Conference paper · IEEE High Performance Extreme Computing… 2025
Data-Driven Dynamic Algorithm Dispatch with Large Language Models
IEEE High Performance Extreme Computing Conference (HPEC), 2025
Abstract
We introduce a large language model (LLM)-driven approach for generating dynamic algorithmic dispatch heuristics in high-performance linear algebra. By combining prompt engineering with LLaMA 3 and a curated performance database, the model learns to synthesize selection heuristics that exploit structural patterns to identify fast algorithmic choices. A case study on LU factorization demonstrates the model’s ability to replicate expert-designed strategies.
This work, developed as part of the DARPA–MIT SmartSolve project, highlights the promise of LLMs for algorithmic discovery and the development of more adaptive, fast linear algebra software.
The full text is available as a PDF.
Cite this paper
Download .bib ↓Rushil N. Shah, Emmanuel Lujan, Rabab Alomairy and Alan Edelman, “Data-Driven Dynamic Algorithm Dispatch with Large Language Models,” IEEE High Performance Extreme Computing Conference (HPEC), 2025.
@inproceedings{shah2025data,
title={Data-Driven Dynamic Algorithm Dispatch with Large Language Models},
author={Shah, Rushil N. and Lujan, Emmanuel and Alomairy, Rabab and Edelman, Alan},
booktitle={IEEE High Performance Extreme Computing Conference (HPEC)},
year={2025},
url={https://ieee-hpec.org/wp-content/uploads/2026/01/120.pdf}
}