Exploiting half-wits: smarter storage for low-power devices
Mastooreh Salajegheh, Yue Wang, Kevin Fu, Anxiao Andrew Jiang, Erik Learned-Miller · ScholarWorks@UMassAmherst (University of Massachusetts Amherst) · 2011
This work analyzes the stochastic behavior of writing to embedded flash memory at voltages lower than recom-mended by a microcontroller’s specifications to reduce energy consumption. Flash memory integrated within a microcontroller typically requires the entire chip to op-erate on common supply voltage almost double what the CPU portion requires. Our approach tolerates a lower supply voltage so that the CPUmay operate in a more en-ergy efficient manner. Energy efficient coding algorithms then cope with flash memory that behaves unpredictably. Our software-only coding algorithms (in-place writes, multiple-place writes, RS-Berger codes) enable reliable storage at low voltages on unmodified hardware by ex-ploiting the electrically cumulative nature of half-written data in write-once bits. For a sensor monitoring applica-tion using the MSP430, coding with in-place writes re-duces the overall energy consumption by 34%. In-place writes are competitive when the time spent on computa-tion is at least four times greater than the time spent on writes to flash memory. Our evaluation shows that tightly maintaining the digital abstraction for storage in embed-ded flash memory comes at a significant cost to energy consumption with minimal gain in reliability. 1