Performance-Based and Aging-Aware Resource Allocation for Concurrent GPU Applications

Zois-Gerasimos Tasoulas, Ryan Guss, Iraklis Anagnostopoulos
{"title":"Performance-Based and Aging-Aware Resource Allocation for Concurrent GPU Applications","authors":"Zois-Gerasimos Tasoulas, Ryan Guss, Iraklis Anagnostopoulos","doi":"10.1109/DFT.2018.8602850","DOIUrl":null,"url":null,"abstract":"GPUs are an important part in the effort to overcome performance thresholds and unlock the true potential of computing as they offer increased computational capabilities and are cost efficient. Until now, GPUs are designed to execute one application at a time so the field of concurrent GPU applications is not exhaustively explored. When multiple applications that belong to different types, e.g., compute or memory intensive, are executed on the same platform concurrently, significant performance degradation and imbalances in terms of component aging may occur. These imbalances can lead to weak system reliability, further performance degradation and acceleration of failure time. In this paper, we propose a resource allocating algorithm that mitigates the aging imbalances without inserting overhead during the execution, limiting aging imbalance among Streaming Multiprocessors (SMs) to a standard deviation of 0.4%. Additionally, the proposed algorithm improves SM allocation for each application, achieving up to 33% higher throughput.","PeriodicalId":297244,"journal":{"name":"2018 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DFT.2018.8602850","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

GPUs are an important part in the effort to overcome performance thresholds and unlock the true potential of computing as they offer increased computational capabilities and are cost efficient. Until now, GPUs are designed to execute one application at a time so the field of concurrent GPU applications is not exhaustively explored. When multiple applications that belong to different types, e.g., compute or memory intensive, are executed on the same platform concurrently, significant performance degradation and imbalances in terms of component aging may occur. These imbalances can lead to weak system reliability, further performance degradation and acceleration of failure time. In this paper, we propose a resource allocating algorithm that mitigates the aging imbalances without inserting overhead during the execution, limiting aging imbalance among Streaming Multiprocessors (SMs) to a standard deviation of 0.4%. Additionally, the proposed algorithm improves SM allocation for each application, achieving up to 33% higher throughput.
基于性能和感知老化的并发GPU应用资源分配
gpu是努力克服性能阈值和释放计算真正潜力的重要组成部分,因为它们提供了更高的计算能力并且具有成本效益。到目前为止,GPU被设计为一次执行一个应用程序,因此并发GPU应用程序领域并没有被彻底探索。当属于不同类型的多个应用程序(例如,计算或内存密集型应用程序)在同一平台上并发执行时,可能会出现显著的性能下降和组件老化方面的不平衡。这些不平衡可能导致系统可靠性降低、性能进一步下降和故障时间加速。在本文中,我们提出了一种资源分配算法,该算法可以减轻老化不平衡,而不会在执行期间插入开销,将流多处理器(SMs)之间的老化不平衡限制在0.4%的标准差内。此外,该算法改进了每个应用的SM分配,实现了高达33%的吞吐量提高。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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:481959085
Book学术官方微信