SYNtzulu: A Tiny RISC-V-Controlled SNN Processor for Real-Time Sensor Data Analysis on Low-Power FPGAs
Gianluca Leone, Matteo Antonio Scrugli, Lorenzo Badas, Luca Martis, Luigi Raffo, Paolo Meloni
Abstract
Spiking Neural Networks (SNNs) are energy- and performance-efficient tools that have been found to be very useful in AI applications at the edge. This paper introduces <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SYNtzulu</monospace>, an SNN processing element designed to be used in low-cost and low-power FPGA devices for near-sensor data analysis. The system is equipped with a RISC-V subsystem responsible for controlling the input/output and setting runtime parameters, thus increasing its flexibility. We evaluated the system, which was implemented on a Lattice iCE40UP5K FPGA, in various use cases employing SNNs with accuracy comparable to the state-of-the-art. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SYNtzulu</monospace> dissipates a maximum power of 12.05 mW when performing SNN inference, which can be reduced to an average of just 1.45 mW through the use of dynamic power management.