A Portable Programming Interface for Performance Evaluation on Modern Processors

Author:

Browne S.1,Dongarra J.2,Garner N.1,Ho G.1,Mucci P.3

Affiliation:

1. Computer Science Department, University of Tennessee, Knoxville, Tennessee, U.S.A.

2. Computer Science Department, University of Tennessee, Knoxville, and Oak Ridge Laboratory, Tennessee, U.S.A.

3. Computer Science Department, University of Tennessee, Knoxville, Tennessee, U.S.A.,

Abstract

The purpose of the PAPI project is to specify a standard application programming interface (API) for accessing hardware performance counters available on most modern microprocessors. These counters exist as a small set of registers that count events, which are occurrences of specific signals and states related to the processor’s function. Monitoring these events facilitates correlation between the structure of source/object code and the efficiency of the mapping of that code to the underlying architecture. This correlation has a variety of uses in performance analysis, including hand tuning, compiler optimization, debugging, benchmarking, monitoring, and performance modeling. In addition, it is hoped that this information will prove useful in the development of new compilation technology as well as in steering architectural development toward alleviating commonly occurring bottlenecks in high performance computing.

Publisher

SAGE Publications

Subject

Hardware and Architecture,Theoretical Computer Science,Software

Reference9 articles.

Cited by 362 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Efficient Cross-platform Multiplexing of Hardware Performance Counters via Adaptive Grouping;ACM Transactions on Architecture and Code Optimization;2024-01-19

2. Energy consumption comparison of parallel linear systems solver algorithms on HPC infrastructure;Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis;2023-11-12

3. GPUscout: Locating Data Movement-related Bottlenecks on GPUs;Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis;2023-11-12

4. Performance Engineering for Graduate Students: a View from Amsterdam;Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis;2023-11-12

5. CLC: A cross-level program characterization method;Performance Evaluation;2023-09

全球学者库

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"全球学者库"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前全球学者库共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2023 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3