AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913697303101440 |
|---|---|
| author | Mahmud, Quazi Ishtiaque TehraniJamsaz, Ali Phan, Hung Chen, Le Capotă, Mihai Willke, Theodore Ahmed, Nesreen K. Jannesari, Ali |
| author_facet | Mahmud, Quazi Ishtiaque TehraniJamsaz, Ali Phan, Hung Chen, Le Capotă, Mihai Willke, Theodore Ahmed, Nesreen K. Jannesari, Ali |
| contents | 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 \ourtool, a novel way to generate context using guidance from graph neural networks (GNNs) to generate efficient parallel codes. We evaluate \ourtool \xspace{} on $12$ applications from two well-known benchmark suites of parallel codes: NAS Parallel Benchmark and Rodinia Benchmark. Our results show that \ourtool \xspace{} 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, \ourtool \xspace{} improves the ability of the most powerful LLM to date, GPT-4, by achieving $\approx$17\% (on NAS benchmark) and $\approx$16\% (on Rodinia benchmark) better speedup. In addition, we propose \ourscore \xspace{} for evaluating the quality of the parallel code and show its effectiveness in evaluating parallel codes. \ourtool \xspace is available at https://github.com/quazirafi/AutoParLLM.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_04047 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs Mahmud, Quazi Ishtiaque TehraniJamsaz, Ali Phan, Hung Chen, Le Capotă, Mihai Willke, Theodore Ahmed, Nesreen K. Jannesari, Ali Machine Learning 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 \ourtool, a novel way to generate context using guidance from graph neural networks (GNNs) to generate efficient parallel codes. We evaluate \ourtool \xspace{} on $12$ applications from two well-known benchmark suites of parallel codes: NAS Parallel Benchmark and Rodinia Benchmark. Our results show that \ourtool \xspace{} 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, \ourtool \xspace{} improves the ability of the most powerful LLM to date, GPT-4, by achieving $\approx$17\% (on NAS benchmark) and $\approx$16\% (on Rodinia benchmark) better speedup. In addition, we propose \ourscore \xspace{} for evaluating the quality of the parallel code and show its effectiveness in evaluating parallel codes. \ourtool \xspace is available at https://github.com/quazirafi/AutoParLLM.git. |
| title | AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2310.04047 |