AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs
Quazi Ishtiaque Mahmud, Ali TehraniJamsaz, Hung D Phan, Le Chen, Mihai Capotă, Theodore L. Willke, Nesreen K. Ahmed, Ali Jannesari
Abstract
In-Context Learning (ICL) has been shown to be a powerful technique to augment the capabilities of LLMs for a diverse range of tasks. This work proposes AutoParLLM, a novel way to generate context using guidance from graph neural networks (GNNs) to generate efficient parallel codes. We evaluate AutoParLLM on 12 applications from two well-known benchmark suites of parallel codes: NAS Parallel Benchmark and Rodinia Benchmark. Our results show that AutoParLLM improves the state-of-the-art LLMs (e.g., GPT-4) by 19.9% in NAS and 6.48% in Rodinia benchmark in terms of CodeBERTScore for the task of parallel code generation. Moreover, AutoParLLM improves the ability of the most powerful LLM to date, GPT-4, by achieving 17% (on NAS benchmark) and 16% (on Rodinia benchmark) better speedup. In addition, we propose OMPScore for evaluating the quality of the parallel code and show its effectiveness in evaluating parallel codes.
BibTeX
@inproceedings{mahmud-etal-2025-autoparllm,
title = "{A}uto{P}ar{LLM}: {GNN}-guided Context Generation for Zero-Shot Code Parallelization using {LLM}s",
author = "Mahmud, Quazi Ishtiaque and
TehraniJamsaz, Ali and
Phan, Hung D and
Chen, Le and
Capot{\u{a}}, Mihai and
Willke, Theodore L. and
Ahmed, Nesreen K. and
Jannesari, Ali",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.593/",
pages = "11821--11841",
ISBN = "979-8-89176-189-6"
}