Work

Data-Driven Dynamic Algorithm Dispatch with Large Language Models

Year: 2026

Type: preprint

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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2608.21584

Authors: Shah, Rushil, Lujan, Emmanuel, Alomairy, Rabab, Edelman, Alan

Institutions: MIT Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7204201371

Cites:

Cited by:

Related to: 10