EdgeCortix has introduced RAIDEN, a next-generation AI chiplet platform designed specifically for physical AI—systems that interact with the real world, such as robotics and autonomous machines. The platform extends the company's existing energy-efficient design philosophy into a modular chiplet architecture, allowing performance to scale without sacrificing power efficiency.
According to the announcement, RAIDEN is positioned to address the growing computational demands of physical AI, where latency and power constraints are critical. By adopting a chiplet-based approach, EdgeCortix aims to offer flexibility in configuration while maintaining the low-energy characteristics that have defined its earlier products.
The company states that RAIDEN carries its energy-efficient design into a new performance class, suggesting that the platform can handle more demanding AI workloads than previous offerings. However, specific performance figures, chiplet configurations, and availability details were not disclosed in the initial release. The platform represents a strategic move to compete in the expanding edge AI hardware market, where scalability and efficiency are increasingly important.