Comparison of reconfigurable structures for flexible word-length multiplication

O. A. Pfänder, R. Nopper, H. J. Pfleiderer, S. Zhou, Amine Bermak

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Binary multiplication continues to be one of the essential arithmetic operations in digital circuits. Even though field-programmable gate arrays (FPGAs) are becoming more and more powerful these days, the vendors cannot avoid implementing multiplications with high word-lengths using embedded blocks instead of configurable logic. But on the other hand, the circuit's efficiency decreases if the provided word-length of the hard-wired multipliers exceeds the precision requirements of the algorithm mapped into the FPGA. Thus it is beneficial to use multiplier blocks with configurable word-length, optimized for area, speed and power dissipation, e.g. regarding digital signal processing (DSP) applications. In this contribution, we present different approaches and structures for the realization of a multiplication with variable precision and perform an objective comparison. This includes one approach based on a modified Baugh and Wooley algorithm and three structures using Booth's arithmetic operand recoding with different array structures. All modules have the option to compute signed two's complement fix-point numbers either as an individual computing unit or interconnected to a superior array. Therefore, a high throughput at low precision through parallelism, or a high precision through concatenation can be achieved.

Original languageEnglish
Pages (from-to)113-118
Number of pages6
JournalAdvances in Radio Science
Volume6
Publication statusPublished - 2008
Externally publishedYes

Fingerprint

Field programmable gate arrays (FPGA)
Digital circuits
Digital signal processing
Energy dissipation
Throughput
Networks (circuits)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Pfänder, O. A., Nopper, R., Pfleiderer, H. J., Zhou, S., & Bermak, A. (2008). Comparison of reconfigurable structures for flexible word-length multiplication. Advances in Radio Science, 6, 113-118.

Comparison of reconfigurable structures for flexible word-length multiplication. / Pfänder, O. A.; Nopper, R.; Pfleiderer, H. J.; Zhou, S.; Bermak, Amine.

In: Advances in Radio Science, Vol. 6, 2008, p. 113-118.

Research output: Contribution to journalArticle

Pfänder, OA, Nopper, R, Pfleiderer, HJ, Zhou, S & Bermak, A 2008, 'Comparison of reconfigurable structures for flexible word-length multiplication', Advances in Radio Science, vol. 6, pp. 113-118.
Pfänder, O. A. ; Nopper, R. ; Pfleiderer, H. J. ; Zhou, S. ; Bermak, Amine. / Comparison of reconfigurable structures for flexible word-length multiplication. In: Advances in Radio Science. 2008 ; Vol. 6. pp. 113-118.
@article{cc733992b3d140429c5f0c1661273891,
title = "Comparison of reconfigurable structures for flexible word-length multiplication",
abstract = "Binary multiplication continues to be one of the essential arithmetic operations in digital circuits. Even though field-programmable gate arrays (FPGAs) are becoming more and more powerful these days, the vendors cannot avoid implementing multiplications with high word-lengths using embedded blocks instead of configurable logic. But on the other hand, the circuit's efficiency decreases if the provided word-length of the hard-wired multipliers exceeds the precision requirements of the algorithm mapped into the FPGA. Thus it is beneficial to use multiplier blocks with configurable word-length, optimized for area, speed and power dissipation, e.g. regarding digital signal processing (DSP) applications. In this contribution, we present different approaches and structures for the realization of a multiplication with variable precision and perform an objective comparison. This includes one approach based on a modified Baugh and Wooley algorithm and three structures using Booth's arithmetic operand recoding with different array structures. All modules have the option to compute signed two's complement fix-point numbers either as an individual computing unit or interconnected to a superior array. Therefore, a high throughput at low precision through parallelism, or a high precision through concatenation can be achieved.",
author = "Pf{\"a}nder, {O. A.} and R. Nopper and Pfleiderer, {H. J.} and S. Zhou and Amine Bermak",
year = "2008",
language = "English",
volume = "6",
pages = "113--118",
journal = "Advances in Radio Science",
issn = "1684-9965",
publisher = "Copernicus",

}

TY - JOUR

T1 - Comparison of reconfigurable structures for flexible word-length multiplication

AU - Pfänder, O. A.

AU - Nopper, R.

AU - Pfleiderer, H. J.

AU - Zhou, S.

AU - Bermak, Amine

PY - 2008

Y1 - 2008

N2 - Binary multiplication continues to be one of the essential arithmetic operations in digital circuits. Even though field-programmable gate arrays (FPGAs) are becoming more and more powerful these days, the vendors cannot avoid implementing multiplications with high word-lengths using embedded blocks instead of configurable logic. But on the other hand, the circuit's efficiency decreases if the provided word-length of the hard-wired multipliers exceeds the precision requirements of the algorithm mapped into the FPGA. Thus it is beneficial to use multiplier blocks with configurable word-length, optimized for area, speed and power dissipation, e.g. regarding digital signal processing (DSP) applications. In this contribution, we present different approaches and structures for the realization of a multiplication with variable precision and perform an objective comparison. This includes one approach based on a modified Baugh and Wooley algorithm and three structures using Booth's arithmetic operand recoding with different array structures. All modules have the option to compute signed two's complement fix-point numbers either as an individual computing unit or interconnected to a superior array. Therefore, a high throughput at low precision through parallelism, or a high precision through concatenation can be achieved.

AB - Binary multiplication continues to be one of the essential arithmetic operations in digital circuits. Even though field-programmable gate arrays (FPGAs) are becoming more and more powerful these days, the vendors cannot avoid implementing multiplications with high word-lengths using embedded blocks instead of configurable logic. But on the other hand, the circuit's efficiency decreases if the provided word-length of the hard-wired multipliers exceeds the precision requirements of the algorithm mapped into the FPGA. Thus it is beneficial to use multiplier blocks with configurable word-length, optimized for area, speed and power dissipation, e.g. regarding digital signal processing (DSP) applications. In this contribution, we present different approaches and structures for the realization of a multiplication with variable precision and perform an objective comparison. This includes one approach based on a modified Baugh and Wooley algorithm and three structures using Booth's arithmetic operand recoding with different array structures. All modules have the option to compute signed two's complement fix-point numbers either as an individual computing unit or interconnected to a superior array. Therefore, a high throughput at low precision through parallelism, or a high precision through concatenation can be achieved.

UR - http://www.scopus.com/inward/record.url?scp=67749149017&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67749149017&partnerID=8YFLogxK

M3 - Article

VL - 6

SP - 113

EP - 118

JO - Advances in Radio Science

JF - Advances in Radio Science

SN - 1684-9965

ER -