Abstract
In this study, we present a novel dataset for training machine learning models translating between OpenMP Fortran and C++ code. To ensure reliability and applicability, the dataset is created from a range of representative open-source OpenMP benchmarks. It is also refined using a meticulous code similarity test. The effectiveness of our dataset is assessed using both quantitative (CodeBLEU) and qualitative (human evaluation) methods. We showcase how this dataset significantly elevates the translation competencies of large language models (LLMs). Specifically, models without prior coding knowledge experienced a boost of x 5.1 in their CodeBLEU scores, while models with some coding familiarity saw an impressive x 9.9-fold increase. The best fine-tuned model using our dataset outperforms GPT-4. It is also reaching human-level accuracy. This work underscores the immense potential of our dataset in propelling advancements in the domain of code translation for high-performance computing. The dataset is accessible at https://github.com/bin123apple/Fortran-CPP-HPC-code-translation-dataset.
Original language | English (US) |
---|---|
Title of host publication | 2023 IEEE High Performance Extreme Computing Conference, HPEC 2023 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9798350308600 |
DOIs | |
State | Published - 2023 |
Externally published | Yes |
Event | 2023 IEEE High Performance Extreme Computing Conference, HPEC 2023 - Virtual, Online, United States Duration: Sep 25 2023 → Sep 29 2023 |
Publication series
Name | 2023 IEEE High Performance Extreme Computing Conference, HPEC 2023 |
---|
Conference
Conference | 2023 IEEE High Performance Extreme Computing Conference, HPEC 2023 |
---|---|
Country/Territory | United States |
City | Virtual, Online |
Period | 9/25/23 → 9/29/23 |
Bibliographical note
Publisher Copyright:© 2023 IEEE.
Keywords
- C++
- Code Translation
- Fortran
- Large Language Model
- OpenMP