Publications

2026

1. [ACL’26] ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation

   Erel Kaplan, Tomer Bitan, Lian Ghrayeb, Le Chen, Tom Yotam, Niranjan Hasabnis, and Gal Oren

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026

   DOI Bib

   @inproceedings{kaplan2026paracodex,
     title = {ParaCodex: A Profiling-Guided Autonomous Coding Agent for Reliable Parallel Code Generation and Translation},
     author = {Kaplan, Erel and Bitan, Tomer and Ghrayeb, Lian and Chen, Le and Yotam, Tom and Hasabnis, Niranjan and Oren, Gal},
     booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
     month = jul,
     year = {2026},
     address = {San Diego, California, United States},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2026.acl-long.732/},
     doi = {10.18653/v1/2026.acl-long.732},
     pages = {16113--16136},
     isbn = {979-8-89176-390-6}
   }

2. [Preprint] Latent Reasoning Guidance for Parallel Code Translation

   Tomer Bitan, Erel Kaplan, Ron Bar-Yadin, Lian Ghrayeb, Le Chen, Shrey Jhaveri, and others

   arXiv preprint arXiv:2606.05518, Jul 2026

   Bib

   @article{bitan2026latent,
     title = {Latent Reasoning Guidance for Parallel Code Translation},
     author = {Bitan, Tomer and Kaplan, Erel and Bar-Yadin, Ron and Ghrayeb, Lian and Chen, Le and Jhaveri, Shrey and others},
     journal = {arXiv preprint arXiv:2606.05518},
     year = {2026},
     url = {https://arxiv.org/abs/2606.05518}
   }

3. [Preprint] ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation

   Tom Yotam, Le Chen, Tomer Bitan, Niranjan Hasabnis, Gal Oren, and others

   ResearchGate preprint, Jul 2026

   Bib

   @article{chen2026parbench,
     title = {ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation},
     author = {Yotam, Tom and Chen, Le and Bitan, Tomer and Hasabnis, Niranjan and Oren, Gal and others},
     journal = {ResearchGate preprint},
     year = {2026},
     url = {https://www.researchgate.net/publication/405207787_ParBench_A_Benchmark_for_Reliable_Evaluation_of_LLM_Parallel_Code_Translation}
   }

4. [PEARC’26] Improving Usability and Productivity of PETSc with Agent-Based Workflows

   Barry Smith, Hong Zhang, Junchao Zhang, Satish Balay, Le Chen, Murat Keçeli, and Lois Curfman McInnes

   In Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities, Jul 2026

   DOI Bib

   @inproceedings{smith2026petsc,
     title = {Improving Usability and Productivity of PETSc with Agent-Based Workflows},
     author = {Smith, Barry and Zhang, Hong and Zhang, Junchao and Balay, Satish and Chen, Le and Ke{\c{c}}eli, Murat and McInnes, Lois Curfman},
     booktitle = {Proceedings of the Practice and Experience in Advanced Research Computing 2026: Resilient Roots + Empowered Communities},
     series = {PEARC '26},
     articleno = {38},
     numpages = {5},
     year = {2026},
     address = {New York, NY, USA},
     publisher = {Association for Computing Machinery},
     isbn = {9798400723773},
     url = {https://doi.org/10.1145/3785462.3815882},
     doi = {10.1145/3785462.3815882}
   }

5. [Preprint] An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc

   Hong Zhang, Barry Smith, Satish Balay, Le Chen, Murat Keçeli, Lois Curfman McInnes, and Junchao Zhang

   arXiv preprint arXiv:2603.15976, Jul 2026

   🏆 AgentBeats 3rd Place · Impact Argonne Bib

   PETScAgent-Bench earned third place in the Coding Agent track of Phase 1 of the AgentBeats competition (organized by Berkeley RDI, 1,300+ registered groups) and was the only national-laboratory-led benchmark to receive an award. The project also received an Impact Argonne Award in the category of Innovation.

