Design an Optimized Compiler to Enhance Performance of Android Applications

Dahdouh, Marwa; Ayman, Mouhamad; Khawatmi, Souheil; Bouchi, A.

doi:10.5120/ijca2019919709

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed optimized algorithm of Smali instructions is based on replacing high execution time instructions with lower execution time instructions [18]. Android applications are written and the optimized compiler is applied to generate corresponding Smali code [19]. Special structures are proposed to be adopted in the designing of the compiler.…”

Section: Smali Code Optimizationmentioning

confidence: 99%

Programmatic Effect of Optimized Smali Code on Saving Energy of Android Applications

Dahdouh¹,

Bouchi²,

Khawatmi³

et al. 2020

IJCA

Self Cite

View full text Add to dashboard Cite

This paper presents the effect of saving Android application execution time on saving energy consumed by optimized applications. An algorithm for optimizing instructions on a Smali code-level proposes to provide execution time. The Smali optimization algorithm relies on replacing high execution times instructions with lower execution times ones and equivalent in behavior. MySMALI compiler is designed to support the proposed optimization algorithm and applied on Android applications. Optimized APK files are generated for optimized applications. Measurements of APKs execution times are taken. Measurements prove that the percentage of optimization in execution time is approximately 26.27%. The paper provides code-level estimates of the energy consumption of Android applications. A programmatic method about reading operating system files is applied to determine resource consumption by the applications. Energy measurements are also recorded by a power monitor (PowerTutor) for Android-based mobile platforms. The measurements of resources (Memory, CPU, Disk) consumption prove that the optimized compiler helps to save the consumption percentage of Android applications about 19.9%. The memory consumed is provided by the optimized compiler to approximately 20000 Kbyte and 31.7 KB size of files. The time that the optimized process of application consumes from the CPU time is reduced from 26% to 5%. The results demonstrate that the providing execution times of applications can save energy consumed to approximately 8.4%, and can save the power consumption by up to 14%.

show abstract

Section: Smali Code Optimizationmentioning

confidence: 99%