Efficient profile-guided size optimization for native mobile applications

Lee, Kyung-Woo; Hoag, Ellis; Tillmann, Nikolai

doi:10.1145/3497776.3517764

Cited by 7 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and key scenarios [11]. Outlining [4, 8, 11, 15ś17] improves the code size by factoring out the common code into functions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Scalable size inliner for mobile applications (WIP)

Lee¹,

Ren²,

Nay³

2022

Proceedings of the 23rd ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems

Self Cite

View full text Add to dashboard Cite

Inlining is critical for both performance and size in mobile apps. When building large mobile apps, ThinLTO, a scalable link-time optimization is imperative in order to achieve both optimal size and build scalability. However, inlining with ThinLTO is not tuned to reduce the code size because each module inliner works independently without modeling the size cost across modules, and functions are often not eligible to import due to private references, appearing in Objective-C or Swift for iOS. This paper extends the bitcode summary to perform a global inlining analysis to find inline candidates for saving the code size. Using this summary information, a pre-inliner eagerly inlines the candidates that are proven to shrink the size. When the inline candidates are not eligible to import, a pre-merger combines their bitcode modules to remove inline restrictions. Our work improves the size of real-world mobile apps when compared to the MinSize (-Oz) optimization level. We reduced the code size by 2.8% for SocialApp and 4.0% for ChatApp.

show abstract

“…and key scenarios [11]. Outlining [4, 8, 11, 15ś17] improves the code size by factoring out the common code into functions.…”

Section: Introductionmentioning

confidence: 99%

“…Commercial mobile apps [4,11] are globally optimized at link time using either the regular full link-time optimization (LTO) or ThinLTO [10]. When building large apps, we use ThinLTO [10] because using LTO is impractical, taking a long time to build.…”

Section: Introductionmentioning

confidence: 99%