LM4HPC: Towards Effective Language Model Application in High-Performance Computing
This work addresses the problem of integrating language models into HPC software analysis for researchers and developers, but it is incremental as it builds on existing tools and APIs.
The paper tackles the challenge of applying language models to high-performance computing (HPC) software analysis and optimization by designing the LM4HPC framework, which facilitates research and development with HPC-specific support and shows it can help users quickly evaluate state-of-the-art models and generate insightful leaderboards.
In recent years, language models (LMs), such as GPT-4, have been widely used in multiple domains, including natural language processing, visualization, and so on. However, applying them for analyzing and optimizing high-performance computing (HPC) software is still challenging due to the lack of HPC-specific support. In this paper, we design the LM4HPC framework to facilitate the research and development of HPC software analyses and optimizations using LMs. Tailored for supporting HPC datasets, AI models, and pipelines, our framework is built on top of a range of components from different levels of the machine learning software stack, with Hugging Face-compatible APIs. Using three representative tasks, we evaluated the prototype of our framework. The results show that LM4HPC can help users quickly evaluate a set of state-of-the-art models and generate insightful leaderboards.