Cadence Design Methods introduced two AI-related collaborations at its CadenceLIVE occasion this week, increasing its work with Nvidia and introducing new integrations with Google Cloud. The Nvidia partnership focuses on combining AI with physics-based simulation and accelerated computing for robotic techniques and system-level design.
The businesses mentioned the strategy targets modelling and deployment in semiconductors and large-scale AI infrastructure, together with robotic techniques that Nvidia describes as physical AI.
Cadence is integrating its multi-physics simulation and system design instruments with Nvidia’s CUDA-X libraries, AI fashions, and Omniverse-based simulation atmosphere. The instruments mannequin thermal and mechanical interactions so engineers can assess how techniques behave beneath real-world working circumstances. In addition they prolong past chip design to cowl infrastructure parts like networking and energy techniques. The mixed platform lets engineers simulate system behaviour earlier than bodily deployment. The businesses mentioned system efficiency depends upon how compute, networking and energy techniques function collectively.
The collaboration additionally consists of robotics growth. Cadence’s physics engines, which mannequin how real-world supplies work together, are being linked with Nvidia’s AI fashions used to coach AI-driven robotic techniques in simulated environments.
“We’re working with you within the board on robotic techniques,” mentioned Nvidia CEO Jensen Huang in the course of the occasion.
Coaching robots in simulation reduces the necessity for real-world knowledge assortment. The businesses mentioned these datasets have to be generated with physics-based fashions not gathered from bodily techniques. Simulation-generated datasets are used to coach fashions, with outcomes depending on the accuracy of the underlying physics fashions.
“The extra correct (generated coaching knowledge) is, the higher the mannequin will likely be,” mentioned Cadence CEO Anirudh Devgan.
Nvidia mentioned industrial robotics firms are utilizing its Isaac simulation frameworks and Omniverse-based digital twin instruments to check robotic techniques earlier than deployment. Firms together with ABB Robotics, FANUC, YASKAWA, and KUKA are integrating these simulation instruments into digital commissioning workflows to check manufacturing techniques in software program previous to bodily rollout.
Nvidia mentioned these techniques are used to mannequin complicated robotic operations and full manufacturing traces utilizing bodily correct digital environments.
Chip design automation on cloud
Individually, Cadence launched a brand new AI agent designed to automate later-stage chip design duties. The agent focuses on bodily format processes, translating circuit designs into silicon implementations. The discharge builds on an earlier agent launched this 12 months for front-end chip design, the place circuits are outlined in code-like descriptions. That earlier system handles circuit design, whereas the brand new agent focuses on translating these designs into bodily layouts on silicon.
The system will likely be out there by Google Cloud. Cadence mentioned the mixing combines its digital design automation instruments with Google’s Gemini fashions for automated design and verification workflows. The cloud deployment permits groups to run these workloads with out counting on on-premise compute infrastructure.
Cadence’s ChipStack AI Tremendous Agent platform makes use of model-based reasoning with native design instruments to coordinate duties in a number of design phases. The system can interpret design necessities and mechanically execute duties in numerous phases of the design course of.
Cadence reported productiveness features of as much as 10 occasions in early deployments in design and verification duties. The corporate didn’t disclose particular buyer implementations.
“We assist construct AI techniques, after which these AI techniques will help enhance the design course of,” Devgan mentioned.
The businesses mentioned simulation instruments are used to validate techniques in digital environments earlier than bodily deployment. Digital twin fashions enable engineers to check design trade-offs, consider efficiency situations, and optimise configurations in software program.
They added that the price and complexity of large-scale knowledge centre infrastructure restrict the usage of trial-and-error deployment strategies.
Quantum fashions announcement
In a separate announcement, Nvidia launched a household of open-source quantum AI fashions referred to as NVIDIA Ising. The fashions are named after the Ising mannequin, a mathematical framework used to characterize interactions in bodily techniques.
The fashions are designed to help quantum processor calibration and quantum error correction. Nvidia mentioned the fashions ship as much as 2.5 occasions quicker efficiency and 3 times increased accuracy in decoding processes used for error correction.
“AI is important to creating quantum computing sensible,” Huang mentioned. “With Ising, AI turns into the management aircraft – the working system of quantum machines – reworking fragile qubits to scalable and dependable quantum-GPU techniques.”
(Picture by Homa Appliances)
See additionally: Hyundai expands into robotics and bodily AI techniques
Wish to be taught extra about AI and large knowledge from trade leaders? Take a look at AI & Big Data Expo going down in Amsterdam, California, and London. The great occasion is a part of TechEx and co-located with different main expertise occasions. Click on here for extra data.
AI Information is powered by TechForge Media. Discover different upcoming enterprise expertise occasions and webinars here.