   @article{zhang2026agentic,
     title = {An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc},
     author = {Zhang, Hong and Smith, Barry and Balay, Satish and Chen, Le and Ke{\c{c}}eli, Murat and McInnes, Lois Curfman and Zhang, Junchao},
     journal = {arXiv preprint arXiv:2603.15976},
     year = {2026},
     url = {https://arxiv.org/abs/2603.15976},
   }

6. [ACL’26] Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation

   Le Chen, Nuo Xu, Winson Chen, Bin Lei, Pei-Hung Lin, Dunzhi Zhou, Rajeev Thakur, Caiwen Ding, Ali Jannesari, and Chunhua Liao

   In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026

   DOI Bib

   @inproceedings{chen2026beyond,
     title = {Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation},
     author = {Chen, Le and Xu, Nuo and Chen, Winson and Lei, Bin and Lin, Pei-Hung and Zhou, Dunzhi and Thakur, Rajeev and Ding, Caiwen and Jannesari, Ali and Liao, Chunhua},
     booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
     month = jul,
     year = {2026},
     address = {San Diego, California, United States},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2026.acl-long.1557/},
     doi = {10.18653/v1/2026.acl-long.1557},
     pages = {33781--33803},
     isbn = {979-8-89176-390-6}
   }

7. [Preprint] FABRICA: Agentic CUDA-to-CSL Translation and Optimization for Wafer-Scale Systems

   Yuebo Luo, Eliu Huerta, Venkatram Vishwanath, Caiwen Ding, Rajeev Thakur, and Le Chen

   arXiv preprint arXiv:2608.25124, Jul 2026

   Bib

   @article{luo2026fabrica,
     title = {FABRICA: Agentic CUDA-to-CSL Translation and Optimization for Wafer-Scale Systems},
     author = {Luo, Yuebo and Huerta, Eliu and Vishwanath, Venkatram and Ding, Caiwen and Thakur, Rajeev and Chen, Le},
     journal = {arXiv preprint arXiv:2608.25124},
     year = {2026},
     url = {https://arxiv.org/abs/2608.25124}
   }

2025

1. [NAACL’25] AutoParLLM: GNN-guided Context Generation for Zero-Shot Code Parallelization using LLMs

   Quazi Ishtiaque Mahmud, Ali TehraniJamsaz, Hung D Phan, Le Chen, Mihai Capotă, Theodore L. Willke, Nesreen K. Ahmed, and Ali Jannesari

   In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Apr 2025

   Abs DOI Bib

   In-Context Learning (ICL) has been shown to be a powerful technique to augment the capabilities of LLMs for a diverse range of tasks. This work proposes AutoParLLM, a novel way to generate context using guidance from graph neural networks (GNNs) to generate efficient parallel codes. We evaluate AutoParLLM on 12 applications from two well-known benchmark suites of parallel codes: NAS Parallel Benchmark and Rodinia Benchmark. Our results show that AutoParLLM improves the state-of-the-art LLMs (e.g., GPT-4) by 19.9% in NAS and 6.48% in Rodinia benchmark in terms of CodeBERTScore for the task of parallel code generation. Moreover, AutoParLLM improves the ability of the most powerful LLM to date, GPT-4, by achieving 17% (on NAS benchmark) and 16% (on Rodinia benchmark) better speedup. In addition, we propose OMPScore for evaluating the quality of the parallel code and show its effectiveness in evaluating parallel codes.

   @inproceedings{mahmud2025autoparllm,
     title = {{A}uto{P}ar{LLM}: {GNN}-guided Context Generation for Zero-Shot Code Parallelization using {LLM}s},
     author = {Mahmud, Quazi Ishtiaque and TehraniJamsaz, Ali and Phan, Hung D and Chen, Le and Capot{\u{a}}, Mihai and Willke, Theodore L. and Ahmed, Nesreen K. and Jannesari, Ali},
     editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
     booktitle = {Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},
     month = apr,
     year = {2025},
     address = {Albuquerque, New Mexico},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.naacl-long.593/},
     doi = {10.18653/v1/2025.naacl-long.593},
     pages = {11821--11841},
     isbn = {979-8-89176-189-6}
   }

2. [IPDPS’25] PCEBench: A Multi-Dimensional Benchmark for Evaluating Large Language Models in Parallel Code Generation

   Le Chen, Nesreen Ahmed, Mihai Capotă, Ted Willke, Niranjan Hasabnis, and Ali Jannesari

