NESL Technical Report #: 2014-4-3
Abstract: Increasing hardware variability in newer integrated circuit fabrication technologies has caused corresponding power variations on a large scale. These variations are particularly exaggerated for idle power consumption, motivating the need to mitigate the effects of variability in systems whose operation is dominated by long idle states with periodic active states. In systems where computation is severely limited by anemic energy reserves and where a long overall system lifetime is desired, maximizing the quality of a given application subject to these constraints is both challenging and an important step towards achieving high quality deployments. This work describes VaRTOS, an architecture and corresponding set of operating system abstractions that provide explicit treatment of both idle and active power variations for tasks running in real time operating systems. Tasks in VaRTOS express elasticity by exposing individual knobs--shared variables that the operating system can tune to adjust task quality and correspondingly task power, maximizing application utility both on a per-task and system-wide basis. We provide results regarding online learning of instance-specific sleep power, active power, and task-level power expenditure on simulated hardware with demonstrated effects for several prototypical applications. Our results show that VaRTOS can reduce variability-induced energy expenditure errors from over 70% in many cases to under 2% in most cases and under 5% in the worst-case.
Publication Forum: Transactions on Embedded Computing Systems
Page (Count): 25
NESL Document?: Yes
Document category: Journal Paper