A novel high performance SIMD 54-bit multiply array

Zhao Lv, Shuming Chen, Yaohua Wang
{"title":"A novel high performance SIMD 54-bit multiply array","authors":"Zhao Lv, Shuming Chen, Yaohua Wang","doi":"10.1109/ICAM.2017.8242180","DOIUrl":null,"url":null,"abstract":"We present a novel SIMD multiply array for fixed-point and floating-point multiplication. To be concrete, the array supports one 54 (unsigned), one 32 or four 16 bits (signed/unsigned) operation. Based on the enhanced booth decode algorithm, the time overhead of the multiplications is reduced. The proposed intermediate result reuse strategy can reduce area overhead of the SIMD multiply array. The synthesize result shows the area can be reduced by 37% compared with the multiply without the reuse architecture.","PeriodicalId":117801,"journal":{"name":"2017 2nd IEEE International Conference on Integrated Circuits and Microsystems (ICICM)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 2nd IEEE International Conference on Integrated Circuits and Microsystems (ICICM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAM.2017.8242180","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

We present a novel SIMD multiply array for fixed-point and floating-point multiplication. To be concrete, the array supports one 54 (unsigned), one 32 or four 16 bits (signed/unsigned) operation. Based on the enhanced booth decode algorithm, the time overhead of the multiplications is reduced. The proposed intermediate result reuse strategy can reduce area overhead of the SIMD multiply array. The synthesize result shows the area can be reduced by 37% compared with the multiply without the reuse architecture.
一种新型的高性能SIMD 54位乘法阵列
提出了一种新的SIMD乘法数组,用于定点和浮点乘法。具体来说,该数组支持一个54位(无符号)、一个32位或四个16位(有符号/无符号)操作。基于改进的摊位译码算法,减少了乘法的时间开销。所提出的中间结果重用策略可以减少SIMD乘法数组的面积开销。综合结果表明,与不采用重用结构的乘法相比,其面积可减少37%。
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