BARM: A Batch-Aware Resource Manager for Boosting Multiple Neural Networks Inference on GPUs With Memory Oversubscription
Author:
Affiliation:
1. Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan
Funder
Ministry of Science and Technology, Taiwan
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Computational Theory and Mathematics,Hardware and Architecture,Signal Processing
Link
http://xplorestaging.ieee.org/ielx7/71/9790018/09861695.pdf?arnumber=9861695
Reference51 articles.
1. Going deeper with convolutions
2. Deep Residual Learning for Image Recognition
3. E2bird: Enhanced Elastic Batch for Improving Responsiveness and Throughput of Deep Learning Services
4. SACAT: Streaming-Aware Conflict-Avoiding Thrashing-Resistant GPGPU Cache Management Scheme
5. FlexSched: Efficient scheduling techniques for concurrent kernel execution on GPUs
Cited by 2 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. Memory Reference Analysis and Implications for Executing AI Workloads in Mobile Systems;2023 International Conference on Electrical and Information Technology (IEIT);2023-09-14
2. ITIF: Integrated Transformers Inference Framework for Multiple Tenants on GPU;Proceedings of the 52nd International Conference on Parallel Processing;2023-08-07
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