MaxTracker: Continuously Tracking the Maximum Computation Progress for Energy Harvesting ReRAM-based CNN Accelerators
- 17 September 2021
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 20 (5s), 1-23
- https://doi.org/10.1145/3477009
Abstract
There is an ongoing trend to increasingly offload inference tasks, such as CNNs, to edge devices in many IoT scenarios. As energy harvesting is an attractive IoT power source, recent ReRAM-based CNN accelerators have been designed for operation on harvested energy. When addressing the instability problems of harvested energy, prior optimization techniques often assume that the load is fixed, overlooking the close interactions among input power, computational load, and circuit efficiency, or adapt the dynamic load to match the just-in-time incoming power under a simple harvesting architecture with no intermediate energy storage. Targeting a more efficient harvesting architecture equipped with both energy storage and energy delivery modules, this paper is the first effort to target whole system, end-to-end efficiency for an energy harvesting ReRAM-based accelerator. First, we model the relationships among ReRAM load power, DC-DC converter efficiency, and power failure overhead. Then, a maximum computation progress tracking scheme (MaxTracker) is proposed to achieve a joint optimization of the whole system by tuning the load power of the ReRAM-based accelerator. Specifically, MaxTracker accommodates both continuous and intermittent computing schemes and provides dynamic ReRAM load according to harvesting scenarios. We evaluate MaxTracker over four input power scenarios, and the experimental results show average speedups of 38.4%/40.3% (up to 51.3%/84.4%), over a full activation scheme (with energy storage) and order-of-magnitude speedups over the recently proposed (energy storage-less) ResiRCA technique. Furthermore, we also explore MaxTracker in combination with the Capybara reconfigurable capacitor approach to offer more flexible tuners and thus further boost the system performance.Keywords
Funding Information
- NSFC (#61872251)
- Beijing Advanced Innovation Center for Imaging Technology, and NSF (#1629915, #1763681, #1822923 and #2008365)
This publication has 31 references indexed in Scilit:
- Alpaca: intermittent execution without checkpointsProceedings of the ACM on Programming Languages, 2017
- Self-Powered ZigBee Wireless Sensor Nodes for Railway Condition MonitoringIEEE Transactions on Intelligent Transportation Systems, 2017
- Self-Powered Multiparameter Health SensorIEEE Journal of Biomedical and Health Informatics, 2017
- Reconfigurable DC/DC Converter for Efficiency and Reliability OptimizationIEEE Journal of Emerging and Selected Topics in Power Electronics, 2017
- Maximum Energy Efficiency Tracking Circuits for Converter-Less Energy Harvesting Sensor NodesIEEE Transactions on Circuits and Systems II: Express Briefs, 2016
- ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in CrossbarsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- ISAACACM SIGARCH Computer Architecture News, 2016
- A 28 nm FDSOI Integrated Reconfigurable Switched-Capacitor Based Step-Up DC-DC Converter With 88% Peak EfficiencyIEEE Journal of Solid-State Circuits, 2015
- Ambient RF Energy Harvesting Sensor Device With Capacitor-Leakage-Aware Duty Cycle ControlIEEE Sensors Journal, 2013
- Energy Harvesting Sensor Nodes: Survey and ImplicationsIEEE Communications Surveys & Tutorials, 2010