Lattice sensAIā„¢ Solution Stack

Accelerate Integration of Flexible, Low Power Inferencing at the Edge

Lattice sensAI is an AI/ML solution stack designed for low-power, small-footprint FPGA-based artificial intelligence (AI) and machine learning (ML) applications, primarily at the far-edge near-sensor devices. It provides a combination of FPGA hardware, software tools, and IP cores to enable AI inferencing on embedded systems.
sensAI Stack

 

Key Features of sensAI:

  1. Optimized for Low Power & Low Latency next to the sensor
    • Designed to run AI/ML workloads efficiently on Lattice’s low-power FPGAs (like CrossLink-NX, Certus-NX, and Nexus-based devices).
    • Ideal for always-on and real-time AI processing.
  2. Production-Ready End Use-Case and Applications
    • Accelerate time-to-market with a growing library of validated use-cases and applications, reducing development risk and enabling quick deployment in real-world scenarios.
  3. Pre-Optimized IP Cores & Reference Designs
    • Comes with pre-optimized neural network IP cores for functions like face detection, object recognition, anomaly detection, and gesture control.
    • Helps accelerate development time for AI applications.
  4. Toolchain: Lattice sensAI Studio
    • Provides an end-to-end AI development environment, integrating model training, optimization, compilation, and FPGA deployment.
    • Supports hardware/software co-design, allowing users to fine-tune models for specific use cases.
  5. SDK: Lattice sensAI Edge Vision Engine
    • The SDK and experience visualization tool enable next-generation Human-Machine Interface (HMI) applications with advanced computer vision capabilities in FPGA, ARM, or x86 platforms.

Jump To

System Architecture

The diagram below shows how an FPGA is typically utilized to power AI and machine learning solutions near sensors. Lattice FPGAs offer robust and scalable AI/ML solutions that are simple, low-power, and compact. Scroll down to explore hardware demonstrations that you can download and evaluate today.

Pre-processor: Lattice FPGA AI Accelerator

  • Reduce System Power and Latency
    • Offload AI inferencing from the host SoC to the FPGA to enable real-time decision-making with minimal energy consumption.
  • Enable Always-On Intelligence at the Edge
    • Keep AI processing close to the sensor, enabling continuous, context-aware operation without relying on high-power computing.
  • Optimize Bandwidth and System Efficiency
    • Pre-process and filter sensor data locally, sending only meaningful results to the host—reducing data transfer and overall system load.

Software Tools

  • Lattice sensAI Studio – an intuitive development environment that streamlines the creation, optimization, compilation, and deployment of AI models onto low-power edge FPGA devices.
  • Lattice sensAI Edge Vision Engine – production-ready AI/ML for FPGAs, PCs, and ARM, enabling advanced computer vision end-use-cases and applications.

Videos

Gesture & Gaze
Expand Video

Gesture & Gaze

This demo showcases the AI capabilities that Lattice sensAIā„¢ will enable on future Lattice FPGAs, focusing on gesture and gaze tracking.
sensAI Studio
Expand Video

Lattice sensAIā„¢ Studio

In this demo, users can explore the latest tools from Lattice. They will have the opportunity to run examples for FPGA simulation, neural network training, and compilation for specific devices.
Lattice Avantā„¢ Launch Event – Dec. 5, 2022
Expand Video

Lattice Avantā„¢ Launch Event – Dec. 5, 2022

On Dec. 5, 2022, Lattice unveiled Lattice Avant, a new FPGA platform purpose-built to bring the company’s power efficient architecture, small size, and performance leadership to mid-range FPGAs, offering best-in-class power efficiency, advanced connectivity, and optimized compute. Watch the livecast replay to experience the next level of FPGA innovation.
 Lattice sensAI: Making PCs smarter and more aware
Expand Video

