Build tomorrow’s products today
Artificial intelligence (AI) promises to revolutionize people’s lives. Whether it’s autonomous cars or advances in the medical industry, we will all benefit from this revolution. How will we get there?
Convolution and recurrent neural networks and machine and deep learning algorithms present the opportunity to enable this electronics revolution and create a new silicon renaissance with advances in software and IP. The electronics industry is addressing larger and larger volumes of design and simulation data that increase complexity and challenge productivity.
To meet the changing requirements of our customers, Cadence continues to invest in and develop products for this evolving market:
Tools and flows: Utilizing machine learning/deep learning techniques inside our design tools make them smarter and faster, as well as increase designer productivity—exponentially.
IP: Our broad offering of Tensilica® DSPs and processors for AI at-the-edge processing and memory IP provide AI capability for consumer devices, while advanced memory interfaces enable machine learning in the cloud and high-performance computing.
READ MORE
CLOSE
Improving Our Tools and Flows
Reduce evaluating time, leverage our libraries of algorithm
LEARN MORE
Enabling Artificial Intelligence
Enable compute and data-intensive machine learning/AI applications
LEARN MORE
Improving Our Tools and Flows
We’re already using machine learning techniques to produce better, more predictable outcomes for many tasks in the EDA flow. But there are so many more potential areas for improvements. Machine learning can help our customers meet their time-to-market requirements if we can make the design process smarter and reduce the amount of manual intervention necessary. The goal is to allow our tools to suggest solutions to common problems that might otherwise take design teams weeks or months to evaluate.
Cadence is using combinations of statistical models with increasing sophistication in our simulation, verification, analog, power analysis, place-and-route, and modeling tools. Here are just a few examples:
Virtuoso® Layout Suite for Electrically Aware Design and Analog Design Environments – The Virtuoso Electrically Aware Design Environment uses analytics and machine learning technologies for rapid in-design parasitic extraction. The Virtuoso Analog Design Environment uses machine learning for mismatch modeling for design tuning and verification.
JasperGold® Formal Verification Platform (Apps) – This next-generation platform features machine learning technology to improve verification throughput for the JasperGold apps.
Silicon Signoff – Cadence employs machine learning technology across its electrical signoff portfolio of products including the Liberate™ Characterization Portfolio and the Tempus™ Timing Signoff Solution.
We are also pushing the leading edge of machine and deep learning research to improve the design of ICs and verification closure with a vision toward design improvement. The Cadence machine learning team leverages our libraries of algorithms across platforms and products to ensure each wave of innovation impacts the breadth of our EDA and IP solutions.
Enabling Artificial Intelligence Systems
So many of our customers are designing AI applications that challenge the traditional capacity, productivity, and compute requirements we have seen in the electronics industry. For example, running computationally complex algorithms on standard processors often does not give the performance or power efficiency necessary for compute- and data-intensive machine learning/AI applications.
Cadence is a leader in the advanced memory interfaces required by AI applications in servers. Along with our partner Micron, Cadence introduced the world’s first DDR5 IP silicon prototype memory subsystem. Cadence and Samsung have partnered to bring GDDR6 interfaces to market. To support AI in mobile and automotive applications, Cadence has introduced the first working silicon for LPDDR5 in 7nm technology.
Our Tensilica DSPs and processors are optimized for AI at-the-edge processing. Being at the edge requires that the DSPs and processors have high energy efficiency to meet the needs of mobile products that are battery powered or automotive products that have thermal power constraints.
The Tensilica DNA 100 processor for AI-at-the-edge inference is the recent addition to the Tensilica AI family. It supports both convolution and recurrent neural networks to support AI experiences in vision, speech, radar, lidar, and communication products.
Our Tensilica Vision DSPs for vision and neural network processing are designed into a variety of consumer products. They process complex algorithms in imaging and computer vision, HDR processing, object and face detection, gesture recognition, and many more
Tensilica HiFi DSPs dominate all consumer market segments that require audio processing and AI speech processing, as well as markets that integrate advanced voice UI capabilities. It also has the largest partner ecosystem with an expansive range of audio software.
Driving Innovation and Collaboration
Our technology experts explain how
Cadence Selected for Machine Learning Contract by DARPA
Our job is helping customers design sophisticated silicon, which is becoming more and more complex.
Lip-Bu Tan
Chief Executive Officer
We’ve been leading the industry in the development, deployment, and support of electronic design flows that use machine learning, analytics, and optimization technologies.
Anirudh Devgan
President
Our job is helping customers design sophisticated silicon, which is becoming more and more complex.
Lip-Bu Tan
Chief Executive Officer
We’ve been leading the industry in the development, deployment, and support of electronic design flows that use machine learning, analytics, and optimization technologies.
Anirudh Devgan
President
Fair and useful benchmarks for measuring training and inference performance of ML hardware, software, and services