LM4HPC: Towards Effective Language Model Application in High-Performance Computing

被引：11

作者：

Chen, Le ^{[1
,2
]}

Lin, Pei-Hung ^{[1
]}

Vanderbruggen, Tristan ^{[1
]}

Liao, Chunhua ^{[1
]}

Emani, Murali ^{[3
]}

de Supinski, Bronis ^{[1
]}

机构：

[1] Lawrence Livermore Natl Lab, Livermore, CA 94550 USA

[2] Iowa State Univ, Ames, IA 50010 USA

[3] Argonne Natl Lab, Lemont, IL 60439 USA

来源：

OPENMP: ADVANCED TASK-BASED, DEVICE AND COMPILER PROGRAMMING, IWOMP 2023 | 2023年 / 14114卷

关键词：

Language model; Programming language processing; High-performance computing;

D O I：

10.1007/978-3-031-40744-4_2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：18 / 33

页数：16

共 28 条

[1]

[Anonymous], 2023, The PY-tree-sitter project

[2]

Armengol-estape Jordi, 2022, MAPS 2022: Proceedings of the 6th ACM SIGPLAN International Symposium on Machine Programming, P50, DOI 10.1145/3520312.3534867

[3]

Brown TB, 2020, ADV NEUR IN, V33

[4]

Bubeck S, 2023, Arxiv, DOI [arXiv:2303.12712, DOI 10.48550/ARXIV.2303.12712]

[5]

Chase H., 2023, LangChain: Next Generation Language Processing

[6]

Che SA, 2009, I S WORKL CHAR PROC, P44, DOI 10.1109/IISWC.2009.5306797

[7]

Chen L, 2023, Arxiv, DOI arXiv:2305.05779

[8] Multi-View Learning for Parallelism Discovery of Sequential Programs [J].

Chen, Le ;

Mahmud, Quazi Ishtiaque ;

Jannesari, Ali .

2022 IEEE 36TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW 2022), 2022, :295-303

[9]

Chen M., 2021, arXiv

[10] Early Experience with Transformer-Based Similarity Analysis for DataRaceBench [J].

Chen, Winson ;

Vanderbruggen, Tristan ;

Lin, Pei-Hung ;

Liao, Chunhua ;

Emani, Murali .

2022 IEEE/ACM SIXTH INTERNATIONAL WORKSHOP ON SOFTWARE CORRECTNESS FOR HPC APPLICATIONS (CORRECTNESS), 2022, :45-53

← 1 2 3 →