用大模型自动生成高性能计算软件包安装脚本，成功率从20%提升至80%。
LLMs as Packagers of HPC Software
- 结合代码库分析与检索，通过迭代反馈生成准确的软件包配置。
- 在308个开源软件上测试，安装成功率从20%提升至超80%。
- 适合科研人员和系统工程师快速部署复杂HPC软件环境。
高性能计算（HPC）软件生态高度异构，包含依赖数百个外部包的科学应用，每个包具有不同的构建系统、选项和依赖约束。Spack等工具可自动化依赖解析与环境管理，但其有效性依赖于手动编写的构建配方。随着生态系统扩大，维护现有配方并创建新配方日益费力。尽管大语言模型（LLMs）在代码生成方面展现出潜力，但自动生成正确且可维护的Spack配方仍具挑战。本文系统分析了LLMs与上下文增强方法在生成Spack配方中的作用。为此，我们提出SpackIt，一个端到端框架，融合仓库分析、相关示例检索及诊断反馈驱动的迭代优化。我们将SpackIt应用于308个代表性开源HPC包，评估其效果与局限性。结果表明，SpackIt将零样本设置下的安装成功率从20%提升至最佳配置下的80%以上，证明检索与结构化反馈对可靠包合成的价值。
原文摘要 · Abstract (English)
High performance computing (HPC) software ecosystems are inherently heterogeneous, comprising scientific applications that depend on hundreds of external packages, each with distinct build systems, options, and dependency constraints. Tools such as Spack automate dependency resolution and environment management, but their effectiveness relies on manually written build recipes. As these ecosystems grow, maintaining existing specifications and creating new ones becomes increasingly labor-intensive. While large language models (LLMs) have shown promise in code generation, automatically producing correct and maintainable Spack recipes remains a significant challenge. We present a systematic analysis of how LLMs and context-augmentation methods can assist in the generation of Spack recipes. To this end, we introduce SpackIt, an end-to-end framework that combines repository analysis, retrieval of relevant examples, and iterative refinement through diagnostic feedback. We apply SpackIt to a representative subset of 308 open-source HPC packages to assess its effectiveness and limitations. Our results show that SpackIt increases installation success from 20% in a zero-shot setting to over 80% in its best configuration, demonstrating the value of retrieval and structured feedback for reliable package synthesis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。