在异构嵌入式设备上平衡吞吐量和多 DNN 工作负载的公平执行

IF 5.4 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Andreas Karatzas;Iraklis Anagnostopoulos
{"title":"在异构嵌入式设备上平衡吞吐量和多 DNN 工作负载的公平执行","authors":"Andreas Karatzas;Iraklis Anagnostopoulos","doi":"10.1109/TETC.2024.3407055","DOIUrl":null,"url":null,"abstract":"The rise of Deep Neural Networks (DNNs) has resulted in complex workloads employing multiple DNNs concurrently. This trend introduces unique challenges related to workload distribution, particularly in heterogeneous embedded systems. Current run-time managers struggle to efficiently utilize all computing components on these platforms, resulting in two major problems. First, the system throughput deteriorates due to contention on the computing resources. Second, not all DNNs are affected equally, leading to inconsistent performance levels across different models. To address these challenges, we introduce FairBoost, a framework for efficient and fair multi-DNN inference on heterogeneous embedded systems. FairBoost employs Reinforcement Learning (RL) to efficiently manage multi-DNN workloads. Additionally, it incorporates a novel numerical representation of DNN layers via a Vector Quantized Variational Auto-Encoder (VQ-VAE). Finally, it enables knowledge transfer to similar heterogeneous embedded systems without retraining and/or fine-tuning. Experimental evaluation of FairBoost over 18 DNNs and various multi-DNN scenarios shows an average throughput/fairness improvement of <inline-formula><tex-math>$\\times 3.24$</tex-math></inline-formula>. Additionally, FairBoost facilitates knowledge transfer from the initial platform, Orange Pi 5, to a new system, Odroid N2+, without any retraining or fine-tuning achieving similar gains.","PeriodicalId":13156,"journal":{"name":"IEEE Transactions on Emerging Topics in Computing","volume":"13 2","pages":"409-422"},"PeriodicalIF":5.4000,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Balancing Throughput and Fair Execution of Multi-DNN Workloads on Heterogeneous Embedded Devices\",\"authors\":\"Andreas Karatzas;Iraklis Anagnostopoulos\",\"doi\":\"10.1109/TETC.2024.3407055\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The rise of Deep Neural Networks (DNNs) has resulted in complex workloads employing multiple DNNs concurrently. This trend introduces unique challenges related to workload distribution, particularly in heterogeneous embedded systems. Current run-time managers struggle to efficiently utilize all computing components on these platforms, resulting in two major problems. First, the system throughput deteriorates due to contention on the computing resources. Second, not all DNNs are affected equally, leading to inconsistent performance levels across different models. To address these challenges, we introduce FairBoost, a framework for efficient and fair multi-DNN inference on heterogeneous embedded systems. FairBoost employs Reinforcement Learning (RL) to efficiently manage multi-DNN workloads. Additionally, it incorporates a novel numerical representation of DNN layers via a Vector Quantized Variational Auto-Encoder (VQ-VAE). Finally, it enables knowledge transfer to similar heterogeneous embedded systems without retraining and/or fine-tuning. Experimental evaluation of FairBoost over 18 DNNs and various multi-DNN scenarios shows an average throughput/fairness improvement of <inline-formula><tex-math>$\\\\times 3.24$</tex-math></inline-formula>. Additionally, FairBoost facilitates knowledge transfer from the initial platform, Orange Pi 5, to a new system, Odroid N2+, without any retraining or fine-tuning achieving similar gains.\",\"PeriodicalId\":13156,\"journal\":{\"name\":\"IEEE Transactions on Emerging Topics in Computing\",\"volume\":\"13 2\",\"pages\":\"409-422\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2024-06-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Emerging Topics in Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10551717/\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Emerging Topics in Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10551717/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

深度神经网络(dnn)的兴起导致了同时使用多个dnn的复杂工作负载。这种趋势带来了与工作负载分布相关的独特挑战,特别是在异构嵌入式系统中。当前的运行时管理器很难有效地利用这些平台上的所有计算组件,这导致了两个主要问题。首先,由于计算资源的争用,导致系统吞吐量下降。其次,并非所有dnn都受到相同的影响,导致不同模型的性能水平不一致。为了解决这些挑战,我们引入了FairBoost,这是一个在异构嵌入式系统上高效公平的多深度神经网络推理框架。FairBoost采用强化学习(RL)来有效地管理多深度神经网络工作负载。此外,它通过矢量量化变分自编码器(VQ-VAE)集成了DNN层的新颖数值表示。最后,它可以将知识转移到类似的异构嵌入式系统中,而无需再培训和/或微调。FairBoost在18个dnn和各种多dnn场景下的实验评估显示,平均吞吐量/公平性提高了3.24倍。此外,FairBoost还有助于将知识从初始平台Orange Pi 5转移到新系统Odroid N2+,无需再培训或微调即可获得类似的收益。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Balancing Throughput and Fair Execution of Multi-DNN Workloads on Heterogeneous Embedded Devices
The rise of Deep Neural Networks (DNNs) has resulted in complex workloads employing multiple DNNs concurrently. This trend introduces unique challenges related to workload distribution, particularly in heterogeneous embedded systems. Current run-time managers struggle to efficiently utilize all computing components on these platforms, resulting in two major problems. First, the system throughput deteriorates due to contention on the computing resources. Second, not all DNNs are affected equally, leading to inconsistent performance levels across different models. To address these challenges, we introduce FairBoost, a framework for efficient and fair multi-DNN inference on heterogeneous embedded systems. FairBoost employs Reinforcement Learning (RL) to efficiently manage multi-DNN workloads. Additionally, it incorporates a novel numerical representation of DNN layers via a Vector Quantized Variational Auto-Encoder (VQ-VAE). Finally, it enables knowledge transfer to similar heterogeneous embedded systems without retraining and/or fine-tuning. Experimental evaluation of FairBoost over 18 DNNs and various multi-DNN scenarios shows an average throughput/fairness improvement of $\times 3.24$. Additionally, FairBoost facilitates knowledge transfer from the initial platform, Orange Pi 5, to a new system, Odroid N2+, without any retraining or fine-tuning achieving similar gains.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Transactions on Emerging Topics in Computing
IEEE Transactions on Emerging Topics in Computing Computer Science-Computer Science (miscellaneous)
CiteScore
12.10
自引率
5.10%
发文量
113
期刊介绍: IEEE Transactions on Emerging Topics in Computing publishes papers on emerging aspects of computer science, computing technology, and computing applications not currently covered by other IEEE Computer Society Transactions. Some examples of emerging topics in computing include: IT for Green, Synthetic and organic computing structures and systems, Advanced analytics, Social/occupational computing, Location-based/client computer systems, Morphic computer design, Electronic game systems, & Health-care IT.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信