Research and ACM SRC Posters Archive

Agentic AI Augmentation for Recursive Mixed-Precision Linear Solvers


Poster Type: ACM SRC Posters

Author: Victoria Carrica (Massachusetts Institute of Technology (MIT)), Rabab Alomairy (Massachusetts Institute of Technology (MIT)), Pedro Valero-Lara (Oak Ridge National Laboratory (ORNL)), Alan Edelman (Massachusetts Institute of Technology (MIT))

Abstract: High performance computing increasingly relies on low-precision hardware for throughput, yet scientific applications demand numerical accuracy. Recursive mixed-precision algorithms address this, but extending them to new solvers requires expert-level knowledge. This work investigates agentic AI augmentation to transfer knowledge from a recursive mixed-precision Cholesky solver to new algorithms, evaluating in-context learning (ICL) and parameter-efficient fine-tuning (PEFT), using implementations, documentation, and mathematical formulations as structured knowledge. We find that full-context ICL enables frontier LLMs to generate a high-performance recursive mixed-precision LU factorization achieving up to a 4.9x speedup over cuSOLVER FP32 on H200 GPUs while preserving accuracy, whereas PEFT memorizes the framework but fails to generalize, showing that expert-designed HPC implementations can serve as reusable knowledge for AI systems. At the poster, I will present our knowledge-transfer framework via figures comparing runtime and speedup across ICL prompting levels and models, fine-tuning accuracy results, and our recursive mixed-precision framework and future directions.

Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF


Back to Poster Archive Listing