Design of multithreaded coprocessor IP core for embedded SoC chip

Dexue Zhang, Xiaoyang Zeng, Fengyu Xiao, Qingli Xiao, Lu Zheng
{"title":"Design of multithreaded coprocessor IP core for embedded SoC chip","authors":"Dexue Zhang, Xiaoyang Zeng, Fengyu Xiao, Qingli Xiao, Lu Zheng","doi":"10.1109/ICEIEC.2013.6835455","DOIUrl":null,"url":null,"abstract":"Increasing demand for high performance has impelled the development of process technology and IC design technology. Due to production technology restrictions, traditional single-core processors have encountered bottlenecks both in frequency and performance. Heterogeneous multi-core SoC, such as CPU + coprocessor + peripherals, is accepted as a cost-effective solution for the increasing computation demands in embedded system. The system performance depends on the processor frequency, the memory access rate, and the I/O access rate, but their development is unbalanced, and CPU has to wait for the response from the memory or I/O for a long time in order to continue processing. Hardware multithreading technology has been used to effectively hide memory latency and significantly increase total system performance with low cost. This paper presents a design of coprocessor IP based on altera PicaRISC multithreaded processor which can execute eight threads simultaneously using a time-slicing multithreading approach. The IP core was designed based on avalon bus, and can be easily integrated into nearly any system. The test result shows that fft3780 calculation can speed up to 9 times using 16 threads.","PeriodicalId":419767,"journal":{"name":"2013 IEEE 4th International Conference on Electronics Information and Emergency Communication","volume":"46 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE 4th International Conference on Electronics Information and Emergency Communication","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEIEC.2013.6835455","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Increasing demand for high performance has impelled the development of process technology and IC design technology. Due to production technology restrictions, traditional single-core processors have encountered bottlenecks both in frequency and performance. Heterogeneous multi-core SoC, such as CPU + coprocessor + peripherals, is accepted as a cost-effective solution for the increasing computation demands in embedded system. The system performance depends on the processor frequency, the memory access rate, and the I/O access rate, but their development is unbalanced, and CPU has to wait for the response from the memory or I/O for a long time in order to continue processing. Hardware multithreading technology has been used to effectively hide memory latency and significantly increase total system performance with low cost. This paper presents a design of coprocessor IP based on altera PicaRISC multithreaded processor which can execute eight threads simultaneously using a time-slicing multithreading approach. The IP core was designed based on avalon bus, and can be easily integrated into nearly any system. The test result shows that fft3780 calculation can speed up to 9 times using 16 threads.
嵌入式SoC芯片的多线程协处理器IP核设计
高性能需求的增长推动了工艺技术和集成电路设计技术的发展。由于生产技术的限制,传统的单核处理器在频率和性能上都遇到了瓶颈。异构多核SoC,如CPU +协处理器+外设,被认为是嵌入式系统日益增长的计算需求的一种经济有效的解决方案。系统的性能取决于处理器频率、内存访问速率和I/O访问速率,但它们的发展是不平衡的,CPU需要等待内存或I/O的响应很长时间才能继续处理。硬件多线程技术可以有效地隐藏内存延迟,以较低的成本显著提高系统的整体性能。本文提出了一种基于altera PicaRISC多线程处理器的协处理器IP的设计,该协处理器IP采用时间切片多线程方法,可同时执行8个线程。IP核是基于avalon总线设计的,可以很容易地集成到几乎任何系统中。测试结果表明,使用16个线程时,fft3780的计算速度可以提高9倍。
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:604180095
Book学术官方微信