   In 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS), Apr 2025

   DOI Bib

   @inproceedings{chen2025pcebench,
     author = {Chen, Le and Ahmed, Nesreen and Capotă, Mihai and Willke, Ted and Hasabnis, Niranjan and Jannesari, Ali},
     booktitle = {2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)},
     title = {PCEBench: A Multi-Dimensional Benchmark for Evaluating Large Language Models in Parallel Code Generation},
     year = {2025},
     volume = {},
     number = {},
     pages = {546-557},
     keywords = {Technological innovation;Codes;Parallel programming;Large language models;Scalability;Benchmark testing;Software systems;Multitasking;Natural language processing;Synchronization;large language model;parallel code generation;benchmark;evaluation;LLM agent},
     doi = {10.1109/IPDPS64566.2025.00055}
   }

3. [SC-W’25] FIRST: Federated Inference Resource Scheduling Toolkit for Scientific AI Model Access

   Aditya Tanikanti, Benoı̂t Côté, Yanfei Guo, Le Chen, Nicholaus Saint, Ryan Chard, Ken Raffenetti, Rajeev Thakur, Thomas D. Uram, Ian T. Foster, Michael E. Papka, and Venkatram Vishwanath

   In Proceedings of the SC ’25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2025, St Louis, MO, USA, November 16-21, 2025, Apr 2025

   DOI Bib

   @inproceedings{Aditya2025first,
     author = {Tanikanti, Aditya and C{\{o}}t{\'{e}}, Beno{\{\i}}t and Guo, Yanfei and Chen, Le and Saint, Nicholaus and Chard, Ryan and Raffenetti, Ken and Thakur, Rajeev and Uram, Thomas D. and Foster, Ian T. and Papka, Michael E. and Vishwanath, Venkatram},
     title = {{FIRST:} Federated Inference Resource Scheduling Toolkit for Scientific
                       {AI} Model Access},
     booktitle = {Proceedings of the {SC} '25 Workshops of the International Conference
                       for High Performance Computing, Networking, Storage and Analysis,
                       {SC} Workshops 2025, St Louis, MO, USA, November 16-21, 2025},
     pages = {52--60},
     publisher = {{ACM}},
     year = {2025},
     url = {https://doi.org/10.1145/3731599.3767346},
     doi = {10.1145/3731599.3767346},
     timestamp = {Fri, 26 Dec 2025 20:53:24 +0100},
     biburl = {https://dblp.org/rec/conf/sc/TanikantiCGCSCR25.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

4. [HPEC’25] UniPar: A Unified LLM-Based Framework for Parallel and Accelerated Code Translation in HPC

   Tomer Bitan, Tal Kadosh, Erel Kaplan, Shira Meiri, Le Chen, Peter Morales, Niranjan Hasabnis, and Gal Oren

   In IEEE High Performance Extreme Computing Conference, HPEC 2025, Wakefield, MA, USA, September 15-19, 2025, Apr 2025

   🏆 Outstanding Student Paper DOI Bib

   Recognized with the Outstanding Student Paper Award at HPEC 2025.

   @inproceedings{bitan2025unipar,
     author = {Bitan, Tomer and Kadosh, Tal and Kaplan, Erel and Meiri, Shira and Chen, Le and Morales, Peter and Hasabnis, Niranjan and Oren, Gal},
     title = {UniPar: {A} Unified LLM-Based Framework for Parallel and Accelerated
                       Code Translation in {HPC}},
     booktitle = {{IEEE} High Performance Extreme Computing Conference, {HPEC} 2025,
                       Wakefield, MA, USA, September 15-19, 2025},
     pages = {1--9},
     publisher = {{IEEE}},
     year = {2025},
     url = {https://doi.org/10.1109/HPEC67600.2025.11196677},
     doi = {10.1109/HPEC67600.2025.11196677},
     timestamp = {Sat, 08 Nov 2025 10:18:23 +0100},
     biburl = {https://dblp.org/rec/conf/hpec/BitanKKMCMHO25.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

5. [ICPP-W’25] AI Assistants to Enhance and Exploit the PETSc Knowledge Base

   Barry Smith, Junchao Zhang, Hong Zhang, Lois Curfman McInnes, Murat Keçeli, Archit Vasan, Satish Balay, Toby Isaac, Le Chen, and Venkatram Vishwanath