Lattice sensAI: Making PCs smarter and more aware

Lattice sensAI smart vision sensing technology tracks the user's attention while using their device making PCs smarter and more aware of their surroundings than ever before, by combining the built-in camera with machine learning models running on Lattice’s industry-leading low power FPGAs.
Lattice sensAI: Protecting your PC with onlooker detection
Expand Video

Lattice sensAI: Protecting your PC with onlooker detection

Lattice sensAI vision sensing technology is designed to help protect PC users from visual hackers by warning the user with an on-screen alert, or automatically turning on privacy screen settings, when enabled.
Lattice sensAI: Better collaboration with face framing technology
Expand Video

Lattice sensAI: Better collaboration with face framing technology

Lattice sensAI vision sensing technology helps to keep PC users in frame, even while shifting positions, and understands when new team members enter the frame and automatically refocuses to accommodate them.
Lattice FAD sensAI
Expand Video

Lattice sensAI: accelerating low power AI at the edge

The full-featured Lattice sensAI stack includes everything developers need to evaluate, develop and deploy FPGA-based Machine Learning / Artificial Intelligence solutions - modular hardware platforms, example demonstrations, reference designs, neural network IP cores, software tools for development, and custom design services.

Reference Designs

Object Classification Reference Design

Reference Design

Object Classification Reference Design

The Object Classification reference design shows examples on implementing machine-learning based object classification to edge devices applications.
Object Classification Reference Design
Hand Gesture Detection

Reference Design

Hand Gesture Detection

Implements a low power AI based system to detect hand gestures using an IR image sensor
Hand Gesture Detection
Barcode Detection Reference Design

Reference Design

Barcode Detection Reference Design

Exhibits the barcode detection using CertusPro-NX Voice & Vision Machine Learning Board & its camera barcode detection potential based on Yolov5 NN models.
Barcode Detection Reference Design
Scene Segmentation Reference Design

Reference Design

Scene Segmentation Reference Design

Efficient and low power approach for implementing scene segmentation using Lattice CrossLink-NX FPGA
Scene Segmentation Reference Design
Key Phrase Detection

Reference Design

Key Phrase Detection

Continuous searches for a key phrase utterance via a digital MEMS microphone. Can be re-configured to work with any trained word or phrase.
Key Phrase Detection

Demos

Object Classification Demonstration

Demo

Object Classification Demonstration

This object classification demo provides a sample application for detecting, classifying, and tracking multiple objects running on CertusPro-NX FPGA.
Object Classification Demonstration
User Tracking and Onlooker Detection Demonstration

Demo

User Tracking and Onlooker Detection Demonstration

Sample demonstration for detection and tracking of multiple human faces running on a low power general purpose FPGA using CNN Model
User Tracking and Onlooker Detection Demonstration
Barcode Detection Demonstration

Demo

Barcode Detection Demonstration

This demo implements an algorithm for barcode detection using the CertusPro-NX Voice and Vision Machine Learning Board.
Barcode Detection Demonstration
Human to Machine Interfacing Demonstration

Demo

Human to Machine Interfacing Demonstration

Human-to-machine interface demo uses FPGA-accelerated NN models for detecting, positioning, and identifying persons.
Human to Machine Interfacing Demonstration
Key Phrase Detection

Demo

Key Phrase Detection

Uses artificial intelligence (AI) to detect a specific key-phrase using a tiny, low-power iCE40 UltraPlus FPGA
Key Phrase Detection

Development Kits & Boards

CrossLink-NX Voice and Vision Machine Learning Board

Board

CrossLink-NX Voice and Vision Machine Learning Board

Designed for low-power machine learning applications with Lattice sensAI and CrossLink-NX. Includes image sensors, microphones, HyperRAM, and expansion ports.
CrossLink-NX Voice and Vision Machine Learning Board
CrossLink-NX-33 Voice and Vision Machine Learning Board

Board

CrossLink-NX-33 Voice and Vision Machine Learning Board

CrossLink-NX-33 Voice and Vision Machine Learning Board is designed using Crosslink-NX 33K, ideal for machine learning applications.
CrossLink-NX-33 Voice and Vision Machine Learning Board
CertusPro-NX Voice and Vision Machine Learning Board

