OMP-Engineer: Bridging Syntax Analysis and In-Context Learning for Efficient Automated OpenMP Parallelization

TL;DR

OMP-Engineer combines NLP-based techniques with traditional code analysis to improve the efficiency and accuracy of automated OpenMP parallelization, addressing limitations of existing NLP approaches.

Contribution

This paper introduces OMP-Engineer, a novel framework that integrates syntax analysis with in-context learning to enhance automated OpenMP parallelization.

Findings

Achieves faster parallel code generation with improved accuracy.

Balances efficiency of NLP models with reliability of traditional analysis.

Demonstrates superior performance over existing methods.

Abstract

In advancing parallel programming, particularly with OpenMP, the shift towards NLP-based methods marks a significant innovation beyond traditional S2S tools like Autopar and Cetus. These NLP approaches train on extensive datasets of examples to efficiently generate optimized parallel code, streamlining the development process. This method's strength lies in its ability to swiftly produce parallelized code that runs efficiently. However, this reliance on NLP models, without direct code analysis, can introduce inaccuracies, as these models might not fully grasp the nuanced semantics of the code they parallelize. We build OMP-Engineer, which balances the efficiency and scalability of NLP models with the accuracy and reliability of traditional methods, aiming to enhance the performance of automating parallelization while navigating its inherent challenges.