Research and ACM SRC Posters Archive

VisionHPC: AI Generation of Expert-Level HPC Codes From High-Level Mathematical Abstractions


Poster Type: Research Posters

Author: Pedro Valero-Lara (Oak Ridge National Laboratory (ORNL)), Aaron Young (Oak Ridge National Laboratory (ORNL)), Mohammad Alaul Haque Monil (Oak Ridge National Laboratory (ORNL)), William Godoy (Oak Ridge National Laboratory (ORNL)), Keita Teranishi (Oak Ridge National Laboratory (ORNL)), Jeffrey Vetter (Oak Ridge National Laboratory (ORNL))

Abstract: We present VisionHPC, an agentic AI framework that generates expert-level high performance computing (HPC) code directly from high-level mathematical abstractions. Following extensive expert-guided training, it produces HPC implementations for multicore CPUs and GPUs using widely adopted parallel programming models, including OpenMP, OpenACC, and CUDA/HIP. The framework accepts images of mathematical formulations from three representative scientific domains — linear algebra, partial differential equations, and computational fluid dynamics — and translates them into efficient parallel code. Compared with state-of-the-art multimodal models, including ChatGPT, MathGPT, and Claude, VisionHPC achieves up to 12× higher correctness than the strongest baseline, reaching an average correctness exceeding 95%. These results demonstrate that AI can reliably bridge high-level mathematical descriptions and expert-quality HPC software, substantially improving productivity for scientific software development.

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


Back to Poster Archive Listing