Board

CertusPro-NX Voice and Vision Machine Learning Board

Design AI use cases for the Edge quickly! This board along with the Lattice sensAI solution stack provide the tools for developing vision and audio-based AI applications.
CertusPro-NX Voice and Vision Machine Learning Board
HM01B0 UPduino Shield

Board

HM01B0 UPduino Shield

A complete development kit for implementing Artificial Intelligence (AI) using vision and sound as sensory inputs to a low-cost, low-power iCE40 UltraPlus FPGA.
HM01B0 UPduino Shield

IP Cores

Advanced CNN Accelerator IP

IP Core

Advanced CNN Accelerator IP

Calculates full layers of Neural Network including convolution layer, pooling layer, batch normalization layer, and fully connected layer.
Advanced CNN Accelerator IP
CNN Plus Accelerator IP Core

IP Core

CNN Plus Accelerator IP Core

CNN Plus IP is a flexible accelerator IP that simplifies implementation of Ultra-Low power AI by leveraging capabilities of Lattice FPGAs.
CNN Plus Accelerator IP Core
Convolutional Neural Network (CNN) Accelerator IP

IP Core

Convolutional Neural Network (CNN) Accelerator IP

Implement AI solutions with CNNs from common or custom networks. Configure up to 16-bit widths. Works with Lattice Neural Network Compiler software tool.
Convolutional Neural Network (CNN) Accelerator IP
Convolutional Neural Network (CNN) Compact Accelerator

IP Core

Convolutional Neural Network (CNN) Compact Accelerator

Implement AI solutions with CNNs or BNNs that have power consumption in the mW range. Works with Lattice Neural Network Compiler software tool.
Convolutional Neural Network (CNN) Compact Accelerator
CNN Co-Processor Accelerator IP

IP Core

CNN Co-Processor Accelerator IP

A CNN co-processor accelerator engine for use with low power Lattice FPGAs. The engine can be used with a RISC-V processor to create an SOC and implement TF Lite-based acceleration applications that leverage the parallel compute and distributed resource capabilities of Lattice FPGAs.
CNN Co-Processor Accelerator IP

Custom Design Services

The Lattice sensAI stack includes an ecosystem of select, worldwide design service partners that can deliver custom solutions for a range of end-applications, including mobile, smart home, smart city, smart factory, and smart cars. Click here for more information on Lattice sensAI certified partners.

Documentation

Information Resources
TITLE NUMBER VERSION DATE FORMAT SIZE
Select All
Lattice sensAI Stack Product Brochure
I0265 8.0 4/4/2025 PDF 914.3 KB
TITLE NUMBER VERSION DATE FORMAT SIZE
Select All
Lattice SensAI 4.1: Tools and IP Transform Low-Power FPGAs into Intelligent AI/ML Edge Computing Engines
1.0 11/10/2021 PDF 766.4 KB
Rising Edge AI Requirements Demand Higher Performance Solution
WP-0019 1.0 8/17/2019 PDF 1.1 MB
Bringing Laptops Into the 2020s
WP0024 2.0 7/1/2020 PDF 723.4 KB
Accelerating Implementation of Low Power Artificial Intelligence at the Edge
WP-0014 1.1 11/28/2018 PDF 1.2 MB
Harnessing the Power of AI: An Easy Start with Lattice’s sensAI
WP-0017 1.0 1/31/2019 PDF 2.3 MB

*By clicking on the "Notify Me of Changes" button, you agree to receive notifications on changes to the document(s) you selected.

Awards

The Electronics Industry Awards 2019

Internet of Things Product of the Year

EDN Hot 100 Product Award

Tools & Development

AI Breakthrough Award

Best AI-Based Solution for Engineering

Assodel Award 2019

Best Industrial and Automotive Related Hardware Product

China Electronic Market 2018 Editor's Choice Awards

Most Competitive FPGA Product