partner-offering-banner.png

INTERA EAGLE Cognit Edge AI Accelerator IP

INTERA Group

Member

INTERA Eagle Cognit is an ultra-low-power, near-memory AI accelerator IP designed to deliver maximum performance-per-watt for advanced TinyML and Edge AI applications. Its innovative near-memory computing architecture accelerates matrix-vector operations while minimizing latency, silicon area, and memory footprint. Featuring a scalable configuration of 4 to 16 processing elements, tested up to 32, and configurable 2- to 32-bit precision, Eagle provides flexibility for diverse AI workloads. Its energy-efficient, always-on capabilities make it ideal for battery-powered devices, intelligent sensors, and applications requiring local processing, data privacy, and sovereignty. Supported by INTERA’s open-source software suite and development tools, Eagle enables seamless deployment of classical and spiking neural networks across industrial, healthcare, security, and smart sensing applications.

Features • Near-Memory Computing Architecture – Minimizes data movem...

INTERA Eagle Cognit is an ultra-low-power, near-memory AI accelerator IP designed to deliver maximum performance-per-watt for advanced TinyML and Edge AI applications. Its innovative near-memory computing architecture accelerates matrix-vector operations while minimizing latency, silicon area, and memory footprint. Featuring a scalable configuration of 4 to 16 processing elements, tested up to 32, and configurable 2- to 32-bit precision, Eagle provides flexibility for diverse AI workloads. Its energy-efficient, always-on capabilities make it ideal for battery-powered devices, intelligent sensors, and applications requiring local processing, data privacy, and sovereignty. Supported by INTERA’s open-source software suite and development tools, Eagle enables seamless deployment of classical and spiking neural networks across industrial, healthcare, security, and smart sensing applications.

Features • Near-Memory Computing Architecture – Minimizes data movement to improve AI processing efficiency. • Ultra-Low-Power AI Acceleration – Optimized for energy-efficient Edge AI and TinyML applications. • Matrix-Vector Acceleration (MxV) – Dedicated hardware acceleration for neural network computations. • Scalable Processing Architecture – Supports 4 or 16 processing elements (PEs), tested up to 32 banks/PEs. • Configurable Numerical Precision – Supports 2-bit to 32-bit implementations. • Always-On AI Processing – Enables continuous, low-power intelligence. • Compact Silicon Footprint – Small near-memory AI engine designed for embedded SoC integration. • Low-Latency Inference – Supports fast, real-time AI processing at the edge. • Neuromorphic AI Support – Optimized for Spiking Neural Networks (SNNs), with native support for sparsity. • Multiple Neural Network Models – Supports CNN, LSTM, MLP/FCNN and SNN workloads. • AI Framework Compatibility – Supports TensorFlow, TensorFlow Lite, Keras, PyTorch, ONNX, snnTorch and NIR through its software toolchain. • Integrated Development Ecosystem – Includes software SDK, dataflow compiler, documentation and development resources. • Edge Data Privacy and Sovereignty – Enables local AI inference without relying on cloud processing. • Excellent Cost-to-Performance Ratio – Designed to maximize AI computational efficiency while minimizing silicon and memory requirements.

View Partner Website Right arrow Right arrow Partner Product Page Right arrow Right arrow Contact Now

Key Features

  • • Near-Memory Computing Architecture – Minimizes data movement to improve AI processing efficiency. • Ultra-Low-Power AI Acceleration – Optimized for energy-efficient Edge AI and TinyML applications. • Matrix-Vector Acceleration (MxV) – Dedicated hardware acceleration for neural network computations. • Scalable Processing Architecture – Supports 4 or 16 processing elements (PEs), tested up to 32 banks/PEs. • Configurable Numerical Precision – Supports 2-bit to 32-bit implementations. • Always-On AI Processing – Enables continuous, low-power intelligence. • Compact Silicon Footprint – Small near-memory AI engine designed for embedded SoC integration. • Low-Latency Inference – Supports fast, real-time AI processing at the edge. • Neuromorphic AI Support – Optimized for Spiking Neural Networks (SNNs), with native support for sparsity. • Multiple Neural Network Models – Supports CNN, LSTM, MLP/FCNN and SNN workloads. • AI Framework Compatibility – Supports TensorFlow, TensorFlow Lite, Keras, PyTorch, ONNX, snnTorch and NIR through its software toolchain. • Integrated Development Ecosystem – Includes software SDK, dataflow compiler, documentation and development resources. • Edge Data Privacy and Sovereignty – Enables local AI inference without relying on cloud processing. • Excellent Cost-to-Performance Ratio – Designed to maximize AI computational efficiency while minimizing silicon and memory requirements.

Offering Brief

Offering Brief

Device Family Agilex® 3 FPGA C-Series, Agilex® 5 FPGA D-Series, Agilex® 5 FPGA E-Series, Agilex® 7 FPGA F-Series, Agilex® 7 FPGA I-Series, Agilex® 7 FPGA M-Series, Agilex® 9 FPGA Direct RF-Series, Arria® 10 GT FPGA, Arria® 10 GX FPGA, Arria® 10 SX FPGA, Cyclone® 10 GX FPGA, Cyclone® 10 LP FPGA, Cyclone® IV E FPGA, Cyclone® V GT FPGA, Cyclone® V GX FPGA, Cyclone® V SE FPGA, Cyclone® V ST FPGA, Cyclone® V SX FPGA, Stratix® 10 AX FPGA, Stratix® 10 GX FPGA, Stratix® 10 MX FPGA, Stratix® 10 SX FPGA, Stratix® 10 TX FPGA, Stratix® IV GX FPGA
Offering Status Production
Demo Yes
Design Examples Available Yes
Latest Quartus Version Supported 25.1.2
OS Support INTERA Eagle Cognit is an IP Core (Not a standalone board with its OS)
Development Language C/C++, Encrypted Verilog, Encrypted VHDL, Verilog, VHDL

1. Core Product: Eagle Cognit AI Acceleration IP • AI acceleration Intellectual Property (IP) core. • Optimized for ultra-low power (ULP) inference. • Supports common neural network types: FC, DNN, MLP, CNN, and LSTM. • Integrates into FPGA, ASIC, and SoC designs. 2. Hardware Support • Available on FPGA Dev Boards and INTERA Dev Boards. • Can be used as a daughter board or integrated into custom SoC. 3. Software Suite (Comprehensive & Open-Source) • SDK (Software Development Kit) / Starter Development Kit. • Seamless interoperability with popular deep learning frameworks (Keras, TensorFlow, etc.). • Model Build Environment + Automated Profiling. • Runtime Environment + Firmware. • Demo applications and user guides. • Support for custom and user-provided models.

Ordering Information

EAGLE FPGA 002

from https://intera-group.webflow.io/contact

Get Pricing and Availability

Documentation & Resources

design hub icon Eagle Demo

Market Segment and Sub-Segments

Robotics-252x228

Industrial

View Sub-Segments

Industrial

Energy

Back to Market
Medical-Video-and-Vision-252x228

Medical

View Sub-Segments

Medical

Non-Imaging Patient Devices

Back to Market