Structuring agentic AI for HPC code modernization

arXiv:2606.08710 · cs.SE, cs.AI · Submitted 2026-06-07 · Read on arXiv

cs.SE, cs.AI

Submitted: 2026-06-07

Updated: 2026-06-07

Comments: 10 pages

Journal ref: USRSE'26 Conference Proceedings (2026)

License: http://creativecommons.org/licenses/by-sa/4.0/

The gist: Modernization of legacy scientific codes is often necessary to keep up with the ever-evolving changes in the compute resource ecosystem.

Terminology

Agentic AI — 5× in this paper · explained in 1 episode
Fidelity — 5× in this paper · explained in 2 episodes
Core — 4× in this paper · explained in 2 episodes
Reproducing Kernel Particle Method — 4× in this paper
AI Agents — 3× in this paper · explained in 2 episodes
Large Language Model (LLM) — 3× in this paper · explained in 3 episodes
Message Passing Interface — 2× in this paper
Abstraction — 1× in this paper · explained in 1 episode
Abundance — 1× in this paper · explained in 1 episode
Adam — 1× in this paper · explained in 2 episodes
Adaptation — 1× in this paper · explained in 1 episode
Arbiter — 1× in this paper · explained in 1 episode
Benchmark — 1× in this paper · explained in 2 episodes
Calibration — 1× in this paper · explained in 7 episodes
Finite Element Methods — 1× in this paper
Hallucination — 1× in this paper · explained in 3 episodes
Hybrid Approach — 1× in this paper · explained in 4 episodes
Inverse Design — 1× in this paper · explained in 2 episodes
Nonlinear Meshfree Analysis Program — 1× in this paper
Pruning — 1× in this paper · explained in 4 episodes
Scaffolding — 1× in this paper · explained in 3 episodes
Semantic Drift — 1× in this paper · explained in 3 episodes
Topology Optimization — 1× in this paper
While Large Language Model — 1× in this paper

Abstract

Modernization of legacy scientific codes is often necessary to keep up with the ever-evolving changes in the compute resource ecosystem. Parallelization and migration from poorly supported software ecosystems are two of the most time-consuming activities in the research software engineering field. This paper presents our experience in the successful, two-phase AI-assisted modernization of NMAP-RKPM, a roughly 60,000-line, 3D explicit solid mechanics physics engine based on the Reproducing Kernel Particle Method (RKPM). We converted this single-threaded, Fortran based MPI application into a OpenMP-parallel C++ based MPI tool in the span of a few months. While Large Language Model (LLM) based tools on their own proved inadequate, we developed a highly structured "hand-holding" agentic AI methodology, like providing manually created examples, ensuring continuous buildability and limiting session scope, that was instead highly effective. The paper provides both the AI-assisted steps that were successful and the problems that we had to overcome, alongside the reasoning behind the chosen path.

Terminology

Abstract

Related papers