# Code Translation

Translating parallel scientific code among CUDA, OpenMP and SYCL has relied on fixed sequential pipelines that apply one repair strategy to every error and judge correctness only by compilation and execution. A verdict-driven orchestrator splits translation, compilation diagnosis and execution validation into three agents and routes each failure to a patch, semantic, sync or memory repair skill. On 30 HeCBench kernels, three open-source models and six translation directions, the workflow reaches a higher verified correctness rate than LASSI in all 18 model-and-direction combinations while using up to 52.4% fewer tokens.

Translating parallel scientific code among CUDA, OpenMP and SYCL has relied on fixed sequential pipelines that apply one repair strategy to every error and judge correctness only by compilation and execution. A verdict-driven orchestrator splits translation, compilation diagnosis and execution validation into three agents and routes each failure to a patch, semantic, sync or memory repair skill. On 30 HeCBench kernels, three open-source models and six translation directions, the workflow reaches a higher verified correctness rate than LASSI in all 18 model-and-direction combinations while using up to 52.4% fewer tokens.

Four LLMs rewrote the Kessler warm-rain microphysics Fortran code into GPU-executable JAX, reproducing the Fortran reference to near floating-point precision while differing widely in GPU performance, with the fastest reaching about 357 times the speed of serial Fortran in cached GPU execution.

Four LLMs rewrote the Kessler warm-rain microphysics Fortran code into GPU-executable JAX, reproducing the Fortran reference to near floating-point precision while differing widely in GPU performance, with the fastest reaching about 357 times the speed of serial Fortran in cached GPU execution.

The work proposes collaborative human–AI agentic workflows in which domain experts write the specification and plan and agents write code under a deterministic orchestration pattern, with each stage ending in a numerical comparison against reference code and human approval; across fourteen experiments on translating MCFM from Fortran to C++, a simple author–reviewer loop with enforced limits settled a comparable number of files to a multi-agent workflow at about one-third the cost per file.

The work proposes collaborative human–AI agentic workflows in which domain experts write the specification and plan and agents write code under a deterministic orchestration pattern, with each stage ending in a numerical comparison against reference code and human approval; across fourteen experiments on translating MCFM from Fortran to C++, a simple author–reviewer loop with enforced limits settled a comparable number of files to a multi-agent workflow at about one-third the cost per file.