Prose-to-P4: Leveraging High Level Languages
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913398255517696 |
|---|---|
| author | Dumitru, Mihai-Valentin Bădoiu, Vlad-Andrei Raiciu, Costin |
| author_facet | Dumitru, Mihai-Valentin Bădoiu, Vlad-Andrei Raiciu, Costin |
| contents | Languages such as P4 and NPL have enabled a wide and diverse range of networking applications that take advantage of programmable dataplanes. However, software development in these languages is difficult. To address this issue, high-level languages have been designed to offer programmers powerful abstractions that reduce the time, effort and domain-knowledge required for developing networking applications. These languages are then translated by a compiler into P4/NPL code. Inspired by the recent success of Large Language Models (LLMs) in the task of code generation, we propose to raise the level of abstraction even higher, employing LLMs to translate prose into high-level networking code. We analyze the problem, focusing on the motivation and opportunities, as well as the challenges involved and sketch out a roadmap for the development of a system that can generate high-level dataplane code from natural language instructions. We present some promising preliminary results on generating Lucid code from natural language. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13679 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prose-to-P4: Leveraging High Level Languages Dumitru, Mihai-Valentin Bădoiu, Vlad-Andrei Raiciu, Costin Networking and Internet Architecture Machine Learning Languages such as P4 and NPL have enabled a wide and diverse range of networking applications that take advantage of programmable dataplanes. However, software development in these languages is difficult. To address this issue, high-level languages have been designed to offer programmers powerful abstractions that reduce the time, effort and domain-knowledge required for developing networking applications. These languages are then translated by a compiler into P4/NPL code. Inspired by the recent success of Large Language Models (LLMs) in the task of code generation, we propose to raise the level of abstraction even higher, employing LLMs to translate prose into high-level networking code. We analyze the problem, focusing on the motivation and opportunities, as well as the challenges involved and sketch out a roadmap for the development of a system that can generate high-level dataplane code from natural language instructions. We present some promising preliminary results on generating Lucid code from natural language. |
| title | Prose-to-P4: Leveraging High Level Languages |
| topic | Networking and Internet Architecture Machine Learning |
| url | https://arxiv.org/abs/2406.13679 |