YJIT: a basic block versioning JIT compiler for CRuby

Chevalier-Boisvert, Maxime; Gibbs, N. H.; Boussier, Jean; Wu, Si Xing; Patterson, Aaron; Newton, Kevin; Hawthorn, John

doi:10.1145/3486606.3486781

Cited by 4 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we use benchmarks from the TruffleRuby and YJIT projects [4]. These are larger application-level benchmarks collected to guide the development of optimizations for the two corresponding Ruby implementations.…”

Section: Selection Of the Benchmark Setmentioning

confidence: 99%

“…We use R to analyze these traces, compute statistics, and generate summary plots and tables. 4 The results of the analysis are described in detail in Section 4.…”

Section: Behavior Monitoring and Analysismentioning

confidence: 99%

“…Ruby is used for many different applications, ranging from personal blogs to large industrial codebases used for instance by AirBnB, GitHub, Shopify, and Stripe. In this paper, we analyze the call-site behavior of a corpus of Ruby benchmarks, which were in part built to guide the optimization of Ruby implementations for and by Shopify [4], the Ruby, and the Ruby-on-Rails communities. These benchmarks include Rails-based applications, document-processing systems, a NES emulator, and others.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Who You Gonna Call: Analyzing the Run-Time Call-Site Behavior of Ruby Applications

Kaleba

Larose

Jones

et al. 2022

Proceedings of the 18th ACM SIGPLAN International Symposium on Dynamic Languages

View full text Add to dashboard Cite

Applications written in dynamic languages are becoming larger and larger and companies increasingly use multimillion line codebases in production. At the same time, dynamic languages rely heavily on dynamic optimizations, particularly those that reduce the overhead of method calls.In this work, we study the call-site behavior of Ruby benchmarks that are being used to guide the development of upcoming Ruby implementations such as TruffleRuby and YJIT. We study the interaction of call-site lookup caches, method splitting, and elimination of duplicate call-targets.We find that these optimizations are indeed highly effective on both smaller and large benchmarks, methods and closures alike, and help to open up opportunities for further optimizations such as inlining. However, we show that TruffleRuby's splitting may be applied too aggressively on already-monomorphic call-sites, coming at a run-time cost. We also find three distinct patterns in the evolution of callsite behavior over time, which may help to guide novel optimizations. We believe that our results may support language implementers in optimizing runtime systems for large codebases built in dynamic languages.CCS Concepts: • Software and its engineering → Language features; Object oriented languages; Dynamic compilers.

show abstract

Section: Selection Of the Benchmark Setmentioning

confidence: 99%

“…We use R to analyze these traces, compute statistics, and generate summary plots and tables. 4 The results of the analysis are described in detail in Section 4.…”

Section: Behavior Monitoring and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation