.webp){kind=small}
About INTERA Group
Program Level
Member
Certified Engineers
35
Languages
Arabic, English, French, German, Russian, Spanish
INTERA is an Edge Computing Systems Company focused on advanced semiconductor IP for high-performance, energy-efficient AI processing at the edge. Our core business is the development and licensing of scalable AI computing architectures and acceleration engines including Neural Processing Units (NPUs), dedicated AI accelerators, and neuromorphic hardware blocks for seamless integration into SoCs and embedded devices. With a strong focus on TinyML and embedded AI, our technology enables real-time, on-device inference in resource-constrained, battery-powered, and always-on systems. INTERA solutions combine optimized hardware IP with supporting software stacks compilers, SDKs, runtime frameworks, and model-optimization toolchains to deliver superior computing performance, ultra-low power consumption, reduced memory footprint, smaller silicon area, lower latency, and high integration flexibility. Our technologies address applications across manufacturing, energy, healthcare, logistics, IoT, robotics, smart infrastructure, and defense.
Headquarters: Sabino Arana #14, 2do., Barcelona, Catalunya, 08028, Spain
Barcelona #1
Offering Type
Acceleration / AI / Cloud
Design Services
Intellectual Property (IP)
Software / OS / RTOS
System Integrator / Provider
Offerings
INTERA Eagle Cognit is an ultra-low-power near-memory AI accelerator IP optimized for TinyML and Edge AI, delivering high performance-per-watt with a scalable 4–16 (tested to 32) PE design and 2–32-bit precision. It enables energy-efficient, always-on inference for battery-powered and privacy-sensitive devices, supported by INTERA’s open-source tools for classical and spiking neural networks.
INTERA Harrier Cognit is a high-throughput AI accelerator IP with a monolithic streaming architecture optimized for matrix-matrix operations, delivering high-speed, energy-efficient inference for demanding Edge AI and TinyML workloads. Its scalable PE arrays (from 8×8 up to 64×64) and ultra-low-power design suit industrial systems, sensing, predictive maintenance, and security, backed by INTERA’s open-source tools for seamless neural network deployment.
INTERA Falcon Cognit is an ultra-low-power AI accelerator IP designed to deliver high-performance TinyML inference in resource-constrained edge devices. Featuring a compact, memory-mapped, monolithic streaming architecture optimized for matrix-vector operations, Falcon combines low latency, minimal silicon footprint, and exceptional energy efficiency. It’s always-on capabilities make it ideal for battery-powered devices and near-sensor AI applications. Supporting configurable 2- to 32-bit implementations, Falcon enables flexible integration into intelligent semiconductor systems. Combined with INTERA’s open-source software tools and development frameworks, it accelerates AI deployment across industrial, healthcare, security, and smart sensing applications.
Market Segment and Sub-Segments
Aerospace
View Sub-Segments
ASIC Proto
View Sub-Segments
Industrial
View Sub-Segments
Medical
View Sub-Segments