SamurAI: A Versatile IoT Node With Event-Driven Wake-Up and Embedded ML Acceleration
Authors:
- Ivan Miro-PanadesIvan Miro-Panades
- Jean-Frédéric ChristmannJCJean-Frédéric Christmann
- Romain LemaireRLRomain Lemaire
- Clément JanyCJClément Jany
- Baudouin MartineauBMBaudouin Martineau
- Fabrice ChaixFCFabrice Chaix
- Guillaume WaltenerGWGuillaume Waltener
- Emmanuel PluchartEPEmmanuel Pluchart
- Jean-Philippe NoelJNJean-Philippe Noel
- 2 September 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 58 (6) , 1782-1797
Abstract
Increased capabilities, such as recognition and self-adaptability, are now required from Internet-of-Things (IoT) applications. While IoT node power consumption is a major concern for these applications, cloud-based processing is becoming unsustainable due to continuous sensor or image data transmission over the wireless network. Thus, optimized ML capabilities and data transfers should be integrated into the IoT node. Moreover, IoT applications are torn between sporadic data-logging and energy-hungry data processing (e.g., image classification). Thus, the versatility of the node is key in addressing this wide diversity of energy and processing needs. This article presents SamurAI, a versatile IoT node bridging 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. AR contains a 1.7-MOPS event-driven, asynchronous Wake-up Controller (WuC) with a 207-ns wake-up time optimized for sporadic computing, while OD combines a deep-sleep RISC-V CPU and 1.3-TOPS/W machine learning (ML) for more complex tasks up to 36 GOPS. This architecture partitioning achieves the best-in-class versatility metrics, such as peak performance to idle power ratio. On an applicative classification scenario, it demonstrates system power gains, up to $3.5\times $ , compared to cloud-based processing, and, thus, extended battery lifetime.Keywords
All Related Versions
Funding Information
- WAKeMeUP project, which received funding from the Electronic Components and Systems for European Leadership Joint Undertaking in collaboration with the European Union’s (H2020)
- Framework Programme (H2020/2014-2020)
- National Authorities (Agreement 783176)
- SERENE-IoT (Penta (16004)
- MACS (FUI20) projects
This publication has 31 references indexed in Scilit:
- Computation offloading and resource allocation for low-power IoT edge devices2016
- Asynchronous Circuit Designs for the Internet of Everything: A Methodology for Ultralow-Power Circuits with GALS ArchitectureIEEE Solid-State Circuits Magazine, 2016
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- A Subthreshold ARM Cortex-M0+ Subsystem in 65 nm CMOS for WSN Applications with 14 Power Domains, 10T SRAM, and Integrated Voltage RegulatorIEEE Journal of Solid-State Circuits, 2015
- Asynchronous sub-threshold ultra-low power processor2015
- UTBB FDSOI technology flexibility for ultra low power internet-of-things applications2015
- A 460 MHz at 397 mV, 2.6 GHz at 1.3 V, 32 bits VLIW DSP Embedding F MAX TrackingIEEE Journal of Solid-State Circuits, 2014
- Scalable 0.35 V to 1.2 V SRAM Bitcell Design From 65 nm CMOS to 28 nm FDSOIIEEE Journal of Solid-State Circuits, 2014
- Architecture and Robust Control of a Digital Frequency-Locked Loop for Fine-Grain Dynamic Voltage and Frequency Scaling in Globally Asynchronous Locally Synchronous StructuresJournal of Low Power Electronics, 2011
- A 32 kb 10T Sub-Threshold SRAM Array With Bit-Interleaving and Differential Read Scheme in 90 nm CMOSIEEE Journal of Solid-State Circuits, 2009