设计一个多项式矩阵乘法的加速硬件架构

K. S. Bodani, A. Kumbhar
{"title":"设计一个多项式矩阵乘法的加速硬件架构","authors":"K. S. Bodani, A. Kumbhar","doi":"10.1109/IBSS.2015.7456663","DOIUrl":null,"url":null,"abstract":"In this project, reconfigurable hardware architecture is used for performing the polynomial matrix multiplications (PMM). Hardware architecture is designed by using the Xilinx system generator tool. System generator enables the use of the math works model-based Simulink design environment for FPGA design. For designing PMM system, Fast Fourier Transform (FFT) technique is used rather than Convolution technique, because convolution takes computational time more than FFT. It's easy to implement the generic structure of FFT. This project implements the sharpening, smoothing, blurring and Gaussian smooth application using polynomial matrix multiplication. The hardware implementation is possible by using field-programmable array architecture. This PMM system takes less time for execution and it uses less FPGA resources like number of slice registers, number of slice LUT's, the number of block RAM/FIFO and number of bonded IOBs. The architecture for computing the PMM is implemented on Virtex-5.","PeriodicalId":317804,"journal":{"name":"2015 IEEE Bombay Section Symposium (IBSS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Designing an accelerated hardware architecture for polynomial matrix multiplications\",\"authors\":\"K. S. Bodani, A. Kumbhar\",\"doi\":\"10.1109/IBSS.2015.7456663\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this project, reconfigurable hardware architecture is used for performing the polynomial matrix multiplications (PMM). Hardware architecture is designed by using the Xilinx system generator tool. System generator enables the use of the math works model-based Simulink design environment for FPGA design. For designing PMM system, Fast Fourier Transform (FFT) technique is used rather than Convolution technique, because convolution takes computational time more than FFT. It's easy to implement the generic structure of FFT. This project implements the sharpening, smoothing, blurring and Gaussian smooth application using polynomial matrix multiplication. The hardware implementation is possible by using field-programmable array architecture. This PMM system takes less time for execution and it uses less FPGA resources like number of slice registers, number of slice LUT's, the number of block RAM/FIFO and number of bonded IOBs. The architecture for computing the PMM is implemented on Virtex-5.\",\"PeriodicalId\":317804,\"journal\":{\"name\":\"2015 IEEE Bombay Section Symposium (IBSS)\",\"volume\":\"54 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 IEEE Bombay Section Symposium (IBSS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IBSS.2015.7456663\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 IEEE Bombay Section Symposium (IBSS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IBSS.2015.7456663","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

在这个项目中,可重构的硬件架构被用于执行多项式矩阵乘法(PMM)。硬件架构设计采用Xilinx系统生成工具。系统生成器能够利用基于数学模型的Simulink设计环境对FPGA进行设计。在PMM系统设计中,采用快速傅里叶变换(FFT)技术而不是卷积技术,因为卷积比FFT需要更多的计算时间。实现FFT的通用结构很容易。本课题利用多项式矩阵乘法实现了锐化、平滑、模糊和高斯平滑的应用。通过使用现场可编程阵列架构,硬件实现成为可能。这种PMM系统需要更少的时间来执行,它使用更少的FPGA资源,如片寄存器的数量,片LUT的数量,块RAM/FIFO的数量和绑定IOBs的数量。计算PMM的架构是在Virtex-5上实现的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Designing an accelerated hardware architecture for polynomial matrix multiplications
In this project, reconfigurable hardware architecture is used for performing the polynomial matrix multiplications (PMM). Hardware architecture is designed by using the Xilinx system generator tool. System generator enables the use of the math works model-based Simulink design environment for FPGA design. For designing PMM system, Fast Fourier Transform (FFT) technique is used rather than Convolution technique, because convolution takes computational time more than FFT. It's easy to implement the generic structure of FFT. This project implements the sharpening, smoothing, blurring and Gaussian smooth application using polynomial matrix multiplication. The hardware implementation is possible by using field-programmable array architecture. This PMM system takes less time for execution and it uses less FPGA resources like number of slice registers, number of slice LUT's, the number of block RAM/FIFO and number of bonded IOBs. The architecture for computing the PMM is implemented on Virtex-5.
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