Datawidth-aware energy-efficient multipliers: a case for going sign magnitude

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Downloads (Pure)

Abstract

Algorithms from many application domains, such as linear algebra and image/signal processing, heavily use the multiplication operator. Despite hardware support which is present in most modern cores, multiplication remains one of the most energy hungry arithmetic operations. This work explores how the energy efficiency of hardware multipliers can be improved by taking into account that the operands of a multiplication typically do not utilize the full width of the datapath. Seven datawidth-aware multiplier designs are implemented and evaluated. Post-layout energy analysis is performed to obtain the energy efficiency of each design for a number of representative benchmarks targeting the consumer market. The results show a significant improvement in energy efficiency compared to a 32-bit Baugh-Wooley baseline multiplier. A 32-bit sign-magnitude based design, integrated in a two's complement datapath, is shown to have a 1.38 times better energy efficiency than a baseline two's complement multiplier. In the best case (JPEG encoding), the energy efficiency is increased by a factor 2.25, demonstrating that a sign-magnitude multiplier, and datawidth-aware multipliers in general, are an attractive option for ultra low-energy designs.

Original languageEnglish
Title of host publicationProceedings - 21st Euromicro Conference on Digital System Design, DSD 2018
EditorsNikos Konofaos, Martin Novotny, Amund Skavhaug
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages54-61
Number of pages8
ISBN (Electronic)978-1-5386-7377-5
ISBN (Print)978-1-5386-7378-2
DOIs
Publication statusPublished - 12 Oct 2018
Event21st Euromicro Conference on Digital System Design, DSD 2018 - Prague, Czech Republic
Duration: 29 Aug 201831 Aug 2018
Conference number: 21
http://dsd-seaa2018.fit.cvut.cz/dsd/

Conference

Conference21st Euromicro Conference on Digital System Design, DSD 2018
Abbreviated titleDSD 2018
CountryCzech Republic
CityPrague
Period29/08/1831/08/18
Internet address

Fingerprint

Energy efficiency
Hardware
Linear algebra
Signal processing

Keywords

  • Datawidth aware
  • Energy efficiency
  • Multiplier
  • Reduced precision
  • Sign magnitude

Cite this

Waeijen, L., Jiao, H., Corporaal, H., & He, Y. (2018). Datawidth-aware energy-efficient multipliers: a case for going sign magnitude. In N. Konofaos, M. Novotny, & A. Skavhaug (Eds.), Proceedings - 21st Euromicro Conference on Digital System Design, DSD 2018 (pp. 54-61). [8491795] Piscataway: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DSD.2018.00024
Waeijen, Luc ; Jiao, Hailong ; Corporaal, Henk ; He, Yifan. / Datawidth-aware energy-efficient multipliers : a case for going sign magnitude. Proceedings - 21st Euromicro Conference on Digital System Design, DSD 2018. editor / Nikos Konofaos ; Martin Novotny ; Amund Skavhaug. Piscataway : Institute of Electrical and Electronics Engineers, 2018. pp. 54-61
@inproceedings{f1d00fa67a7246c0b2a6273c0ae4362a,
title = "Datawidth-aware energy-efficient multipliers: a case for going sign magnitude",
abstract = "Algorithms from many application domains, such as linear algebra and image/signal processing, heavily use the multiplication operator. Despite hardware support which is present in most modern cores, multiplication remains one of the most energy hungry arithmetic operations. This work explores how the energy efficiency of hardware multipliers can be improved by taking into account that the operands of a multiplication typically do not utilize the full width of the datapath. Seven datawidth-aware multiplier designs are implemented and evaluated. Post-layout energy analysis is performed to obtain the energy efficiency of each design for a number of representative benchmarks targeting the consumer market. The results show a significant improvement in energy efficiency compared to a 32-bit Baugh-Wooley baseline multiplier. A 32-bit sign-magnitude based design, integrated in a two's complement datapath, is shown to have a 1.38 times better energy efficiency than a baseline two's complement multiplier. In the best case (JPEG encoding), the energy efficiency is increased by a factor 2.25, demonstrating that a sign-magnitude multiplier, and datawidth-aware multipliers in general, are an attractive option for ultra low-energy designs.",
keywords = "Datawidth aware, Energy efficiency, Multiplier, Reduced precision, Sign magnitude",
author = "Luc Waeijen and Hailong Jiao and Henk Corporaal and Yifan He",
year = "2018",
month = "10",
day = "12",
doi = "10.1109/DSD.2018.00024",
language = "English",
isbn = "978-1-5386-7378-2",
pages = "54--61",
editor = "Nikos Konofaos and Martin Novotny and Amund Skavhaug",
booktitle = "Proceedings - 21st Euromicro Conference on Digital System Design, DSD 2018",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Waeijen, L, Jiao, H, Corporaal, H & He, Y 2018, Datawidth-aware energy-efficient multipliers: a case for going sign magnitude. in N Konofaos, M Novotny & A Skavhaug (eds), Proceedings - 21st Euromicro Conference on Digital System Design, DSD 2018., 8491795, Institute of Electrical and Electronics Engineers, Piscataway, pp. 54-61, 21st Euromicro Conference on Digital System Design, DSD 2018, Prague, Czech Republic, 29/08/18. https://doi.org/10.1109/DSD.2018.00024

