# P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial Code

arXiv: https://arxiv.org/abs/2506.22703 · HTML: https://mlsanity.com/paper/2506.22703/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 28 Jun 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 9 of 9)

- [KernelBench: Can LLMs Write Efficient GPU Kernels?](https://mlsanity.com/paper/2502.10517/) (2025)
- [CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution](https://mlsanity.com/paper/2306.06755/) (2023)
- [OMPGPT: A Generative Pre-trained Transformer Model for OpenMP](https://mlsanity.com/paper/2401.16445/) (2024)
- [Advising OpenMP Parallelization via a Graph-Based Approach with Transformers](https://mlsanity.com/paper/2305.11999/) (2023)
- [LLM-Aided Compilation for Tensor Accelerators](https://mlsanity.com/paper/2408.03408/) (2024)
- [UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance](https://mlsanity.com/paper/2502.11460/) (2025)
- [OMPar: Automatic Parallelization with AI-Driven Source-to-Source Compilation](https://mlsanity.com/paper/2409.14771/) (2024)
- [Oracular Programming: A Modular Foundation for Building LLM-Enabled Software](https://mlsanity.com/paper/2502.05310/) (2025)
- [Developing an Interactive OpenMP Programming Book with Large Language Models](https://mlsanity.com/paper/2409.09296/) (2024)

## Built on by (most cited first, 1 of 1)

- [Exploring the Role of LLMs in HPC Programming: A Survey](https://mlsanity.com/paper/2608.26110/) (2026)

## Abstract (arXiv)

We present P4OMP, a retrieval-augmented framework for transforming serial C/C++ code into OpenMP-annotated parallel code using large language models (LLMs). To our knowledge, this is the first system to apply retrieval-based prompting for OpenMP pragma correctness without model fine-tuning or compiler instrumentation. P4OMP leverages Retrieval-Augmented Generation (RAG) with structured instructional knowledge from OpenMP tutorials to improve the reliability of prompt-driven code generation. By grounding generation in the retrieved context, P4OMP improves syntactic correctness compared to baseline prompting with GPT-3.5-Turbo. We evaluate P4OMP against a baseline, GPT-3.5-Turbo without retrieval, on a comprehensive benchmark of 108 real-world C++ programs drawn from Stack Overflow, PolyBench, and NAS benchmark suites. P4OMP achieves 100% compilation success on all parallelizable cases, while the baseline fails to compile in 20 out of 108 cases. Six cases that rely on non-random-access iterators or thread-unsafe constructs are excluded due to fundamental OpenMP limitations. A detailed analysis demonstrates how P4OMP consistently avoids scoping errors, syntactic misuse, and invalid directive combinations that commonly affect baseline-generated code. We further demonstrate strong runtime scaling across seven compute-intensive benchmarks on an HPC cluster. P4OMP offers a robust, modular pipeline that significantly improves the reliability and applicability of LLM-generated OpenMP code.