   Apr 2025

   DOI Bib

   @article{smith2025ai,
     author = {Smith, Barry and Zhang, Junchao and Zhang, Hong and McInnes, Lois Curfman and Ke{\c{c}}eli, Murat and Vasan, Archit and Balay, Satish and Isaac, Toby and Chen, Le and Vishwanath, Venkatram},
     title = {{AI} Assistants to Enhance and Exploit the PETSc Knowledge Base},
     booktitle = {Workshop Proceedings of the 54th International Conference on Parallel
                       Processing, {ICPP} Workshops 2025, San Diego, CA, USA, September 8-11,
                       2025},
     pages = {9--17},
     publisher = {{ACM}},
     year = {2025},
     url = {https://doi.org/10.1145/3750720.3757281},
     doi = {10.1145/3750720.3757281},
     timestamp = {Thu, 05 Mar 2026 17:17:13 +0100},
     biburl = {https://dblp.org/rec/conf/icppw/000200MKVBICV25.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

6. [SC-W’25] Evaluation of Test-Time Compute Constraints on Safety and Skill Large Reasoning Models

   Adarsha Balaji, Le Chen, Rajeev Thakur, Franck Cappello, and Sandeep Madireddy

   In Proceedings of the SC ’25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2025, St Louis, MO, USA, November 16-21, 2025, Apr 2025

   DOI Bib

   @inproceedings{balaji2025evaluation,
     author = {Balaji, Adarsha and Chen, Le and Thakur, Rajeev and Cappello, Franck and Madireddy, Sandeep},
     title = {Evaluation of Test-Time Compute Constraints on Safety and Skill Large
                       Reasoning Models},
     booktitle = {Proceedings of the {SC} '25 Workshops of the International Conference
                       for High Performance Computing, Networking, Storage and Analysis,
                       {SC} Workshops 2025, St Louis, MO, USA, November 16-21, 2025},
     pages = {534--539},
     publisher = {{ACM}},
     year = {2025},
     url = {https://doi.org/10.1145/3731599.3767406},
     doi = {10.1145/3731599.3767406},
     timestamp = {Fri, 26 Dec 2025 20:53:25 +0100},
     biburl = {https://dblp.org/rec/conf/sc/BalajiCTCM25.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

7. [Preprint] Who Gets the Reward, Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents

   Chih-Hsuan Yang, Tanwi Mallick, Le Chen, Krishnan Raghavan, Aaron Wells, Amal Gueroudji, Ian T. Foster, and others

   arXiv preprint arXiv:2511.10687, Apr 2025

   Bib

   @article{yang2025reward,
     title = {Who Gets the Reward, Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents},
     author = {Yang, Chih-Hsuan and Mallick, Tanwi and Chen, Le and Raghavan, Krishnan and Wells, Aaron and Gueroudji, Amal and Foster, Ian T. and others},
     journal = {arXiv preprint arXiv:2511.10687},
     year = {2025},
     url = {https://arxiv.org/abs/2511.10687}
   }

8. [Preprint] OMPILOT: Harnessing Transformer Models for Auto Parallelization to Shared Memory Computing Paradigms

   Arijit Bhattacharjee, Ali TehraniJamsaz, Le Chen, Niranjan Hasabnis, Mihai Capotă, and others

   arXiv preprint arXiv:2511.03866, Apr 2025

   Bib

   @article{bhattacharjee2025ompilot,
     title = {OMPILOT: Harnessing Transformer Models for Auto Parallelization to Shared Memory Computing Paradigms},
     author = {Bhattacharjee, Arijit and TehraniJamsaz, Ali and Chen, Le and Hasabnis, Niranjan and Capot{\u{a}}, Mihai and others},
     journal = {arXiv preprint arXiv:2511.03866},
     year = {2025},
     url = {https://arxiv.org/abs/2511.03866}
   }

2024

1. [Preprint] The Landscape and Challenges of HPC Research and LLMs

   Le Chen, Nesreen K. Ahmed, Akash Dutta, Arijit Bhattacharjee, Sixing Yu, Quazi Ishtiaque Mahmud, Waqwoya Abebe, Hung Phan, Aishwarya Sarkar, Branden Butler, Niranjan Hasabnis, Gal Oren, Vy A. Vo, Juan Pablo Muñoz, Theodore L. Willke, Tim Mattson, and Ali Jannesari

