OMPILOT: Harnessing Transformer Models for Auto Parallelization to Shared Memory Computing Paradigms
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917072788783104 |
|---|---|
| author | Bhattacharjee, Arijit TehraniJamsaz, Ali Chen, Le Hasabnis, Niranjan Capota, Mihai Ahmed, Nesreen Jannesari, Ali |
| author_facet | Bhattacharjee, Arijit TehraniJamsaz, Ali Chen, Le Hasabnis, Niranjan Capota, Mihai Ahmed, Nesreen Jannesari, Ali |
| contents | Recent advances in large language models (LLMs) have significantly accelerated progress in code translation, enabling more accurate and efficient transformation across programming languages. While originally developed for natural language processing, LLMs have shown strong capabilities in modeling programming language syntax and semantics, outperforming traditional rule-based systems in both accuracy and flexibility. These models have streamlined cross-language conversion, reduced development overhead, and accelerated legacy code migration. In this paper, we introduce OMPILOT, a novel domain-specific encoder-decoder transformer tailored for translating C++ code into OpenMP, enabling effective shared-memory parallelization. OMPILOT leverages custom pre-training objectives that incorporate the semantics of parallel constructs and combines both unsupervised and supervised learning strategies to improve code translation robustness. Unlike previous work that focused primarily on loop-level transformations, OMPILOT operates at the function level to capture a wider semantic context. To evaluate our approach, we propose OMPBLEU, a novel composite metric specifically crafted to assess the correctness and quality of OpenMP parallel constructs, addressing limitations in conventional translation metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_03866 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OMPILOT: Harnessing Transformer Models for Auto Parallelization to Shared Memory Computing Paradigms Bhattacharjee, Arijit TehraniJamsaz, Ali Chen, Le Hasabnis, Niranjan Capota, Mihai Ahmed, Nesreen Jannesari, Ali Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Performance Programming Languages Recent advances in large language models (LLMs) have significantly accelerated progress in code translation, enabling more accurate and efficient transformation across programming languages. While originally developed for natural language processing, LLMs have shown strong capabilities in modeling programming language syntax and semantics, outperforming traditional rule-based systems in both accuracy and flexibility. These models have streamlined cross-language conversion, reduced development overhead, and accelerated legacy code migration. In this paper, we introduce OMPILOT, a novel domain-specific encoder-decoder transformer tailored for translating C++ code into OpenMP, enabling effective shared-memory parallelization. OMPILOT leverages custom pre-training objectives that incorporate the semantics of parallel constructs and combines both unsupervised and supervised learning strategies to improve code translation robustness. Unlike previous work that focused primarily on loop-level transformations, OMPILOT operates at the function level to capture a wider semantic context. To evaluate our approach, we propose OMPBLEU, a novel composite metric specifically crafted to assess the correctness and quality of OpenMP parallel constructs, addressing limitations in conventional translation metrics. |
| title | OMPILOT: Harnessing Transformer Models for Auto Parallelization to Shared Memory Computing Paradigms |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Performance Programming Languages |
| url | https://arxiv.org/abs/2511.03866 |