Quantifying Memory Underutilization in HPC Systems and Using it to Improve Performance via Architecture Support

Author:

Panwar Gagandeep1,Zhang Da1,Pang Yihan1,Dahshan Mai1,DeBardeleben Nathan2,Ravindran Binoy1,Jian Xun1

Affiliation:

1. Virginia Tech, Blacksburg, USA

2. Los Alamos National Laboratory, Los Alamos, USA

Funder

U.S. Department of En- ergy/National Nuclear Security Administration

Office of Naval Research

National Science Foundation

Publisher

ACM

Reference80 articles.

1. [n. d.]. Graph500. https://graph500.org/. [n. d.]. Graph500. https://graph500.org/.

2. [n. d.]. LANL CTS-1 Grizzly - Tundra Extreme Scale Xeon E5-2695v4 18C 2.1GHz Intel Omni-Path. https://www.top500.org/system/178972. [n. d.]. LANL CTS-1 Grizzly - Tundra Extreme Scale Xeon E5-2695v4 18C 2.1GHz Intel Omni-Path. https://www.top500.org/system/178972.

3. [n. d.]. LINPACK. http://www.netlib.org/linpack/. [n. d.]. LINPACK. http://www.netlib.org/linpack/.

4. 2017. Advanced Configuration and Power Interface Specification Version 6.2. https://uefi.org/sites/default/files/resources/ACPI_6_2.pdf. 2017. Advanced Configuration and Power Interface Specification Version 6.2. https://uefi.org/sites/default/files/resources/ACPI_6_2.pdf.

Cited by 19 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. DyLeCT: Achieving Huge-page-like Translation Performance for Hardware-compressed Memory;2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA);2024-06-29

2. Software Resource Disaggregation for HPC with Serverless Computing;2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS);2024-05-27

3. Agile-DRAM: Agile Trade-Offs in Memory Capacity, Latency, and Energy for Data Centers;2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA);2024-03-02

4. Novel Representation Learning Technique Using Graphs for Performance Analytics;2023 International Conference on Machine Learning and Applications (ICMLA);2023-12-15

5. Dynamic Memory Provisioning on Disaggregated HPC Systems;Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis;2023-11-12

同舟云学术

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

"同舟云学术"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,当前同舟云学术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 © 2019-2024 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