Abstract
In modern energy harvesting sensor nodes, nonvolatile SRAM (nvSRAM) has been widely investigated as a promising on-chip memory architecture because of its zero standby power, resilience to power failures, and fast read/write operations. However, conventional approaches transfer all data from SRAM into NVM during the backup process. Thus, large on-chip energy storage capacitors are normally required. In addition, high peak inrush current is generated instantaneously, which has a negative impact on energy efficiency and circuit reliability. To mitigate these problems, we propose a novel holistic backup flow, which consists of a partial backup process and a run-time pre-writeback scheme for nvSRAM based caches. A statistics based dead-block predictor is employed to achieve a fast and low power partial backup process. We also present an adaptive pre-writeback point allocation strategy to further reduce the backup load. Simulation results show that, with our proposed backup scheme, energy storage capacitance is reduced by 34% and inrush current is reduced by 54% on average compared to the conventional full backup scheme. © 2015 EDAA.