Interplay between hardware prefetcher and page eviction policy in CPU-GPU unified virtual memory

Author:

Ganguly Debashis1,Zhang Ziyu1,Yang Jun1,Melhem Rami1

Affiliation:

1. University of Pittsburgh

Publisher

ACM

Reference26 articles.

1. Page Placement Strategies for GPUs within Heterogeneous Memory Systems

2. AMD. 2017. Radeons Next-generation Vega Architecture. https://radeon.com/_downloads/vega-whitepaper-11.6.17.pdf. (2017). AMD. 2017. Radeons Next-generation Vega Architecture. https://radeon.com/_downloads/vega-whitepaper-11.6.17.pdf. (2017).

3. Mosaic

4. Analyzing CUDA workloads using a detailed GPU simulator

Cited by 57 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. Harnessing Integrated CPU-GPU System Memory for HPC: a first look into Grace Hopper;Proceedings of the 53rd International Conference on Parallel Processing;2024-08-12

2. Selective Memory Compression for GPU Memory Oversubscription Management;Proceedings of the 53rd International Conference on Parallel Processing;2024-08-12

3. Shared Virtual Memory: Its Design and Performance Implications for Diverse Applications;Proceedings of the 38th ACM International Conference on Supercomputing;2024-05-30

4. GRIT: Enhancing Multi-GPU Performance with Fine-Grained Dynamic Page Placement;2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA);2024-03-02

5. Bandwidth-Effective DRAM Cache for GPU s with Storage-Class Memory;2024 IEEE International Symposium on High-Performance Computer Architecture (HPCA);2024-03-02

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