K. Singh, VP, Advanced Technology Group at NVIDIA. "We're working alongside leading companies like Synopsys to accelerate and improve production and open new frontiers for the industry." 

According to industry analyst Patrick Moorhead from Moor Insights & Strategy: "AI is transforming the semiconductor industry, enabling engineers to create more complex chips that humans unaided would be unable to produce. The horizons AI will open up are hard to imagine, only we know we'll be able to move faster and do more than we can now – including how we tackle major global issues such as hunger, epidemic control, and climate change. Synopsys is now clearly taking the lead in infusing AI throughout the chip development flow, and we should applaud their investment in the industry's future.”

Featured products

Product Spotlight

Upcoming Events

View all events
Newsletter
Latest global electronics news
© Copyright 2024 Electronic Specifier