Workshops Archive

More with Less: Efficient Parallel Scientific Code Translation via an Agent-Skill Workflow


Workshop: AgenticAI4HPC’26: The First International Workshop on Agentic AI for HPC

Authors: Jianuo Shen (South China University of Technology) and Pengyi Xu and Bo Zhang (Michigan Technological University)

Abstract: Translating parallel scientific codes between HPC programming frameworks is a critical but labor-intensive task. Existing LLM-based approaches rely on fixed sequential pipelines with undifferentiated repair strategies and correctness criteria that do not match scientific computing practice. We present an agent-skill framework that separates translation, compilation diagnosis, and execution validation into three autonomous agents coordinated by a verdict-driven orchestrator, routing each failure to a targeted repair skill rather than retrying blindly. An automated output check drives the self-correction loop, complemented by an offline LLM-based verification that exposes false positives escaping compiler and runtime checks. We evaluate the framework on 30 HeCBench kernels translated bidirectionally among CUDA, OpenMP, and SYCL with three open-source LLMs. Our framework attains the higher verified correctness rate in all 18 model and direction combinations over a state-of-the-art baseline while consuming up to 52.4\% fewer tokens, remaining consistent across models and directions without architectural modification.


Back to AgenticAI4HPC’26: The First International Workshop on Agentic AI for HPC Archive Listing

Back to Full Workshop Archive Listing