带重排序的MSIMD系统仿真

H. Karatza
{"title":"带重排序的MSIMD系统仿真","authors":"H. Karatza","doi":"10.1109/MPCS.1994.367060","DOIUrl":null,"url":null,"abstract":"In this work we study the performance of a multi-processor system model which executes multiple SIMD jobs. Such a parallel computer organization contains multiple Control units (CUs) which share a resource pool of a finite number of Processing Elements (PEs) and operates multiple single-instruction-multiple-data streams (MSIMD). We assume that after the CUs service, resequencing of SIMD jobs takes place which ensures that jobs leave the processing unit on a first-in-first-out basis. A closed queueing network model of a MSIMD computer system is simulated. The performance of two different queueing disciplines in conjunction with the effect of the resequencing delay is investigated for various degrees of multiprogramming and coefficients of variation of the CUs service times.<<ETX>>","PeriodicalId":64175,"journal":{"name":"专用汽车","volume":"62 1","pages":"339-342"},"PeriodicalIF":0.0000,"publicationDate":"1994-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Simulation of a MSIMD system with resequencing\",\"authors\":\"H. Karatza\",\"doi\":\"10.1109/MPCS.1994.367060\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work we study the performance of a multi-processor system model which executes multiple SIMD jobs. Such a parallel computer organization contains multiple Control units (CUs) which share a resource pool of a finite number of Processing Elements (PEs) and operates multiple single-instruction-multiple-data streams (MSIMD). We assume that after the CUs service, resequencing of SIMD jobs takes place which ensures that jobs leave the processing unit on a first-in-first-out basis. A closed queueing network model of a MSIMD computer system is simulated. The performance of two different queueing disciplines in conjunction with the effect of the resequencing delay is investigated for various degrees of multiprogramming and coefficients of variation of the CUs service times.<<ETX>>\",\"PeriodicalId\":64175,\"journal\":{\"name\":\"专用汽车\",\"volume\":\"62 1\",\"pages\":\"339-342\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1994-05-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"专用汽车\",\"FirstCategoryId\":\"1087\",\"ListUrlMain\":\"https://doi.org/10.1109/MPCS.1994.367060\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"专用汽车","FirstCategoryId":"1087","ListUrlMain":"https://doi.org/10.1109/MPCS.1994.367060","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在本工作中,我们研究了执行多个SIMD作业的多处理器系统模型的性能。这种并行计算机组织包含多个控制单元(cu),它们共享有限数量的处理元素(pe)的资源池,并操作多个单指令多数据流(MSIMD)。我们假设在cu服务之后,会对SIMD作业进行重新排序,从而确保作业以先进先出的方式离开处理单元。对MSIMD计算机系统的封闭排队网络模型进行了仿真。在不同程度的多路规划和cu服务时间变异系数下,研究了两种不同排队规则的性能以及重排序延迟的影响。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Simulation of a MSIMD system with resequencing
In this work we study the performance of a multi-processor system model which executes multiple SIMD jobs. Such a parallel computer organization contains multiple Control units (CUs) which share a resource pool of a finite number of Processing Elements (PEs) and operates multiple single-instruction-multiple-data streams (MSIMD). We assume that after the CUs service, resequencing of SIMD jobs takes place which ensures that jobs leave the processing unit on a first-in-first-out basis. A closed queueing network model of a MSIMD computer system is simulated. The performance of two different queueing disciplines in conjunction with the effect of the resequencing delay is investigated for various degrees of multiprogramming and coefficients of variation of the CUs service times.<>
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
自引率
0.00%
发文量
8000
×
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