FPGA Implementation of RNS Adder Based MAC Unit in Ternary Value Logic Domain for Signal Processing Algorithm and its Performance Analysis

Aniruddha Ghosh, A. Sinha
{"title":"FPGA Implementation of RNS Adder Based MAC Unit in Ternary Value Logic Domain for Signal Processing Algorithm and its Performance Analysis","authors":"Aniruddha Ghosh, A. Sinha","doi":"10.1109/EDKCON.2018.8770463","DOIUrl":null,"url":null,"abstract":"Digital signal processing (DSP) based applications are designed using various types of DSP algorithms which are computationally intensive. So, DSP-based applications widely utilize Multiply-Accumulate (MA C) operation for accomplishing speed. In contrast with the binary number system, Residue Number Systems (RNS) is considered to be more prominent because of their abilities of carrying out carry-free arithmetic operations like addition, subtraction. Ternary value logic (TVL) offers several advantages like reduced chip area as well as overall delay, over conventional binary number system. Designing superior adder and multiplier have become the major concern for implementing high performance signal processing applications. To improve the performance of MA C unit, a new architecture is proposed in this paper. In this paper, MA C unit is implemented using ternary multiplier and RNS adder in TVL domain. The major bottleneck of TVL to RNS conversion and vice versa has introduced huge complexity which leads to decreased efficiency of performance due to large conversion time. The performance of RNS based system can be enhanced by choosing relative prime moduli set as improper selection of moduli will affect system speed, dynamic range and hardware complexity. Proposed MAC unit is mapped on field programmable gate array (FPGA) for analysis its performance.","PeriodicalId":344143,"journal":{"name":"2018 IEEE Electron Devices Kolkata Conference (EDKCON)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE Electron Devices Kolkata Conference (EDKCON)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EDKCON.2018.8770463","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

Abstract

Digital signal processing (DSP) based applications are designed using various types of DSP algorithms which are computationally intensive. So, DSP-based applications widely utilize Multiply-Accumulate (MA C) operation for accomplishing speed. In contrast with the binary number system, Residue Number Systems (RNS) is considered to be more prominent because of their abilities of carrying out carry-free arithmetic operations like addition, subtraction. Ternary value logic (TVL) offers several advantages like reduced chip area as well as overall delay, over conventional binary number system. Designing superior adder and multiplier have become the major concern for implementing high performance signal processing applications. To improve the performance of MA C unit, a new architecture is proposed in this paper. In this paper, MA C unit is implemented using ternary multiplier and RNS adder in TVL domain. The major bottleneck of TVL to RNS conversion and vice versa has introduced huge complexity which leads to decreased efficiency of performance due to large conversion time. The performance of RNS based system can be enhanced by choosing relative prime moduli set as improper selection of moduli will affect system speed, dynamic range and hardware complexity. Proposed MAC unit is mapped on field programmable gate array (FPGA) for analysis its performance.
基于RNS加法器的三值逻辑域MAC单元信号处理算法的FPGA实现及性能分析
基于数字信号处理(DSP)的应用程序是使用各种类型的DSP算法设计的,这些算法是计算密集型的。因此,基于dsp的应用广泛采用乘法累加运算来实现速度。与二进制数系统相比,剩余数系统(RNS)被认为更突出,因为它们能够进行加法、减法等无进位算术运算。与传统的二进制数字系统相比,三元值逻辑(TVL)具有诸如减少芯片面积以及总体延迟等优点。设计优质的加法器和乘法器已成为实现高性能信号处理应用的主要关注点。为了提高mc单元的性能,本文提出了一种新的结构。本文在TVL域使用三元乘法器和RNS加法器实现了MA - C单元。TVL到RNS转换的主要瓶颈(反之亦然)引入了巨大的复杂性,由于转换时间长,导致性能效率下降。选择相对素模集可以提高基于RNS的系统的性能,因为模集的选择不当会影响系统的速度、动态范围和硬件复杂度。将所提出的MAC单元映射到现场可编程门阵列(FPGA)上,分析其性能。
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