   CoRR, Apr 2024

   DOI Bib

   @article{chen2024landscape,
     author = {Chen, Le and Ahmed, Nesreen K. and Dutta, Akash and Bhattacharjee, Arijit and Yu, Sixing and Mahmud, Quazi Ishtiaque and Abebe, Waqwoya and Phan, Hung and Sarkar, Aishwarya and Butler, Branden and Hasabnis, Niranjan and Oren, Gal and Vo, Vy A. and Mu{\~{n}}oz, Juan Pablo and Willke, Theodore L. and Mattson, Tim and Jannesari, Ali},
     title = {The Landscape and Challenges of {HPC} Research and LLMs},
     journal = {CoRR},
     volume = {abs/2402.02018},
     year = {2024},
     url = {https://doi.org/10.48550/arXiv.2402.02018},
     doi = {10.48550/ARXIV.2402.02018},
     eprinttype = {arXiv},
     eprint = {2402.02018},
     timestamp = {Wed, 03 Jun 2026 20:27:02 +0200},
     biburl = {https://dblp.org/rec/journals/corr/abs-2402-02018.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

2. [EuroPar’24] OMPGPT: A Generative Pre-trained Transformer Model for OpenMP

   Le Chen, Arijit Bhattacharjee, Nesreen K. Ahmed, Niranjan Hasabnis, Gal Oren, Vy A. Vo, and Ali Jannesari

   In Euro-Par 2024: Parallel Processing - 30th European Conference on Parallel and Distributed Processing, Madrid, Spain, August 26-30, 2024, Proceedings, Part I, Apr 2024

   DOI Bib

   @inproceedings{chen2024ompgpt,
     author = {Chen, Le and Bhattacharjee, Arijit and Ahmed, Nesreen K. and Hasabnis, Niranjan and Oren, Gal and Vo, Vy A. and Jannesari, Ali},
     editor = {Carretero, Jes{\'{u}}s and Shende, Sameer and Garc{\'{\i}}a{-}Blas, Javier and Brandic, Ivona and Olcoz, Katzalin and Schreiber, Martin},
     title = {{OMPGPT:} {A} Generative Pre-trained Transformer Model for OpenMP},
     booktitle = {Euro-Par 2024: Parallel Processing - 30th European Conference on Parallel
                       and Distributed Processing, Madrid, Spain, August 26-30, 2024, Proceedings,
                       Part {I}},
     series = {Lecture Notes in Computer Science},
     volume = {14801},
     pages = {121--134},
     publisher = {Springer},
     year = {2024},
     url = {https://doi.org/10.1007/978-3-031-69577-3_9},
     doi = {10.1007/978-3-031-69577-3_9},
     timestamp = {Mon, 03 Mar 2025 21:04:13 +0100},
     biburl = {https://dblp.org/rec/conf/europar/ChenBAHOVJ24.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

3. [NeurIPS’24] CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming

   Ali TehraniJamsaz, Arijit Bhattacharjee, Le Chen, Nesreen K. Ahmed, Amir Yazdanbakhsh, and Ali Jannesari

   In Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, Apr 2024

   Bib

   @inproceedings{tehrani2024coderosetta,
     author = {TehraniJamsaz, Ali and Bhattacharjee, Arijit and Chen, Le and Ahmed, Nesreen K. and Yazdanbakhsh, Amir and Jannesari, Ali},
     editor = {Globersons, Amir and Mackey, Lester and Belgrave, Danielle and Fan, Angela and Paquet, Ulrich and Tomczak, Jakub M. and Zhang, Cheng},
     title = {CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation
                       for Parallel Programming},
     booktitle = {Advances in Neural Information Processing Systems 38: Annual Conference
                       on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,
                       BC, Canada, December 10 - 15, 2024},
     year = {2024},
     url = {http://papers.nips.cc/paper_files/paper/2024/hash/b6edb87876bec4ac2260bffa083cb992-Abstract-Conference.html},
     timestamp = {Thu, 13 Feb 2025 16:56:44 +0100},
     biburl = {https://dblp.org/rec/conf/nips/TehraniJamsazBC24.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

