Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916315412824064 |
|---|---|
| author | Karanjai, Rabimba Hussain, Aftab Rabin, Md Rafiqul Islam Xu, Lei Shi, Weidong Alipour, Mohammad Amin |
| author_facet | Karanjai, Rabimba Hussain, Aftab Rabin, Md Rafiqul Islam Xu, Lei Shi, Weidong Alipour, Mohammad Amin |
| contents | Unit testing is crucial in software engineering for ensuring quality. However, it's not widely used in parallel and high-performance computing software, particularly scientific applications, due to their smaller, diverse user base and complex logic. These factors make unit testing challenging and expensive, as it requires specialized knowledge and existing automated tools are often ineffective.
To address this, we propose an automated method for generating unit tests for such software, considering their unique features like complex logic and parallel processing. Recently, large language models (LLMs) have shown promise in coding and testing. We explored the capabilities of Davinci (text-davinci-002) and ChatGPT (gpt-3.5-turbo) in creating unit tests for C++ parallel programs. Our results show that LLMs can generate mostly correct and comprehensive unit tests, although they have some limitations, such as repetitive assertions and blank test cases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05202 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing Karanjai, Rabimba Hussain, Aftab Rabin, Md Rafiqul Islam Xu, Lei Shi, Weidong Alipour, Mohammad Amin Software Engineering Artificial Intelligence Unit testing is crucial in software engineering for ensuring quality. However, it's not widely used in parallel and high-performance computing software, particularly scientific applications, due to their smaller, diverse user base and complex logic. These factors make unit testing challenging and expensive, as it requires specialized knowledge and existing automated tools are often ineffective. To address this, we propose an automated method for generating unit tests for such software, considering their unique features like complex logic and parallel processing. Recently, large language models (LLMs) have shown promise in coding and testing. We explored the capabilities of Davinci (text-davinci-002) and ChatGPT (gpt-3.5-turbo) in creating unit tests for C++ parallel programs. Our results show that LLMs can generate mostly correct and comprehensive unit tests, although they have some limitations, such as repetitive assertions and blank test cases. |
| title | Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2407.05202 |