research-article

Improving energy gains of inexact DSP hardware through reciprocative error compensation

Authors:

Avinash Lingamneni,

Krishna V. Palem,

Christian PiguetAuthors Info & Claims

DAC '13: Proceedings of the 50th Annual Design Automation Conference

Article No.: 20, Pages 1 - 8

https://doi.org/10.1145/2463209.2488759

Published: 29 May 2013 Publication History

Abstract

We present a zero hardware-overhead design approach called reciprocative error compensation (REC) that significantly enhances the energy-accuracy trade-off gains in inexact signal processing datapaths by using a two-pronged approach: (a) deliberately redesigning the basic arithmetic blocks to effectively compensate for each other's (expected) error through inexact logic minimization, and (b) "reshaping" the response waveforms of the systems being designed to further reduce any residual error. We apply REC to several DSP primitives such as the FFT and FIR filter blocks, and show that this approach delivers 2-3 orders of magnitude lower (expected) error and more than an order of magnitude lesser Signal-to-Noise Ratio (SNR) loss (in dB) over the previously proposed inexact design techniques, while yielding similar energy gains. Post-layout comparisons in the 65nm process technology show that our REC approach achieves upto 73% energy savings (with corresponding delay and area savings of upto 16% and 62% respectively) when compared to an existing exact DSP implementation while trading a relatively small loss in SNR of less than 1.5 dB.

References

[1]

A. Lingamneni et al. Energy parsimonious circuit design through probabilistic pruning, in proc. of DATE, pages 764--769, Mar 2011.

[2]

A. Lingamneni et al. Parsimonious circuit design for error-tolerant applications through probabilistic logic minimization, in the proc. of the PATMOS, pages 204--213, 2011.

Digital Library

[3]

A. Lingamneni et al. Algorithmic methodologies for ultra-efficient inexact architectures for sustaining technology scaling, in proc. of ACM Intl. Conference on Computing Frontiers, pages 3--12, May 2012.

Digital Library

[4]

A. Lingamneni et al. Synthesizing parsimonious inexact circuits through probabilistic design techniques, in proc. of ACM Transactions on Embedded Computing Systems, 2013.

Digital Library

[5]

D Shin et al. Approximate logic synthesis for error tolerant applications, in the proc. of DATE, pages 957--960, 2010.

Digital Library

[6]

E. J King et al. Data-dependent truncation scheme for parallel multipliers. Asilomar Conf. on Signals, Systems & Computers, 1997.

[7]

S. Haykin. Adaptive Filter Theory. Prentice-Hall, Inc., Englewood Cliffs, NJ., 2002.

Digital Library

[8]

S. He and M. Torkelson. A new approach to pipeline FFT processor, in proc. of Parallel Processing Symposium, (766--770), 1996.

Digital Library

[9]

J. Huang et al. A methodology for energy-quality tradeoff using imprecise hardware, in the 49th DAC, pages 504--509, 2012.

Digital Library

[10]

K. Palem et al. What to do about the end of moore's law, probably! in the 49th DAC, pages 924--929, 2012.

Digital Library

[11]

K. Palem et al. Ten years of building broken chips: The physics and engineering of inexact computing, in proc. of ACM Transactions on Embedded Computing Systems, 2013.

Digital Library

[12]

K. V. Palem et al. Sustaining moore's law in embedded computing through probabilistic and approximate design: retrospects and prospects. In in proc. of CASES, pages 1--10, 2009.

Digital Library

[13]

L. N. B. Chakrapani et al. Highly energy and performance efficient embedded computing through approximately correct arithmetic: A mathematical foundation and preliminary experimental validation. In proc. of IEEE/ACM CASES, pages 187--196, 2008.

Digital Library

[14]

E. McCluskey Jr. Minimization of boolean functions. Bell System Technical Journal, 1956.

[15]

M. R. Choudhury et al. Approximate logic circuits for low overhead, non-intrusive concurrent error detection. in the proc. of DATE, pages 903--908, Mar 2008.

Digital Library

[16]

N. Zhu et al. Design of low-power high-speed truncation-error-tolerant adder and its application in digital signal processing. IEEE Trans. Very Large Scale Integration Sys., 18(8):1225--1229, 2010.

Digital Library

[17]

P. Kulkarni et al. Trading accuracy for power with an underdesigned multiplier architecture, in the proc. of Intl Conf on VLSI Design, (346--351), 2011.

Digital Library

[18]

K. V. Palem. Energy aware algorithm design via probabilistic computing: From algorithms and models to Moore's law and novel (semiconductor) devices. In proc. of CASES, pages 113--116, 2003.

Digital Library

[19]

K. V. Palem. Energy aware computing through probabilistic switching: A study of limits. IEEE Transactions on Computers, 54(9):1123--1137, 2005.

