English 
SiMa.ai, a pioneer in physical AI solutions, announced the first integrated solution from its strategic collaboration with Synopsys. The joint solution provides a blueprint for accelerating architecture exploration and early-stage virtual software development for next-generation AI-enabled automotive SoCs that power applications such as advanced driver assistance systems (ADAS) and in-vehicle infotainment (IVI).
As previously announced , software-defined vehicles enabling greater autonomy and more intelligent in-cabin experiences require power-efficient SoC architectures with machine learning optimized and validated workloads. SiMa.ai and Synopsys are collaborating to deliver this. As a result of this strategic collaboration, the blueprint announced today enables customers to quickly and confidently begin designing and validating custom AI SoCs for their vehicles. By enabling “upstream” software development without waiting for silicon, customers can reduce development costs, improve software quality, reduce production risk, and accelerate time to market for their vehicles.
The new blueprint delivers pre-integrated SoC virtual prototypes and a unified tool workflow, leveraging industry-leading solutions from SiMa.ai and Synopsys, including:
Early stage architecture exploration:
SiMa.ai’s MLA Performance and Power Estimator™ (MPPE) tool enables automotive customers to design optimally sized ML accelerators for their workloads, allowing them to quickly iterate through different accelerator configurations to identify the best option.
Trusted by automotive companies , Synopsys Platform Architect™ enables you to model automotive workloads at the system level, pre-RTL, and analyze performance, power, memory, and interconnect tradeoffs to make informed architecture decisions early in the design cycle.
こちらもお読みください： トヨタシステムズと富士通、量子技術とAIでオンボードコンピュータ設計を革新
Early verification and validation:
The Synopsys Virtualizer™ Development Kit (VDK) enables customers to develop software on a virtual SoC prototype before silicon is available, enabling them to bring up the entire system within days of silicon availability, shaving up to 12 months off vehicle time to market.
について SiMa.ai Palette SDK simplifies the deployment of complex edge AI applications and supports any ML workflow without sacrificing performance or usability, providing a complete ML stack for in-vehicle edge solutions.
Synopsys ZeBu® emulation provides comprehensive pre-silicon hardware/software performance and power validation to ensure your system architecture meets the needs of your expected workloads.
A new collaborative blueprint, including workflows for support tools, is now available for early-stage customer engagement.
ソース PRタイムズ
日本語