迷你线程:增加小规模SMT处理器上的TLP

Joshua Redstone, S. Eggers, H. Levy
{"title":"迷你线程:增加小规模SMT处理器上的TLP","authors":"Joshua Redstone, S. Eggers, H. Levy","doi":"10.1109/HPCA.2003.1183521","DOIUrl":null,"url":null,"abstract":"Several manufacturers have recently announced the first simultaneous-multithreaded processors, both as single CPU and as components of multi-CPU chips. All are small scale, comprising only two to four thread contexts. A significant impediment to the construction of larger-scale SMT is the register file size required by a large number of contexts. This paper introduces and evaluates mini-threads, a simple extension to SMT that increases thread-level parallelism without the commensurate increase in register file size. A mini-threaded SMT CPU adds additional per-thread state to each hardware context; an application executing in a context can create mini-threads that will utilize its own per-thread state, but share the context's architectural register set. The resulting performance will depend on the benefits of additional TLP compared to the costs of executing mini-threads with fewer registers. Our results quantify these factors in detail and demonstrate that mini-threads can improve performance significantly, particularly on small-scale, space-sensitive CPU designs.","PeriodicalId":150992,"journal":{"name":"The Ninth International Symposium on High-Performance Computer Architecture, 2003. HPCA-9 2003. Proceedings.","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2003-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"27","resultStr":"{\"title\":\"Mini-threads: increasing TLP on small-scale SMT processors\",\"authors\":\"Joshua Redstone, S. Eggers, H. Levy\",\"doi\":\"10.1109/HPCA.2003.1183521\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Several manufacturers have recently announced the first simultaneous-multithreaded processors, both as single CPU and as components of multi-CPU chips. All are small scale, comprising only two to four thread contexts. A significant impediment to the construction of larger-scale SMT is the register file size required by a large number of contexts. This paper introduces and evaluates mini-threads, a simple extension to SMT that increases thread-level parallelism without the commensurate increase in register file size. A mini-threaded SMT CPU adds additional per-thread state to each hardware context; an application executing in a context can create mini-threads that will utilize its own per-thread state, but share the context's architectural register set. The resulting performance will depend on the benefits of additional TLP compared to the costs of executing mini-threads with fewer registers. Our results quantify these factors in detail and demonstrate that mini-threads can improve performance significantly, particularly on small-scale, space-sensitive CPU designs.\",\"PeriodicalId\":150992,\"journal\":{\"name\":\"The Ninth International Symposium on High-Performance Computer Architecture, 2003. HPCA-9 2003. Proceedings.\",\"volume\":\"28 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2003-02-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"27\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The Ninth International Symposium on High-Performance Computer Architecture, 2003. HPCA-9 2003. Proceedings.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HPCA.2003.1183521\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Ninth International Symposium on High-Performance Computer Architecture, 2003. HPCA-9 2003. Proceedings.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HPCA.2003.1183521","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 27

摘要

几家制造商最近宣布了第一款同步多线程处理器,既可以作为单个CPU,也可以作为多CPU芯片的组件。所有这些都是小规模的,只包含两到四个线程上下文。构建大规模SMT的一个重要障碍是大量上下文所需的寄存器文件大小。本文介绍并评估了迷你线程,这是SMT的一种简单扩展,可以在不相应地增加寄存器文件大小的情况下提高线程级并行性。迷你线程SMT CPU为每个硬件上下文添加了额外的每个线程状态;在上下文中执行的应用程序可以创建微型线程,这些线程将利用自己的每个线程状态,但共享上下文的体系结构寄存器集。最终的性能将取决于额外的TLP带来的好处与使用更少的寄存器执行迷你线程的成本相比。我们的结果详细地量化了这些因素,并证明了迷你线程可以显著提高性能,特别是在小型、空间敏感的CPU设计上。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Mini-threads: increasing TLP on small-scale SMT processors
Several manufacturers have recently announced the first simultaneous-multithreaded processors, both as single CPU and as components of multi-CPU chips. All are small scale, comprising only two to four thread contexts. A significant impediment to the construction of larger-scale SMT is the register file size required by a large number of contexts. This paper introduces and evaluates mini-threads, a simple extension to SMT that increases thread-level parallelism without the commensurate increase in register file size. A mini-threaded SMT CPU adds additional per-thread state to each hardware context; an application executing in a context can create mini-threads that will utilize its own per-thread state, but share the context's architectural register set. The resulting performance will depend on the benefits of additional TLP compared to the costs of executing mini-threads with fewer registers. Our results quantify these factors in detail and demonstrate that mini-threads can improve performance significantly, particularly on small-scale, space-sensitive CPU designs.
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
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