VIDEO
EdgeCortix Looks To Chiplets For Third-Gen Reconfigurable AI Chip
Inside EdgeCortix’s vision for efficient AI inference, from SAKURA-II and space applications to next-generation chiplet architecture.
In this episode of AI with Sally, Sakya Dasgupta, Founder and CEO of EdgeCortix, joins Sally Ward-Foxton to discuss software-first AI inference, the architecture behind SAKURA-II, and what it takes to deliver high-performance, energy-efficient AI at the edge. They also dive into EdgeCortix’s work with NASA, space and aerospace applications, Japan’s semiconductor resurgence, and what’s ahead for the company’s next-generation platform.
EdgeCortix Edge AI Platform
Full-Stack Solution: Integrated Platform Increases Ecosystem Value Over Time
MERA Compiler and Framework
Industry first software platform enabling AI inference across heterogeneous systems
Unique Software
Unique Software
Dynamic Neural Accelerator® Technology
Flexible, run-time reconfigurable, highly-parallelized and efficient architecture
Proprietary Architecture
Proprietary Architecture
SAKURA®-II
AI Accelerator
AI Accelerator
High Performance, Low Power, Generative AI ready, effectively handles multi-billion parameter models
Efficient Hardware
Efficient Hardware
AI Accelerator
Modules and Cards
Modules and Cards
Up to 240 TOPS in systems
powered by the latest SAKURA-II
AI Accelerators
Deployable Systems
powered by the latest SAKURA-II
AI Accelerators
Deployable Systems