Cadence leverages AI technology to accelerate system design
Cadence Design Systems has begun integrating artificial intelligence (AI) into its flagship suite of chip design software to help chip designers build better chips faster than they could alone.
Now it’s also powering its system design software with AI to help companies build electronic devices and systems around those chips. Cadence’s latest artificial intelligence platform, called Optimality Intelligent System Explorer, connects to its multi-physics system analysis software to automatically identify areas for system-level improvement.
The San Jose, Calif.-based company said AI technology will help improve productivity. This will allow engineers, on average, to design and qualify electronic devices 10 times faster than traditional manual methods.
Cadence is a leading provider of Electronic Design Automation (EDA) software used in chip design. It is also a major player in multiphysics software used to compose different aspects of a system, ranging from the heat dissipation of a chip’s package to the integrity of power supply and signal transmission on a circuit board. printed.
“For years, system-level optimization has been extremely inefficient as engineers move from design to prototyping to mass production, with testing and tweaking every step of the way, Ben Gu said. , responsible for the company’s multiphysics systems analysis activity.
With Optimality Explorer, “it is now possible to perform system-level optimization, from IC to package, PCB to system, in a fraction of the time and with Cadence’s benchmark accuracy.”
Last year saw the arrival of the Cerebrus Intelligent Chip Explorer, which uses a unique reinforcement learning engine. It uses AI technology to automate parts of the chip design process and suggest improvements to chip designs, minimizing engineering effort and tape time.
One problem Cadence is trying to solve with Cerebrus is chip scheduling. Chip placement requires carefully configuring up to thousands of different components in a compact three-dimensional space.
The reinforcement learning engine at the heart of the Cerebrus technology learns to optimize the placement of building blocks on the chip in a way that makes it less power-hungry and reduces die area.
Reinforcement learning uses positive and negative feedback to learn a complicated task instead of relying on specific instructions on how to complete it. Cadence said it rewards AI when it gets closer to performance and energy efficiency goals for the chip, signaling that it should continue. Conversely, when the AI changes the chip design in a way that has the opposite effect, the system gives it is a virtual penalty. Over time, Cerebrus converges on a strategy for optimally placing components on a floor plan.
MediaTek was an early customer of Cerebrus optimization technology, using it to reduce the die area of a key component inside one of its processors by 5% and power consumption. energy of more than 6%.
Systems analyzed by AI
Now it brings similar AI technology to its multiphysics computational software, including its Clarity Solver for 3D electromagnetic (EM) analysis and SigrityX to assess signal (SI) and power (PI) integrity. ).
With Optimality Explorer, Clarity and Sigrity X solvers help improve productivity by allowing engineers to explore a large number of possible system designs and converge on a design that delivers optimal electrical performance.
The tool is also designed to allow customers to extend AI-based optimization to Cadence’s multiphysics technologies to create a complete computational software suite, spanning simulation, optimization, and approval.
Ease of use is another major benefit, the company said. Customers can enable Optimality Explorer technology in Clarity 3D and SigrityX environments when faced with a challenging design problem.
One of the earliest customers of the AI systems design software is Microsoft, which combines Optimality Explorer with Cadence’s Clarity 3D solver to test circuit boards before mass production.
“Optimality Explorer’s AI-powered optimization has allowed us to discover new designs and methodologies that we wouldn’t have done otherwise,” said Kyle Chen, principal hardware engineer at Microsoft.
General availability is expected in Q4 2022.