--- format: "aidr-story-markdown/v1" id: "623bfefcef89120183c6c1caced482c29533acff8cefbe8e8f5d6171a41c8f20" canonical_url: "https://aidr.today/623bfefc?lang=en" title: "AI-Assisted GPU Porting of a 250k Line Legacy Weather Simulation Code" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-08-15T22:41:51.000Z" category: "Infra" topics: ["gpu","porting","legacy-code"] source_urls: ["https://arxiv.org/abs/2608.13122"] summary: "Recent advances in large language models have made CLI-based AI agents a practical tool for accelerating GPU porting of large legacy scientific applications. Such applications, however, are not merely old code bases; they are scientific assets whose credibility has been accumulated through long-term development, comparison with observations, and use in domain studies. GPU porting must therefore preserve this scientific validity while adapting the implementation to GPU-centric HPC systems. This paper presents a validation-centric AI-assisted GPU porting workflow through a case study of CReSS, a legacy Fortran weather simulation code with more than 250,000 lines. The workflow uses an AI agent to extract OpenMP regions, generate dump-based kernel benchmarks from physically meaningful simulation states, apply OpenACC transformations, and validate results through element-wise comparison with dumped reference data and application-level validation. Using a real typhoon simulation, the workflow produced numerically validated GPU implementations for 162 target kernels and achieved a 5.1x application-level speedup within practical wall-clock development cost. In particular, it detected nume…" --- # AI\-Assisted GPU Porting of a 250k Line Legacy Weather Simulation Code > [Open the canonical story]() **Published:** 2026-08-15T22:41:51.000Z **Category:** Infra **Topics:** gpu, porting, legacy\-code ## Summary Recent advances in large language models have made CLI\-based AI agents a practical tool for accelerating GPU porting of large legacy scientific applications\. Such applications, however, are not merely old code bases; they are scientific assets whose credibility has been accumulated through long\-term development, comparison with observations, and use in domain studies\. GPU porting must therefore preserve this scientific validity while adapting the implementation to GPU\-centric HPC systems\. This paper presents a validation\-centric AI\-assisted GPU porting workflow through a case study of CReSS, a legacy Fortran weather simulation code with more than 250,000 lines\. The workflow uses an AI agent to extract OpenMP regions, generate dump\-based kernel benchmarks from physically meaningful simulation states, apply OpenACC transformations, and validate results through element\-wise comparison with dumped reference data and application\-level validation\. Using a real typhoon simulation, the workflow produced numerically validated GPU implementations for 162 target kernels and achieved a 5\.1x application\-level speedup within practical wall\-clock development cost\. In particular, it detected nume… ## Sources - [Story source]()