Diagnosing Compiler Performance by Comparing Optimization Decisions

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A10473978" target="_blank" >RIV/00216208:11320/23:10473978 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1145/3617651.3622994" target="_blank" >https://doi.org/10.1145/3617651.3622994</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1145/3617651.3622994" target="_blank" >10.1145/3617651.3622994</a>

Result language
angličtina
Original language name
Diagnosing Compiler Performance by Comparing Optimization Decisions
Original language description
Modern compilers apply a set of optimization passes aiming to speed up the generated code. The combined effect of individual optimizations is difficult to predict. Thus, changes to a compiler's code may hinder the performance of generated code as an unintended consequence. Performance regressions in compiled code are often related to misapplied optimizations. The regressions are hard to investigate, considering the vast number of compilation units and applied optimizations. A compilation unit consists of a root method and inlined methods. Thus, a method may be part of several compilation units and may be optimized differently in each. Moreover, inlining decisions are not invariant across runs of the virtual machine (VM). We propose to solve the problem of diagnosing performance regressions by capturing the compiler's optimization decisions. We do so by representing the applied optimization phases, optimization decisions, and inlining decisions in the form of trees. This paper introduces an approach utilizing tree edit distance (TED) to detect optimization differences in a semi-automated way. We present an approach to compare optimization decisions in differently inlined methods. We employ these techniques to pinpoint the causes of performance problems in various benchmarks of the Graal compiler.
Czech name
—
Czech description
—

Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project
—
Continuities
S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
MPLR 2023 - Proceedings of the 20th ACM SIGPLAN International Conference on Managed Programming Languages and Runtimes
ISBN
979-8-4007-0380-5
ISSN
—
e-ISSN
—
Number of pages
15
Pages from-to
47-61
Publisher name
ACM
Place of publication
USA
Event location
Cascais, Portugal
Event date
Oct 22, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001142913500006

Similar results(10)