LASSI: LLM-based Automated Self-correcting pipeline for generating parallel Scientific Codes

(Pending: introductory description.)

Please note: The codes generated from the published paper listed below will be included in this repository soon.

Also, we plan to include 'getting started' instructions and will provide an extension of the Notebook to instead run as a command line Python script.

Contact inforation: Matthew T. Dearing, University of Illinois Chicago - mdear2 (at) uic.edu

If you use LASSI in your work, then please cite the following paper:

Dearing, M. T., Tao, Y., Wu, X., Lan, Z., Taylor, V. "LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes" (accepted) International Workshop on Large Language Models and HPC (LLMxHPC), IEEE International Conference on Cluster Computing (CLUSTER) (2024). Pre-print at arXiv:2407.01638.