Datawidth-aware energy-efficient multipliers : a case for going sign magnitude. / Waeijen, Luc; Jiao, Hailong; Corporaal, Henk; He, Yifan.

Proceedings - 21st Euromicro Conference on Digital System Design, DSD 2018. ed. / Nikos Konofaos; Martin Novotny; Amund Skavhaug. Piscataway : Institute of Electrical and Electronics Engineers, 2018. p. 54-61 8491795.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Datawidth-aware energy-efficient multipliers

T2 - a case for going sign magnitude

AU - Waeijen, Luc

AU - Jiao, Hailong

AU - Corporaal, Henk

AU - He, Yifan

PY - 2018/10/12

Y1 - 2018/10/12

N2 - Algorithms from many application domains, such as linear algebra and image/signal processing, heavily use the multiplication operator. Despite hardware support which is present in most modern cores, multiplication remains one of the most energy hungry arithmetic operations. This work explores how the energy efficiency of hardware multipliers can be improved by taking into account that the operands of a multiplication typically do not utilize the full width of the datapath. Seven datawidth-aware multiplier designs are implemented and evaluated. Post-layout energy analysis is performed to obtain the energy efficiency of each design for a number of representative benchmarks targeting the consumer market. The results show a significant improvement in energy efficiency compared to a 32-bit Baugh-Wooley baseline multiplier. A 32-bit sign-magnitude based design, integrated in a two's complement datapath, is shown to have a 1.38 times better energy efficiency than a baseline two's complement multiplier. In the best case (JPEG encoding), the energy efficiency is increased by a factor 2.25, demonstrating that a sign-magnitude multiplier, and datawidth-aware multipliers in general, are an attractive option for ultra low-energy designs.

AB - Algorithms from many application domains, such as linear algebra and image/signal processing, heavily use the multiplication operator. Despite hardware support which is present in most modern cores, multiplication remains one of the most energy hungry arithmetic operations. This work explores how the energy efficiency of hardware multipliers can be improved by taking into account that the operands of a multiplication typically do not utilize the full width of the datapath. Seven datawidth-aware multiplier designs are implemented and evaluated. Post-layout energy analysis is performed to obtain the energy efficiency of each design for a number of representative benchmarks targeting the consumer market. The results show a significant improvement in energy efficiency compared to a 32-bit Baugh-Wooley baseline multiplier. A 32-bit sign-magnitude based design, integrated in a two's complement datapath, is shown to have a 1.38 times better energy efficiency than a baseline two's complement multiplier. In the best case (JPEG encoding), the energy efficiency is increased by a factor 2.25, demonstrating that a sign-magnitude multiplier, and datawidth-aware multipliers in general, are an attractive option for ultra low-energy designs.

KW - Datawidth aware

KW - Energy efficiency

KW - Multiplier

KW - Reduced precision

KW - Sign magnitude

UR - http://www.scopus.com/inward/record.url?scp=85056445633&partnerID=8YFLogxK

U2 - 10.1109/DSD.2018.00024

DO - 10.1109/DSD.2018.00024

M3 - Conference contribution

AN - SCOPUS:85056445633

SN - 978-1-5386-7378-2

SP - 54

EP - 61

BT - Proceedings - 21st Euromicro Conference on Digital System Design, DSD 2018

A2 - Konofaos, Nikos

A2 - Novotny, Martin

A2 - Skavhaug, Amund

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Waeijen L, Jiao H, Corporaal H, He Y. Datawidth-aware energy-efficient multipliers: a case for going sign magnitude. In Konofaos N, Novotny M, Skavhaug A, editors, Proceedings - 21st Euromicro Conference on Digital System Design, DSD 2018. Piscataway: Institute of Electrical and Electronics Engineers. 2018. p. 54-61. 8491795 https://doi.org/10.1109/DSD.2018.00024