# ACCeLLiuM: Supervised Fine-Tuning for Automated OpenACC Pragma Generation

arXiv: https://arxiv.org/abs/2509.20380 · HTML: https://mlsanity.com/paper/2509.20380/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 36 references that are in the map.
- First posted on arXiv 20 Sep 2025.

## Builds on (most cited first, 12 of 12)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [OMPGPT: A Generative Pre-trained Transformer Model for OpenMP](https://mlsanity.com/paper/2401.16445/) (2024)
- [Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation](https://mlsanity.com/paper/2305.05779/) (2023)
- [MonoCoder: Domain-Specific Code Language Model for HPC Codes and Tasks](https://mlsanity.com/paper/2312.13322/) (2023)
- [Quantifying OpenMP: Statistical Insights into Usage and Adoption](https://mlsanity.com/paper/2308.08002/) (2023)
- [AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs](https://mlsanity.com/paper/2310.04047/) (2023)

## Abstract (arXiv)

The increasing ubiquity of GPUs is accompanied by the increasing complexity of their hardware and parallel programming frameworks. Directive-based parallel programming standards like OpenACC simplify GPU programming to some extent by abstracting away low-level complexities, but a fair amount of expertise is still required in order to use those directives effectively. We introduce ACCeLLiuM, two open weights Large Language Models specifically fine-tuned for generating expert OpenACC directives for data-parallel loops, along with the supervised fine-tuning dataset that was used to train them. The ACCeLLiuM SFT dataset contains 4,033 OpenACC pragma-loop pairs mined from public GitHub C/C++ repositories, with 3,223 pairs for training and 810 for testing. Experimental evaluations show a pronounced performance gap in generating correct OpenACC pragmas between base LLMs and our fine-tuned versions. On the held-out test set, base LLMs fail to consistently generate valid pragmas, whereas LLMs fine-tuned on the ACCeLLiuM dataset generate valid pragmas with the correct directive type for 87% of the data-parallel loops, and exact pragmas--including directives, clauses, clause order, and clause variables--for 50% of the cases. Even when not exact, generated pragmas frequently incorporate the correct clauses in a different order than the ground-truth label, or include additional clauses that enable finer control over parallel execution, data movement, and concurrency, offering practical value beyond strict string-matching. By publicly releasing the code, models, and dataset as ACCeLLiuM we hope to establish a reproducible benchmark for LLM-powered OpenACC pragma generation, and lower the barrier to automated GPU offloading of serially written programs.