Reducing programmer burden in task-based intermittent computing development
M.A. van Eerden (TU Delft - Electrical Engineering, Mathematics and Computer Science)
P. Pawelczak – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
J.G.H. Cockx – Graduation committee member (TU Delft - Electrical Engineering, Mathematics and Computer Science)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Wireless sensors are used in many critical application field such as agriculture, healthcare and transportation. Such sensors often use batteries, which have a limited lifespan and contribute to environmental damage in the form of waste. Batteryless sensors solve these problems, but come with their own challenges; they frequently experience power failures because their energy storage is limited. To make sure the system can make forward progress, Intermittent Computing (ImC) techniques are used to back up the system state before the power fails. One such technique consists of splitting the program up into tasks, and backing up the system state after a task has fully executed. Such a task-based approach requires a non-standard programming model, often with many keywords that need to be inserted manually. This increases the burden on the programmer, moving focus to inserting the right keyword at the right time and not forgetting anything, instead of focusing on the things that really matter. To solve this problem, this work Code Instrumentation for Task-based Intermittent computing Development (CITID), a compileand runtime ImC system that reduces the programmer effort of a state-of-the-art task-based ImC system by removing up to 96% of necessary manually placed keywords, while insignificantly affecting performance in most cases.