EdgeCortix secures $21M to develop energy-efficient AI chiplet
This funding will drive the development of NovaEdge — a next-generation, energy-efficient edge AI chiplet designed for high-performance generative AI inference and on-device learning.
EdgeCortix, a Tokyo-based fabless semiconductor company specializing in energy-efficient edge AI, has been awarded an additional 3 billion Yen (USD 21 Million) project from Japan’s New Energy and Industrial Technology Development Organization (NEDO), a national research and development agency under the Ministry of Economy, Trade and Industry (METI).
This funding will drive the development of NovaEdge — a next-generation, energy-efficient edge AI chiplet designed for high-performance generative AI inference and on-device learning. This solution aims to significantly enhance computational and power efficiency in edge computing environments, while also ensuring adaptability to the rapidly evolving AI model landscape, according to a media release.
The NovaEdge AI chiplet platform builds upon EdgeCortix’s innovative Dynamic Neural Accelerator (DNA) architecture, integrating their latest generation of programmable AI processor with RISC-V-based general-purpose processing in a highly energy-efficient, scalable form factor.
Paired with an enhanced version of the company’s MERA compiler and software framework, NovaEdge will enable seamless model optimization, rapid deployment, and real-time on-device learning capabilities. The platform will be developed using TSMC’s technology node, targeting mass production at the Japan Advanced Semiconductor Manufacturing (JASM) facility in Kumamoto, in the future, the media release said.
Combined with a previous 4 billion Yen project from NEDO in November 2024 to develop energy-efficient AI chiplets for post-5G communication systems, EdgeCortix has now secured a total of 7 billion Yen (approximately USD 49 million) in Japanese government-backed R&D support.
“NovaEdge represents a major leap forward, enabling robust, adaptable, and real-time generative AI capabilities directly at the edge,” said Sakyasingha Dasgupta, Founder & CEO of EdgeCortix. “This milestone strengthens our mission to drive domestic fabless semiconductor innovation and deliver real-world impact across critical sectors, including robotics, autonomous systems, healthcare, smart manufacturing, space and security.”
