SAIH:A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems

扫码查看

原文链接

万方数据

外文摘要：Novel artificial intelligence(AI)technology has expedited various scientific research,e.g.,cosmology,physics,and bioinformatics,inevitably becoming a significant category of workload on high-performance computing(HPC)sys-tems.Existing AI benchmarks tend to customize well-recognized AI applications,so as to evaluate the AI performance of HPC systems under the predefined problem size,in terms of datasets and AI models.However,driven by novel AI technol-ogy,most of AI applications are evolving fast on models and datasets to achieve higher accuracy and be applicable to more scenarios.Due to the lack of scalability on the problem size,static AI benchmarks might be under competent to help un-derstand the performance trend of evolving AI applications on HPC systems,in particular,the scientific AI applications on large-scale systems.In this paper,we propose a scalable evaluation methodology(SAIH)for analyzing the AI performance trend of HPC systems with scaling the problem sizes of customized AI applications.To enable scalability,SAIH builds a set of novel mechanisms for augmenting problem sizes.As the data and model constantly scale,we can investigate the trend and range of AI performance on HPC systems,and further diagnose system bottlenecks.To verify our methodology,we augment a cosmological AI application to evaluate a real HPC system equipped with GPUs as a case study of SAIH.With data and model augment,SAIH can progressively evaluate the AI performance trend of HPC systems,e.g.,increas-ing from 5.2％to 59.6％of the peak theoretical hardware performance.The evaluation results are analyzed and summa-rized into insight findings on performance issues.For instance,we find that the AI application constantly consumes the I/O bandwidth of the shared parallel file system during its iteratively training model.If I/O contention exists,the shared parallel file system might become a bottleneck.

外文关键词：

high-performance computing(HPC)deep learningparallel computingAI framework

作者：

杜江溯、李东升、文英鹏、江嘉治、黄聃、廖湘科、卢宇彤

展开 >

作者单位：

School of Computer Science and Engineering,Sun Yat-sen University,Guangzhou 510006,China

基金：

National Natural Science Foundation of ChinaZhejiang LabProgram for Guangdong Introducing Innovative and Entrepreneurial TeamsGuangdong Provincial Natural Science Foundation of ChinaMajor Program of Guangdong Basic and Applied Research of China

项目编号：

U18114612021KC0AB042016ZT06D2112018B0303120022019B030302002

出版年：

2024

DOI：

10.1007/s11390-023-1840-y

计算机科学技术学报(英文版)

中国计算机学会

计算机科学技术学报(英文版)

CSTPCD

影响因子：0.432

ISSN：1000-9000

年,卷(期)：2024.39(2)