A metaobject protocol for optimizing application-speci€c run-Time variability
Just-in-Time compilers and their aggressive speculative optimizations reduced the performance gap between dynamic and static languages drastically. To successfully speculate, compilers rely on the program variability observed at run time to be low, and use heuristics to determine when optimization i...
| Publicado: |
2017
|
|---|---|
| Materias: | |
| Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97814503_v_n_p_Chari http://hdl.handle.net/20.500.12110/paper_97814503_v_n_p_Chari |
| Aporte de: |
| id |
paper:paper_97814503_v_n_p_Chari |
|---|---|
| record_format |
dspace |
| spelling |
paper:paper_97814503_v_n_p_Chari2023-06-08T16:37:34Z A metaobject protocol for optimizing application-speci€c run-Time variability Object oriented programming Optimization Application developers Application level Application performance Dynamic compilation Just in time compilers Metaobject protocol Speculative optimization Variability patterns Program compilers Just-in-Time compilers and their aggressive speculative optimizations reduced the performance gap between dynamic and static languages drastically. To successfully speculate, compilers rely on the program variability observed at run time to be low, and use heuristics to determine when optimization is beneficial. However, some variability patterns are hard to capture with heuristics. Specifically, ephemeral, warmup, rare, and highly indirect variability are challenges for today's compiler heuristics. As a consequence, they can lead to reduced application performance. However, these types of variability are identi€able at the application level and could be mitigated with information provided by developers. As a solution, we propose a metaobject protocol for dynamic compilation systems to enable application developers to provide such information at run time. As a proof of concept, we demonstrate performance improvements for a few scenarios in a dynamic language built on top of the Truffle and Graal system. © 2017 ACM. 2017 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97814503_v_n_p_Chari http://hdl.handle.net/20.500.12110/paper_97814503_v_n_p_Chari |
| institution |
Universidad de Buenos Aires |
| institution_str |
I-28 |
| repository_str |
R-134 |
| collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
| topic |
Object oriented programming Optimization Application developers Application level Application performance Dynamic compilation Just in time compilers Metaobject protocol Speculative optimization Variability patterns Program compilers |
| spellingShingle |
Object oriented programming Optimization Application developers Application level Application performance Dynamic compilation Just in time compilers Metaobject protocol Speculative optimization Variability patterns Program compilers A metaobject protocol for optimizing application-speci€c run-Time variability |
| topic_facet |
Object oriented programming Optimization Application developers Application level Application performance Dynamic compilation Just in time compilers Metaobject protocol Speculative optimization Variability patterns Program compilers |
| description |
Just-in-Time compilers and their aggressive speculative optimizations reduced the performance gap between dynamic and static languages drastically. To successfully speculate, compilers rely on the program variability observed at run time to be low, and use heuristics to determine when optimization is beneficial. However, some variability patterns are hard to capture with heuristics. Specifically, ephemeral, warmup, rare, and highly indirect variability are challenges for today's compiler heuristics. As a consequence, they can lead to reduced application performance. However, these types of variability are identi€able at the application level and could be mitigated with information provided by developers. As a solution, we propose a metaobject protocol for dynamic compilation systems to enable application developers to provide such information at run time. As a proof of concept, we demonstrate performance improvements for a few scenarios in a dynamic language built on top of the Truffle and Graal system. © 2017 ACM. |
| title |
A metaobject protocol for optimizing application-speci€c run-Time variability |
| title_short |
A metaobject protocol for optimizing application-speci€c run-Time variability |
| title_full |
A metaobject protocol for optimizing application-speci€c run-Time variability |
| title_fullStr |
A metaobject protocol for optimizing application-speci€c run-Time variability |
| title_full_unstemmed |
A metaobject protocol for optimizing application-speci€c run-Time variability |
| title_sort |
metaobject protocol for optimizing application-speci€c run-time variability |
| publishDate |
2017 |
| url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_97814503_v_n_p_Chari http://hdl.handle.net/20.500.12110/paper_97814503_v_n_p_Chari |
| _version_ |
1768545809435983872 |