Matrix Odd-Even Partition: A High Power-Efficient Solution to the Small Grain Data Shuffle

Sheng Liu, Shuming Chen, Jianghua Wan, Haiyan Chen, Yaohua Wang
{"title":"Matrix Odd-Even Partition: A High Power-Efficient Solution to the Small Grain Data Shuffle","authors":"Sheng Liu, Shuming Chen, Jianghua Wan, Haiyan Chen, Yaohua Wang","doi":"10.1109/NAS.2011.29","DOIUrl":null,"url":null,"abstract":"The shuffle operation is one of the bottlenecks invector DSPs. The partitioning problem of the shuffle matrix will have a great effect on the design of the shuffle unit, when dealing with the small grain data shuffle using a smaller-sized crossbar. The traditional matrix block partitioning solution will bring much chip area, power consumption and critical path delay. This paper presents a new matrix partitioning solution: the odd-even partition, which has advantages in dealing with the data going into or out of the shuffle network. It can simplify the hardware design and improve the power efficacy of the shuffle unit in vector DSPs, compared with the matrix block partitioning solution. The principles and theorems of the odd-even partition are explained and proofed. The shuffle unit based on the odd-even partition is implemented. Some contrastive experimental results show that the odd-even partitioning solution can decrease the critical path delay by 12.2%~21.6%, reduce the hardware area by 20.9%~40.8% and cut down the power consumption by 23.5%~56.8%, compared with the matrix block partitioning solution.","PeriodicalId":263887,"journal":{"name":"2011 IEEE Sixth International Conference on Networking, Architecture, and Storage","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 IEEE Sixth International Conference on Networking, Architecture, and Storage","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NAS.2011.29","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

The shuffle operation is one of the bottlenecks invector DSPs. The partitioning problem of the shuffle matrix will have a great effect on the design of the shuffle unit, when dealing with the small grain data shuffle using a smaller-sized crossbar. The traditional matrix block partitioning solution will bring much chip area, power consumption and critical path delay. This paper presents a new matrix partitioning solution: the odd-even partition, which has advantages in dealing with the data going into or out of the shuffle network. It can simplify the hardware design and improve the power efficacy of the shuffle unit in vector DSPs, compared with the matrix block partitioning solution. The principles and theorems of the odd-even partition are explained and proofed. The shuffle unit based on the odd-even partition is implemented. Some contrastive experimental results show that the odd-even partitioning solution can decrease the critical path delay by 12.2%~21.6%, reduce the hardware area by 20.9%~40.8% and cut down the power consumption by 23.5%~56.8%, compared with the matrix block partitioning solution.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
矩阵奇偶划分:小粒度数据Shuffle的高效解决方案
shuffle操作是矢量dsp的瓶颈之一。在使用较小尺寸的交叉条处理小粒度数据shuffle时,shuffle矩阵的划分问题将对shuffle单元的设计产生很大的影响。传统的矩阵块划分方案会带来很大的芯片面积、功耗和关键路径延迟。本文提出了一种新的矩阵划分方法:奇偶划分,它在处理shuffle网络中进出的数据时具有优势。与矩阵块划分方案相比,它可以简化矢量dsp中shuffle单元的硬件设计,提高功耗效率。说明并证明了奇偶分划的原理和定理。实现了基于奇偶分区的shuffle单元。对比实验结果表明,奇偶分块方案与矩阵分块方案相比,关键路径延迟降低12.2%~21.6%,硬件面积减少20.9%~40.8%,功耗降低23.5%~56.8%。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Scalable Index Update for Block-Level Continuous Data Protection A Novel Highly Scalable Architecture with Partially Distributed Pipeline and Hardware/Software Instruction Encoding A Processor-DMA-Based Memory Copy Hardware Accelerator Supporting Efficient Memory Conflicts Reduction Using the DMA Cache Technique in Vector DSPs Applying Modified TAM to Privacy Setting Tools on SNS
wanfang
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1