# LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes

arXiv: https://arxiv.org/abs/2407.01638 · HTML: https://mlsanity.com/paper/2407.01638/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 30 Jun 2024.

## Builds on (most cited first, 15 of 15)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [StarCoder 2 and The Stack v2: The Next Generation](https://mlsanity.com/paper/2402.19173/) (2024)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Nemotron-4 340B Technical Report](https://mlsanity.com/paper/2406.11704/) (2024)
- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing](https://mlsanity.com/paper/2404.12253/) (2024)
- [Can Large Language Models Write Parallel Code?](https://mlsanity.com/paper/2401.12554/) (2024)
- [The Unreasonable Effectiveness of Eccentric Automatic Prompts](https://mlsanity.com/paper/2402.10949/) (2024)
- [Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C++](https://mlsanity.com/paper/2307.07686/) (2023)

## Built on by (most cited first, 10 of 10)

- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation](https://mlsanity.com/paper/2412.11014/) (2024)
- [HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages](https://mlsanity.com/paper/2412.15178/) (2024)
- [Generative AI Uses and Risks for Knowledge Workers in a Science Organization](https://mlsanity.com/paper/2501.16577/) (2025)
- [Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes](https://mlsanity.com/paper/2505.02184/) (2025)
- [Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation](https://mlsanity.com/paper/2512.03086/) (2025)
- [CelloAI: Leveraging Large Language Models for HPC Software Development in High Energy Physics](https://mlsanity.com/paper/2508.16713/) (2025)
- [Adding New Capability in Existing Scientific Application with LLM Assistance](https://mlsanity.com/paper/2511.00087/) (2025)
- [ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation](https://mlsanity.com/paper/2601.04327/) (2026)
- [Cross-Model Cross-Language AI Coding Agent Performance: Accuracy and Speed of Parallel CLRS Algorithms](https://mlsanity.com/paper/2607.26083/) (2026)

## Abstract (arXiv)

This paper addresses the problem of providing a novel approach to sourcing significant training data for LLMs focused on science and engineering. In particular, a crucial challenge is sourcing parallel scientific codes in the ranges of millions to billions of codes. To tackle this problem, we propose an automated pipeline framework called LASSI, designed to translate between parallel programming languages by bootstrapping existing closed- or open-source LLMs. LASSI incorporates autonomous enhancement through self-correcting loops where errors encountered during the compilation and execution of generated code are fed back to the LLM through guided prompting for debugging and refactoring. We highlight the bi-directional translation of existing GPU benchmarks between OpenMP target offload and CUDA to validate LASSI. The results of evaluating LASSI with different application codes across four LLMs demonstrate the effectiveness of LASSI for generating executable parallel codes, with 80% of OpenMP to CUDA translations and 85% of CUDA to OpenMP translations producing the expected output. We also observe approximately 78% of OpenMP to CUDA translations and 62% of CUDA to OpenMP translations execute within 10% of or at a faster runtime than the original benchmark code in the same language.