SPELLing out energy leaks: Aiding developers locate energy inefficient code

Abstract

Although hardware is generally seen as the main culprit for a computer's energy usage, software too has a tremendous impact on the energy spent. Unfortunately, there is still not enough support for software developers so they can make their code more energy-aware.This paper proposes a technique to detect energy inefficient fragments in the source code of a software system. Test cases are executed to obtain energy consumption measurements, and a statistical method, based on spectrumbased fault localization, is introduced to relate energy consumption to the source code. The result of our technique is an energy ranking of source code fragments pointing developers to possible energy leaks in their code. This technique was implemented in the SPELL toolkit.Finally, in order to evaluate our technique, we conducted an empirical study where we asked participants to optimize the energy efficiency of a software system using our tool, while also having two other groups using no tool assistance and a profiler, respectively. We showed statistical evidence that developers using our technique were able to improve the energy efficiency by 43% on average, and even out performing a profiler for energy optimization.

Does maintainability relate to the energy consumption of software? A case study

“…Jelschen et al (2012), for their part, expose that some reengineering techniques improve the energy efficiency of mobile applications. Pereira et al (2020) propose a spectrum-based energy leak detection technique to identify inefficient energy consumption in the source code of software systems. This technique uses a statistical method to associate the energy consumed with the different components of the source code of a software system, thus drawing the developer's attention to the most critical red points in his code.…”

On energy debt

“…For example, for Android energy analysis there is eCalc [10], vLens [15], eProf [22], or Trepn [12,13]. Nevertheless, there is evidence that relying only on profilers and measuring tools are not enough to locate efficiency problems [23]. There is also work in automatic tools to help detect energy greedy code spots [23], refactoring for the most energy efficient data structure [26], or refactoring energy greedy Android patterns [5,8].…”

“…Nevertheless, there is evidence that relying only on profilers and measuring tools are not enough to locate efficiency problems [23]. There is also work in automatic tools to help detect energy greedy code spots [23], refactoring for the most energy efficient data structure [26], or refactoring energy greedy Android patterns [5,8]. These works, however, do not yet translate their potential gains across a period of time into the actual energy savings a developer or business can have on the software by applying such transformations.…”

Energy wars - Chrome vs. Firefox

“…What users do not currently consider, due to the lack of information, is the energy efficiency of the browsers. While many might assume speed directly equates energy efficiency, there are several research works showing this is in fact not always direct [1,5,19,20]. According to statcounter 3 and w3schools 4 , the most used browsers are Google Chrome and Mozilla Firefox, therefore, we decided to compare these two browsers.…”