4. [Preprint] Fortran2cpp: Automating fortran-to-c++ migration using llms via multi-turn dialogue and dual-agent integration

   Le Chen, Bin Lei, Dunzhi Zhou, Pei-Hung Lin, Chunhua Liao, Caiwen Ding, and Ali Jannesari

   arXiv e-prints, Apr 2024

   Bib

   @article{chen2024fortran2cpp,
     url = {https://arxiv.org/abs/2412.19770},
     title = {Fortran2cpp: Automating fortran-to-c++ migration using llms via multi-turn dialogue and dual-agent integration},
     author = {Chen, Le and Lei, Bin and Zhou, Dunzhi and Lin, Pei-Hung and Liao, Chunhua and Ding, Caiwen and Jannesari, Ali},
     journal = {arXiv e-prints},
     pages = {arXiv--2412},
     year = {2024}
   }

2023

1. [SC-W’23] HPC-GPT: Integrating Large Language Model for High-Performance Computing

   Xianzhong Ding, Le Chen, Murali Emani, Chunhua Liao, Pei-Hung Lin, Tristan Vanderbruggen, Zhen Xie, Alberto Cerpa, and Wan Du

   In Proceedings of the SC ’23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, SC-W 2023, Denver, CO, USA, November 12-17, 2023, Apr 2023

   DOI Bib

   @inproceedings{ding2023hpc,
     author = {Ding, Xianzhong and Chen, Le and Emani, Murali and Liao, Chunhua and Lin, Pei{-}Hung and Vanderbruggen, Tristan and Xie, Zhen and Cerpa, Alberto and Du, Wan},
     title = {{HPC-GPT:} Integrating Large Language Model for High-Performance Computing},
     booktitle = {Proceedings of the {SC} '23 Workshops of The International Conference
                       on High Performance Computing, Network, Storage, and Analysis, {SC-W}
                       2023, Denver, CO, USA, November 12-17, 2023},
     pages = {951--960},
     publisher = {{ACM}},
     year = {2023},
     url = {https://doi.org/10.1145/3624062.3624172},
     doi = {10.1145/3624062.3624172},
     timestamp = {Sun, 19 Jan 2025 13:19:21 +0100},
     biburl = {https://dblp.org/rec/conf/sc/DingCELLVXCD23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

2. [IWOMP’23] LM4HPC: Towards Effective Language Model Application in High-Performance Computing

   Le Chen, Pei-Hung Lin, Tristan Vanderbruggen, Chunhua Liao, Murali Emani, and Bronis R. Supinski

   In OpenMP: Advanced Task-Based, Device and Compiler Programming - 19th International Workshop on OpenMP, IWOMP 2023, Bristol, UK, September 13-15, 2023, Proceedings, Apr 2023

   DOI Bib

   @inproceedings{chen2023lm4hpc,
     author = {Chen, Le and Lin, Pei{-}Hung and Vanderbruggen, Tristan and Liao, Chunhua and Emani, Murali and de Supinski, Bronis R.},
     editor = {McIntosh{-}Smith, Simon and Klemm, Michael and de Supinski, Bronis R. and Deakin, Tom and Klinkenberg, Jannis},
     title = {{LM4HPC:} Towards Effective Language Model Application in High-Performance
                       Computing},
     booktitle = {OpenMP: Advanced Task-Based, Device and Compiler Programming - 19th
                       International Workshop on OpenMP, {IWOMP} 2023, Bristol, UK, September
                       13-15, 2023, Proceedings},
     series = {Lecture Notes in Computer Science},
     volume = {14114},
     pages = {18--33},
     publisher = {Springer},
     year = {2023},
     url = {https://doi.org/10.1007/978-3-031-40744-4_2},
     doi = {10.1007/978-3-031-40744-4_2},
     timestamp = {Thu, 14 Sep 2023 20:25:47 +0200},
     biburl = {https://dblp.org/rec/conf/iwomp/ChenLVLES23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

3. [SC-W’23] Data Race Detection Using Large Language Models

   Le Chen, Xianzhong Ding, Murali Emani, Tristan Vanderbruggen, Pei-Hung Lin, and Chunhua Liao

   In Proceedings of the SC ’23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, Denver, CO, USA, Apr 2023

