Control flow graph based code optimization using graph neural networks
Frontiers in Robotics and AI · 11.03.2026 · 13
DOI: 10.3389/frobt.2026.1731740 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Robotics and AI, online erschienen am 11.03.2026. Verfasst von Melih Peker und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computer Engineering Department, Bilkent University, Ankara, Türkiye. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Selecting a good set of optimization flags requires extensive effort and expert input. While most of the prior research considers using static, spatial, or dynamic features, some of the latest research directly applied deep neural networks to source code. We combined the static features, spatial features, and deep neural networks by representing source code as graphs and trained Graph Neural Network for automatically finding suitable optimization flags. We created a dataset of 12000 graphs using 256 optimization flag combinations on 47 benchmarks. We trained and tested our model using these benchmarks, and our results show that we can achieve a maximum of 48.6% speed-up compared to the case where all optimization flags are enabled.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Engineering Department, Bilkent University, Ankara, Türkiye.
- Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Türkiye.
Zitieren
APA
Peker, M., & Ozturk, O. (2026). Control flow graph based code optimization using graph neural networks. Frontiers in Robotics and AI, 13. https://doi.org/10.3389/frobt.2026.1731740
Vancouver
Peker M, Ozturk O. Control flow graph based code optimization using graph neural networks. Frontiers in Robotics and AI. 2026;13. doi:10.3389/frobt.2026.1731740
BibTeX
@article{Peker2026,
author = {Peker, Melih and Ozturk, Ozcan},
title = {Control flow graph based code optimization using graph neural networks},
journal = {Frontiers in Robotics and AI},
year = {2026},
volume = {13},
doi = {10.3389/frobt.2026.1731740}
}
EUVIMED