SamurAI: A 1.7MOPS-36GOPS Adaptive Versatile IoT Node with 15,000× Peak-to-Idle Power Reduction, 207ns Wake-Up Time and 1.3TOPS/W ML Efficiency
Ivan Miro-Panades, Benoît Tain, Jean‐Frédéric Christmann, David Coriat, Romain Lemaire, C. Jany, Baudouin Martineau, Fabrice Chaix, Anthony Quelen, Emmanuel Pluchart, Jean-Philippe Noël, Réda Boumchedda, Adam Makosiej, Maxime Montoya, Simone Bacles-Min, David Briand, Jean‐Marc Philippe, Alexandre Valentian, Frédéric Heitzmann, Édith Beigné, Fabien Clermidy
Abstract
IoT node application requirements are torn between sporadic data-logging and energy-hungry data processing (e.g. image classification). This paper presents a versatile IoT node covering this gap in processing and energy by leveraging two on-chip sub-systems: a low power, clock-less, event-driven Always-Responsive (AR) part and an energy-efficient On-Demand (OD) part. The AR contains a 1.7MOPS event-driven, asynchronous Wake-up Controller (WuC) with 207ns wake-up time optimized for short sporadic computing. OD combines a deep-sleep RISC-V CPU and 1.3TOPS/W Machine Learning (ML) and crypto accelerators for more complex tasks. The node can perform up to 36GOPS while achieving 15,000× reduction from peak-to-idle power consumption. The interest of this versatile architecture is demonstrated with 105μW daily average power on an applicative classification scenario.