   Abs DOI Bib

   Large language models (LLMs) are demonstrating significant promise as an alternate strategy to facilitate analyses and optimizations of high-performance computing programs, circumventing the need for resource-intensive manual tool creation. In this paper, we explore a novel LLM-based data race detection approach combining prompting engineering and fine-tuning techniques. We create a dedicated dataset named DRB-ML, which is derived from DataRaceBench, with fine-grain labels showing the presence of data race pairs and their associated variables, line numbers, and read/write information. DRB-ML is then used to evaluate representative LLMs and fine-tune open-source ones. Our experiment shows that LLMs can be a viable approach to data race detection. However, they still cannot compete with traditional data race detection tools when we need detailed information about variable pairs causing data races.

   @inproceedings{chen2023data,
     author = {Chen, Le and Ding, Xianzhong and Emani, Murali and Vanderbruggen, Tristan and Lin, Pei-Hung and Liao, Chunhua},
     title = {Data Race Detection Using Large Language Models},
     year = {2023},
     isbn = {9798400707858},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     url = {https://doi.org/10.1145/3624062.3624088},
     doi = {10.1145/3624062.3624088},
     booktitle = {Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis},
     pages = {215–223},
     numpages = {9},
     keywords = {OpenMP, data race detection, large language model},
     location = {Denver, CO, USA},
     series = {SC-W '23}
   }

4. [MLSys’23] Learning to Parallelize with OpenMP by Augmented Heterogeneous AST Representation

   Le Chen, Quazi Ishtiaque Mahmud, Hung Phan, Nesreen K. Ahmed, and Ali Jannesari

   In Proceedings of the Sixth Conference on Machine Learning and Systems, MLSys 2023, Miami, FL, USA, June 4-8, 2023, Apr 2023

   🎫 MLSys Travel Grant Bib

   Supported by an MLSys 2023 Travel Grant.

   @inproceedings{chen2023learning,
     author = {Chen, Le and Mahmud, Quazi Ishtiaque and Phan, Hung and Ahmed, Nesreen K. and Jannesari, Ali},
     editor = {Song, Dawn and Carbin, Michael and Chen, Tianqi},
     title = {Learning to Parallelize with OpenMP by Augmented Heterogeneous {AST}
                       Representation},
     booktitle = {Proceedings of the Sixth Conference on Machine Learning and Systems,
                       MLSys 2023, Miami, FL, USA, June 4-8, 2023},
     publisher = {mlsys.org},
     year = {2023},
     url = {https://proceedings.mlsys.org/paper_files/paper/2023/hash/8ee477d6175a03d7098fa23641a2d298-Abstract-mlsys2023.html},
     timestamp = {Fri, 28 Jun 2024 15:58:54 +0200},
     biburl = {https://dblp.org/rec/conf/mlsys/ChenMPAJ23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

5. [NeurIPS’23] PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis

   Ali TehraniJamsaz, Quazi Ishtiaque Mahmud, Le Chen, Nesreen K. Ahmed, and Ali Jannesari

   In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Apr 2023

   Bib

   @inproceedings{tehranijamsaz2023perfograph,
     author = {TehraniJamsaz, Ali and Mahmud, Quazi Ishtiaque and Chen, Le and Ahmed, Nesreen K. and Jannesari, Ali},
     editor = {Oh, Alice and Naumann, Tristan and Globerson, Amir and Saenko, Kate and Hardt, Moritz and Levine, Sergey},
     title = {{PERFOGRAPH:} {A} Numerical Aware Program Graph Representation for
                       Performance Optimization and Program Analysis},
     booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference
                       on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
                       LA, USA, December 10 - 16, 2023},
     year = {2023},
     url = {http://papers.nips.cc/paper_files/paper/2023/hash/b41907dd4df5c60f86216b73fe0c7465-Abstract-Conference.html},
     timestamp = {Fri, 01 Mar 2024 16:26:20 +0100},
     biburl = {https://dblp.org/rec/conf/nips/TehraniJamsazMC23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

6. [HPEC’23] Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C++

   Bin Lei, Caiwen Ding, Le Chen, Pei-Hung Lin, and Chunhua Liao

   In IEEE High Performance Extreme Computing Conference, HPEC 2023, Boston, MA, USA, September 25-29, 2023, Apr 2023

   🏆 Outstanding Student Paper DOI Bib

   Recognized with the Outstanding Student Paper Award at HPEC 2023.

