Synopsys attended Nvidia GTC Berlin and showcased its industry-leading portfolio of more than 20 GPU-enabled electronic design automation (EDA) and multiphysics solutions.
Now supporting 50 Nvidia CUDA-X libraries and frameworks, Synopsys is applying AI to enable significantly faster design and simulation analysis cycles to minimize the persistent speed vs. precision tradeoff during product development.
Why it matters?
Increasing system sophistication and performance are driving greater compute requirements to power engineering workflows. The Synopsys and Nvidia strategic partnership is advancing GPU-enabled engineering solutions to provide a powerful and secure foundation for accelerating physical AI, virtual prototyping, and silicon and system design.
The conference also spotlights how European engineering teams across the automotive, aerospace, semiconductor, and AI infrastructure segments are leveraging Synopsys solutions to shift more development and validation into virtual environments that expand design space exploration and shrink waiting times for actionable, predictive insights into silicon and system design and performance. Advancements showcased with customers during GTC Berlin include:
Advancing physical AI, semiconductor innovation, and virtual prototyping:
* Synopsys is now part of the Nvidia Halos safety ecosystem, integrating newly announced Nvidia Halos SAFE to enrich and extend events with a physics-based, traceable workflow spanning sensor simulation, virtualization, digital twins, and safety analysis.
Ansys AVxcelerate real-time sensor simulation technologies, now part of Synopsys, augment events with high fidelity stimuli for software-in-the-loop and hardware-in-the-loop testing. Ansys medini connects ground-truth synthetic data back to hazards and safety requirements, integrating simulation and validation results into a structured safety case.
* Synopsys is collaborating with T-Systems using a FORVIA HELLA-approved automotive exterior lighting workload in T-Systems’ sovereign Industrial AI Cloud. Running Ansys Speos on Nvidia GPUs cut the simulation runtime from more than 4.5 hours to just under 19 minutes overall vs. a CPU configuration.
* Infineon, a global semiconductor leader in power systems, is using Synopsys Sentaurus Device with Nvidia cuDSS to achieve a 12x speedup in 3D breakdown simulation for next-generation power devices.
* imec, a leading research and innovation hub in advanced semiconductor technologies, is using Synopsys’ GPU-accelerated S-Litho within computational lithography workflows to model advanced DUV, EUV and High-NA EUV processes. Benchmarks of S-Litho on Imec’s model show up to 40x speedup using Nvidia CUDA-X libraries.
Scaling AI infrastructure with photonics
* iPronics is using Ansys Lumerical FDTD and Nvidia H100 GPUs in an AWS cloud environment to develop photonic technologies for AI-scale data centers, achieving up to 13x solver speedup compared with a 96-core CPU environment and reducing a 20-point edge-coupler parameter sweep from approximately nine days to 18 hours.
* Alcyon Photonics also uses Ansys Lumerical to design photonic building blocks, including directional couplers and integrated subsystems, for datacenter transceivers. Electromagnetic simulations and accurate foundry process models help Alcyon analyze fabrication tolerances, alignment sensitivities and broadband optical performance for maximum tape-out confidence.