Lattice reference designs bring intelligence to the edge
June 29, 2017
Reference designs from Oregon-based Lattice Semiconductor can help accelerate the development of products for LoRa communications.
Based on the firm’s iCE40 UltraPlus FPGA devices, the reference designs support LoRa communications, elliptic curve cryptography (ECC) security, signal aggregation, machine learning and graphics acceleration.
With these reference designs, engineers are equipped with additional resources to accelerate the development of differentiated and innovative products. The iCE40 UltraPlus is suitable for offloading power hungry application processors in battery-powered devices.
“The new iCE40 UltraPlus solutions underscore our commitment to continuously provide our customers with updated resources for designing solutions for new markets quickly,” said CH Chee, senior director of marketing at Lattice Semiconductor. “With improved DSP performance, flexible IOs and increased memory for buffering, the iCE40 UltraPlus brings added intelligence to smartphones and IoT edge products, and security to the cloud.”
Built on existing IP and paired with the reference designs, the iCE40 UltraPlus anchors a complete system for enabling sensor-to-cloud security and acceleration at the edge. It is suitable for performing functions such as data capturing, aggregation, encryption, processing and transmission. Key applications include machine learning and on-device artificial intelligence. Trained neural network algorithms are used for always-on, low power human face detection using a low resolution image sensor.
It supports always on graphics such as clocks in mobile and wearable device displays at low power while the application processor is dormant. On security, it encrypts sensor data before transmission to the cloud or sets up an authenticated communications protocol between two systems. And it can control a LoRa compatible radio to send processed sensor data kilometres away.
“IoT edge devices demand energy efficient, always-on sensor functionality, and Lattice’s low power and high performance FPGAs have demonstrated that they can meet the connectivity and processing needed for these advanced applications,” said Terry Moore, CEO at MCCI. “By using the iCE40 UltraPlus with our LoRa design stack, we can support various anomaly detection techniques for always-on security in battery powered applications.”
Ulli Mueller, vice president at Think Silicon, added: “To meet mobile product requirements of always-on sensor functionality, while conserving power consumption, we looked for the smallest, lowest power and lowest cost FPGA device to complement our designs. By integrating the iCE40 UltraPlus FPGA with our NEMA|dc display processor technology, we enable graphic acceleration for always-on displays in wearables and other mobile and embedded display devices.”
And Guy Lemieux, CEO at VectorBlox, said: “FPGAs are ideal for AI and machine learning applications at the edge due to their parallel processing architecture. Our binarised neural network implemented in Lattice’s iCE40 UltraPlus FPGA supports face detection in always-on cameras for smart homes, security and other mobile devices.”