Lattice introduce their latest edge computing solution for always-on, on-device AI

26 September 2018

Credit: Shutterstock
Credit: Shutterstock

Lattice Semiconductor Corporation have expanded the company’s popular AI integration solutions, known collectively as the Lattice sensAI stack, designed to further speed developers' time-to-market for flexible consumer and IIoT machine learning.

Lattice expands its ultra-low power sensAI stack with optimised solutions for always-on, on-device artificial intelligence convolutional neural networking (CNN) accuracy with flexible milliwatt field programmable gate arrays (FPGA/s) solutions. This paves the way for many accomplishments in AI, such as new reference designs for human presence and hand gesture recognition, and all with scalable performance and power.

Building on the ultra-low power (1 mW to 1 W) focus of the sensAI stack, Lattice is releasing new IP cores, reference designs, demos and hardware development kits that provide scalable performance and power for always-on, on-device AI applications.

Said Deepak Boppana, senior director, Product and Segment Marketing, at Lattice Semiconductor: “Flexible, low-power, always-on, on-device AI is increasingly a requirement in edge devices that are battery-operated or have thermal constraints.

“The new features of the sensAI stack are optimised to address this challenge, delivering improved accuracy, scalable performance, and ease-of-use, while still consuming only a few milliwatts of power. With these enhancements, sensAI solutions can now support a variety of low-power, flexible system architectures for always-on, on-device AI.”

Examples of the architectural choices that sensAI solutions enable include the following aspects:

• Standalone iCE40 UltraPlus / ECP5 FPGA based always-on, integrated solutions, with latency, security, and form factor benefits

• Solutions utilising iCE40 UltraPlus as an always-on processor that detects key-phrases or objects, and wakes-up a high-performance AP SoC/ASIC (application-specific integrated circuit) for further analytics only when required, reducing overall system power consumption

• Solutions utilising the scalable performance/power benefits of ECP5 for neural network acceleration, along with input/output flexibility to seamlessly interface to on-board legacy devices, including sensors and low-end microcontrollers for system control

Credit: Shutterstock
Credit: Shutterstock

Updates to the sensAI stack

IP cores – New CNN Compact Accelerator IP core for improved accuracy on iCE40 UltraPlus FPGA, and enhanced CNN Accelerator IP core for improved performance on ECP5 FPGAs

Software tools – Updated neural network compiler tool with improved ease-of-use and both Caffe and TensorFlow support for iCE40 UltraPlus FPGAs

Reference designs – New human presence detection and hand gesture recognition reference designs and demos

Design Service Partners – New vehicle classification and package detection demos from sensAI Design Services Partners

The Lattice sensAI partner ecosystem continues to expand worldwide with new design service and IP partners who are focused on enabling smart home, smart factory, smart city, and smart car applications.

“Lattice’s low power, small size FPGAs and neural network IP cores and tools, will significantly accelerate adoption of artificial intelligence at the edge,” said Amit Vashi, chief operating officer, Softnautics  a sensAI Design Services partner.

“With our expertise in machine learning, we are proud to be working closely with Lattice to enable sensAI solution deployments."


Contact Details and Archive...

Print this page | E-mail this page