Digital Library

[20]

V. Gupta et al. Impact: imprecise adders for low-power approximate computing, in proc. of ISLPED, (409--414), 2011.

Digital Library

Cited By

Rao ESamundiswary P(2024)High-Speed and Low-Power Recursive Rounding Based Approximate Multipliers for Error-Resilience ApplicationsWireless Personal Communications10.1007/s11277-024-11283-0136:2(773-791)Online publication date: 25-Jun-2024
https://doi.org/10.1007/s11277-024-11283-0
Wu YChen CXiao WWang XWen CHan JYin XQian WZhuo C(2023)A Survey on Approximate Multiplier Designs for Energy Efficiency: From Algorithms to CircuitsACM Transactions on Design Automation of Electronic Systems10.1145/361029129:1(1-37)Online publication date: 24-Jul-2023
https://dl.acm.org/doi/10.1145/3610291
Perumal SRajendiran S(2022)Low power multiplier based long short-term memory hardware architecture for smart grid energy managementInternational Journal of System Assurance Engineering and Management10.1007/s13198-022-01662-w13:5(2531-2539)Online publication date: 15-Apr-2022
https://doi.org/10.1007/s13198-022-01662-w
Show More Cited By

Index Terms

Improving energy gains of inexact DSP hardware through reciprocative error compensation
1. Hardware

Recommendations

Reduced Overhead Error Compensation for Energy Efficient Machine Learning Kernels
ICCAD '15: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design

Low overhead error-resiliency techniques such as RAZOR [1] and algorithmic noise-tolerance (ANT) [2] have proven effective in reducing energy consumption. ANT has been shown to be particularly effective for signal processing and machine learning ...
Modeling sleep mode gains in energy-aware networks

Nowadays two main approaches are being pursued to reduce energy consumption of networks: the use of sleep modes in which devices enter a low-power state during inactivity periods, and the adoption of energy proportional mechanisms where the device ...
Adaptive Error Compensation for Low Error Fixed-Width Squarers

In this paper, we present a design method for fixed-width squarer that receives an n-bit input and produces an n-bit squared product. To efficiently compensate for the truncation error, modified Booth-folding encoder signals are used for the generation ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

DAC '13: Proceedings of the 50th Annual Design Automation Conference

May 2013

1285 pages

ISBN:9781450320719

DOI:10.1145/2463209

Copyright © 2013 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

EDAC: Electronic Design Automation Consortium
SIGDA: ACM Special Interest Group on Design Automation
IEEE-CEDA

In-Cooperation

SIGBED: ACM Special Interest Group on Embedded Systems

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 29 May 2013

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Research-article

Conference

DAC '13

Sponsor:

EDAC
SIGDA

DAC '13: The 50th Annual Design Automation Conference 2013

May 29 - June 7, 2013

Texas, Austin

Acceptance Rates

Overall Acceptance Rate 1,770 of 5,499 submissions, 32%

Upcoming Conference

DAC '25

Sponsor:
sigda

62nd ACM/IEEE Design Automation Conference

June 22 - 26, 2025

San Francisco , CA , USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
233
Total Downloads

Downloads (Last 12 months)3
Downloads (Last 6 weeks)0

Reflects downloads up to 08 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Rao ESamundiswary P(2024)High-Speed and Low-Power Recursive Rounding Based Approximate Multipliers for Error-Resilience ApplicationsWireless Personal Communications10.1007/s11277-024-11283-0136:2(773-791)Online publication date: 25-Jun-2024
https://doi.org/10.1007/s11277-024-11283-0
Wu YChen CXiao WWang XWen CHan JYin XQian WZhuo C(2023)A Survey on Approximate Multiplier Designs for Energy Efficiency: From Algorithms to CircuitsACM Transactions on Design Automation of Electronic Systems10.1145/361029129:1(1-37)Online publication date: 24-Jul-2023
https://dl.acm.org/doi/10.1145/3610291
Perumal SRajendiran S(2022)Low power multiplier based long short-term memory hardware architecture for smart grid energy managementInternational Journal of System Assurance Engineering and Management10.1007/s13198-022-01662-w13:5(2531-2539)Online publication date: 15-Apr-2022
https://doi.org/10.1007/s13198-022-01662-w
Rao ESamundiswary P(2021)Error-Efficient Approximate Multiplier Design using Rounding Based Approach for Image Smoothing ApplicationJournal of Electronic Testing10.1007/s10836-021-05971-zOnline publication date: 10-Nov-2021
https://doi.org/10.1007/s10836-021-05971-z
Raha ARaghunathan V(2017)qLUTACM Transactions on Embedded Computing Systems10.1145/312653116:5s(1-23)Online publication date: 27-Sep-2017
https://dl.acm.org/doi/10.1145/3126531
Kadiyala SPudi VLam S(2017)Approximate compressed sensing for hardware-efficient image compression2017 30th IEEE International System-on-Chip Conference (SOCC)10.1109/SOCC.2017.8226074(340-345)Online publication date: Sep-2017
https://doi.org/10.1109/SOCC.2017.8226074
Düben PSchlachter JParishkrati Yenugula SAugustine JEnz CPalem KPalmer TNebel WAtienza D(2015)Opportunities for energy efficient computingProceedings of the 2015 Design, Automation & Test in Europe Conference & Exhibition10.5555/2755753.2755927(764-769)Online publication date: 9-Mar-2015
https://dl.acm.org/doi/10.5555/2755753.2755927
Kadiyala SSen AMahajan SWang QLingamneni AGerman JHong XBanerjee APalem KBasu A(2015)Perceptually guided inexact DSP design for power, area efficient hearing aid2015 IEEE Biomedical Circuits and Systems Conference (BioCAS)10.1109/BioCAS.2015.7348319(1-4)Online publication date: Oct-2015
https://doi.org/10.1109/BioCAS.2015.7348319
Lingamneni AEnz CPalem KPiguet C(2014)Highly energy-efficient and quality-tunable inexact FFT acceleratorsProceedings of the IEEE 2014 Custom Integrated Circuits Conference10.1109/CICC.2014.6946047(1-4)Online publication date: Sep-2014
https://doi.org/10.1109/CICC.2014.6946047

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten