CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909367759011840 |
|---|---|
| author | TehraniJamsaz, Ali Bhattacharjee, Arijit Chen, Le Ahmed, Nesreen K. Yazdanbakhsh, Amir Jannesari, Ali |
| author_facet | TehraniJamsaz, Ali Bhattacharjee, Arijit Chen, Le Ahmed, Nesreen K. Yazdanbakhsh, Amir Jannesari, Ali |
| contents | Recent advancements in Large Language Models (LLMs) have renewed interest in automatic programming language translation. Encoder-decoder transformer models, in particular, have shown promise in translating between different programming languages. However, translating between a language and its high-performance computing (HPC) extensions remains underexplored due to challenges such as complex parallel semantics. In this paper, we introduce CodeRosetta, an encoder-decoder transformer model designed specifically for translating between programming languages and their HPC extensions. CodeRosetta is evaluated on C++ to CUDA and Fortran to C++ translation tasks. It uses a customized learning framework with tailored pretraining and training objectives to effectively capture both code semantics and parallel structural nuances, enabling bidirectional translation. Our results show that CodeRosetta outperforms state-of-the-art baselines in C++ to CUDA translation by 2.9 BLEU and 1.72 CodeBLEU points while improving compilation accuracy by 6.05%. Compared to general closed-source LLMs, our method improves C++ to CUDA translation by 22.08 BLEU and 14.39 CodeBLEU, with 2.75% higher compilation accuracy. Finally, CodeRosetta exhibits proficiency in Fortran to parallel C++ translation, marking it, to our knowledge, as the first encoder-decoder model for this complex task, improving CodeBLEU by at least 4.63 points compared to closed-source and open-code LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20527 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming TehraniJamsaz, Ali Bhattacharjee, Arijit Chen, Le Ahmed, Nesreen K. Yazdanbakhsh, Amir Jannesari, Ali Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Performance Programming Languages Software Engineering Recent advancements in Large Language Models (LLMs) have renewed interest in automatic programming language translation. Encoder-decoder transformer models, in particular, have shown promise in translating between different programming languages. However, translating between a language and its high-performance computing (HPC) extensions remains underexplored due to challenges such as complex parallel semantics. In this paper, we introduce CodeRosetta, an encoder-decoder transformer model designed specifically for translating between programming languages and their HPC extensions. CodeRosetta is evaluated on C++ to CUDA and Fortran to C++ translation tasks. It uses a customized learning framework with tailored pretraining and training objectives to effectively capture both code semantics and parallel structural nuances, enabling bidirectional translation. Our results show that CodeRosetta outperforms state-of-the-art baselines in C++ to CUDA translation by 2.9 BLEU and 1.72 CodeBLEU points while improving compilation accuracy by 6.05%. Compared to general closed-source LLMs, our method improves C++ to CUDA translation by 22.08 BLEU and 14.39 CodeBLEU, with 2.75% higher compilation accuracy. Finally, CodeRosetta exhibits proficiency in Fortran to parallel C++ translation, marking it, to our knowledge, as the first encoder-decoder model for this complex task, improving CodeBLEU by at least 4.63 points compared to closed-source and open-code LLMs. |
| title | CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Performance Programming Languages Software Engineering |
| url | https://arxiv.org/abs/2410.20527 |