Prose-to-P4: Leveraging High Level Languages

TL;DR

This paper explores using large language models to translate natural language descriptions into high-level networking code, aiming to simplify development in programmable dataplane languages like P4.

Contribution

It proposes leveraging LLMs to elevate abstraction levels in network programming, providing a roadmap and preliminary results for prose-to-code translation.

Findings

Preliminary success in generating Lucid code from natural language.

Identified challenges and opportunities in prose-to-high-level code translation.

Roadmap for developing LLM-based network programming tools.

Abstract

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.