   @inproceedings{lei2023creating,
     author = {Lei, Bin and Ding, Caiwen and Chen, Le and Lin, Pei{-}Hung and Liao, Chunhua},
     title = {Creating a Dataset for High-Performance Computing Code Translation
                       using LLMs: {A} Bridge Between OpenMP Fortran and {C++}},
     booktitle = {{IEEE} High Performance Extreme Computing Conference, {HPEC} 2023,
                       Boston, MA, USA, September 25-29, 2023},
     pages = {1--7},
     publisher = {{IEEE}},
     year = {2023},
     url = {https://doi.org/10.1109/HPEC58863.2023.10363534},
     doi = {10.1109/HPEC58863.2023.10363534},
     timestamp = {Tue, 21 Apr 2026 16:21:20 +0200},
     biburl = {https://dblp.org/rec/conf/hpec/LeiDCLL23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

7. [Preprint] Compcodevet: A compiler-guided validation and enhancement approach for code dataset

   Le Chen, Arijit Bhattacharjee, Nesreen K Ahmed, Niranjan Hasabnis, Gal Oren, Bin Lei, and Ali Jannesari

   arXiv preprint arXiv:2311.06505, Apr 2023

   Bib

   @article{chen2023compcodevet,
     url = {https://arxiv.org/abs/2311.06505},
     title = {Compcodevet: A compiler-guided validation and enhancement approach for code dataset},
     author = {Chen, Le and Bhattacharjee, Arijit and Ahmed, Nesreen K and Hasabnis, Niranjan and Oren, Gal and Lei, Bin and Jannesari, Ali},
     journal = {arXiv preprint arXiv:2311.06505},
     year = {2023}
   }

8. [Preprint] Flashvideo: A framework for swift inference in text-to-video generation

   Bin Lei, Caiwen Ding, and others

   arXiv preprint arXiv:2401.00869, Apr 2023

   Bib

   @article{lei2023flashvideo,
     url = {https://arxiv.org/abs/2401.00869},
     title = {Flashvideo: A framework for swift inference in text-to-video generation},
     author = {Lei, Bin and Ding, Caiwen and others},
     journal = {arXiv preprint arXiv:2401.00869},
     year = {2023}
   }

9. [Preprint] Dataracebench v1. 4.1 and dataracebench-ml v0. 1: Benchmark suites for data race detection

   Le Chen, Wenhao Wu, Stephen F Siegel, Pei-Hung Lin, and Chunhua Liao

   arXiv preprint arXiv:2308.08473, Apr 2023

   Bib

   @article{chen2023dataracebench,
     url = {https://arxiv.org/abs/2308.08473},
     title = {Dataracebench v1. 4.1 and dataracebench-ml v0. 1: Benchmark suites for data race detection},
     author = {Chen, Le and Wu, Wenhao and Siegel, Stephen F and Lin, Pei-Hung and Liao, Chunhua},
     journal = {arXiv preprint arXiv:2308.08473},
     year = {2023}
   }

2022

1. [IPDPSW’22] Multi-View Learning for Parallelism Discovery of Sequential Programs

   Le Chen, Quazi Ishtiaque Mahmud, and Ali Jannesari

   In IEEE International Parallel and Distributed Processing Symposium, IPDPS Workshops 2022, Lyon, France, May 30 - June 3, 2022, Apr 2022

   DOI Bib

   @inproceedings{chen2022multi,
     author = {Chen, Le and Mahmud, Quazi Ishtiaque and Jannesari, Ali},
     title = {Multi-View Learning for Parallelism Discovery of Sequential Programs},
     booktitle = {{IEEE} International Parallel and Distributed Processing Symposium,
                       {IPDPS} Workshops 2022, Lyon, France, May 30 - June 3, 2022},
     pages = {295--303},
     publisher = {{IEEE}},
     year = {2022},
     url = {https://doi.org/10.1109/IPDPSW55747.2022.00059},
     doi = {10.1109/IPDPSW55747.2022.00059},
     timestamp = {Mon, 03 Mar 2025 21:14:09 +0100},
     biburl = {https://dblp.org/rec/conf/ipps/ChenMJ22.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }