It provides access to platform IP ahead of silicon availability for evaluation to enable pre-production RTL and for teams to develop optimised hardware and concepts such as digital twins to gain expertise early in the design cycle, the company told Electronics Weekly. To aid hardware/software co-design working practices, custom filters allow users to zoom in on critical hotspots, save report configurations for side‑by‑side comparisons, and share views with teammates or domain experts in a shared environment.
Atlas uses physical AI to interpret surroundings via an array of sensors, generating data that must be seamlessly transferred, integrated, and processed in real-time. This data is processed by the embedded AI engine for private decision-making. Low latency, real-time computing is used to control motors and actuators for robotic movements.
The first two products available through Atlas Explorer are the MIPS M8500 microcontroller for low latency control loop applications and the MIPS I8500 deterministic data processing engine. Both are based on RISC-V profiles, enhanced with custom MIPS extensions.
Select customers are able to evaluate the MIPS M8500 processor real-time compute subsystem with Atlas Explorer now, with evaluation boards in Q4 and reference silicon platforms available in the first half of 2026. A MIPS customer automotive platform featuring the processor is expected to begin production in 2027.
Related news: https://www.electronicsweekly.com/news/siemens-applies-ai-across-chip-and-pcb-design-portfolio-2025-06/
