MIPS, GlobalFoundries Bet on Physical AI

2026-03-03 · Source: Big Data & AI News - EE Times · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Software Development & Engineering · Depth: Intermediate, medium

Summary

MIPS, having emerged from bankruptcy and acquired Synopsys's ARC processor IP business, is making a significant comeback by shifting its focus from its foundational MIPS instruction set to RISC-V architecture, specifically targeting "physical AI" and autonomous edge applications. The company's eighth generation of products is RISC-V, exemplified by Mobileye's EyeQ7, and MIPS is positioning itself as a "technology enabler" through its Atlas Explorer virtual platform for software-hardware co-design. A key differentiator is its focus on deterministic processing for mission-critical functions, supported by the first ISO 26262 ASIL-B certified RISC-V multi-threaded core and Real-Time Multi-Threading (RTMT) for picosecond context switching. The acquisition by GlobalFoundries (GF) has accelerated NPU development and positions GF as a vertically integrated physical AI platform, offering a full stack from IP to manufacturing. This strategy focuses on mature technology nodes to reduce customer costs and enhance competitive advantage.

Key takeaway

MIPS, now RISC-V focused and backed by GlobalFoundries, is strategically positioning itself as a vertically integrated "physical AI" platform for autonomous edge and mission-critical applications. Their S8200 RISC-V NPUs, developed via the Atlas Explorer co-design platform, feature ISO 26262 ASIL-B certified cores and Real-Time Multi-Threading (RTMT) enabling picosecond-level context switching for deterministic, low-latency workloads. This unique IP-plus-foundry model offers optimized, cost-effective solutions for on-device AI, exemplified by Mobileye's EyeQ7, addressing the shift to software-defined vehicles.

Topics

• RISC-V Architecture
• Physical AI
• Automotive ADAS
• Real-Time Multi-Threading
• GlobalFoundries Integration

Best for: Computer Vision Engineer, AI Hardware Engineer, AI Engineer, Software Engineer

Related on AIssential

• When Arm Meets RISC-V: SiPearl, Semidynamics to Co-Develop Sovereign AI Platform — European firms SiPearl and Semidynamics are building a sovereign, rack-scale AI inference platform using Arm CPUs and RISC-V accelerators.
• Here’s how our TPUs power increasingly demanding AI workloads. — TPUs are Google's custom chips optimized for high-speed AI model computation.
• Heterogeneous Tasks Offloading in Vehicular Edge Computing: A Federated Meta Deep Reinforcement Learning Approach — FedMAGS optimizes VEC task offloading using federated meta-learning, GATs, and Seq2Seq for privacy-preserving, scalable performance.
• Building Robotics Applications with Ryzen AI and ROS 2 — Integrate Ryzen AI perception models into ROS 2 robotics applications for power-efficient edge processing.
• RISC-V Pivots from Academia to Industrial Heavyweight — RISC-V is rapidly expanding globally, driven by modularity, specialization, and strategic standardization for diverse applications.
• Meta to Deploy “Millions” of Nvidia Processors — AI investment is driving significant shifts in chip deployment, software development, and market dynamics across multiple sectors.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Big Data & AI News - EE Times.