Computation as estimation: Estimation-theoretic IC design improves robustness and reduces power consumption

Sriram Narayanan; Girish V. Varatkar; Douglas L. Jones; Naresh R. Shanbhag

doi:10.1109/ICASSP.2008.4517886

Computation as estimation: Estimation-theoretic IC design improves robustness and reduces power consumption

Sriram Narayanan, Girish V. Varatkar, Douglas L. Jones, Naresh R. Shanbhag

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Modern Integrated Circuits (ICs) are designed as massively parallel systems as a consequence of diminishing silicon feature sizes. This has adversely impacted reliability because of increased errors due to process and environmental variations, and particle hits. Viewing hardware errors as analogous to measurement or system noise allows us to borrow results from estimation theory and extend Moore's law. The estimation-theoretic framework provides a design optimization formalization that enables power/reliability trade-off in broad classes of applications. Two applications described here show that specific instantiations of the framework yield significant power savings and system reliability.

Original language	English (US)
Title of host publication	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages	1421-1424
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2008.4517886
State	Published - Sep 16 2008
Event	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States Duration: Mar 31 2008 → Apr 4 2008

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Other

Other	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Country	United States
City	Las Vegas, NV
Period	3/31/08 → 4/4/08

Keywords

Estimation-theoretic computation
Low-power IC design
Robust gigascale systems
Sensor networks-on-chip

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2008.4517886

Fingerprint Dive into the research topics of 'Computation as estimation: Estimation-theoretic IC design improves robustness and reduces power consumption'. Together they form a unique fingerprint.

Cite this

Narayanan, S., Varatkar, G. V., Jones, D. L., & Shanbhag, N. R. (2008). Computation as estimation: Estimation-theoretic IC design improves robustness and reduces power consumption. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (pp. 1421-1424). [4517886] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4517886

Computation as estimation : Estimation-theoretic IC design improves robustness and reduces power consumption. / Narayanan, Sriram; Varatkar, Girish V.; Jones, Douglas L.; Shanbhag, Naresh R.

2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 1421-1424 4517886 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Narayanan, S, Varatkar, GV, Jones, DL & Shanbhag, NR 2008, Computation as estimation: Estimation-theoretic IC design improves robustness and reduces power consumption. in 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP., 4517886, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 1421-1424, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 3/31/08. https://doi.org/10.1109/ICASSP.2008.4517886

Narayanan S, Varatkar GV, Jones DL , Shanbhag NR. Computation as estimation: Estimation-theoretic IC design improves robustness and reduces power consumption. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 1421-1424. 4517886. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4517886

Narayanan, Sriram ; Varatkar, Girish V. ; Jones, Douglas L. ; Shanbhag, Naresh R. / Computation as estimation : Estimation-theoretic IC design improves robustness and reduces power consumption. 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. pp. 1421-1424 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{a46bdd8c857c409da3417b875eca4aae,

title = "Computation as estimation: Estimation-theoretic IC design improves robustness and reduces power consumption",

abstract = "Modern Integrated Circuits (ICs) are designed as massively parallel systems as a consequence of diminishing silicon feature sizes. This has adversely impacted reliability because of increased errors due to process and environmental variations, and particle hits. Viewing hardware errors as analogous to measurement or system noise allows us to borrow results from estimation theory and extend Moore's law. The estimation-theoretic framework provides a design optimization formalization that enables power/reliability trade-off in broad classes of applications. Two applications described here show that specific instantiations of the framework yield significant power savings and system reliability.",

keywords = "Estimation-theoretic computation, Low-power IC design, Robust gigascale systems, Sensor networks-on-chip",

author = "Sriram Narayanan and Varatkar, {Girish V.} and Jones, {Douglas L.} and Shanbhag, {Naresh R.}",

year = "2008",

month = sep,

day = "16",

doi = "10.1109/ICASSP.2008.4517886",

language = "English (US)",

isbn = "1424414849",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "1421--1424",

booktitle = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP",

note = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP ; Conference date: 31-03-2008 Through 04-04-2008",

}

TY - GEN

T1 - Computation as estimation

T2 - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

AU - Narayanan, Sriram

AU - Varatkar, Girish V.

AU - Jones, Douglas L.

AU - Shanbhag, Naresh R.

PY - 2008/9/16

Y1 - 2008/9/16

N2 - Modern Integrated Circuits (ICs) are designed as massively parallel systems as a consequence of diminishing silicon feature sizes. This has adversely impacted reliability because of increased errors due to process and environmental variations, and particle hits. Viewing hardware errors as analogous to measurement or system noise allows us to borrow results from estimation theory and extend Moore's law. The estimation-theoretic framework provides a design optimization formalization that enables power/reliability trade-off in broad classes of applications. Two applications described here show that specific instantiations of the framework yield significant power savings and system reliability.

AB - Modern Integrated Circuits (ICs) are designed as massively parallel systems as a consequence of diminishing silicon feature sizes. This has adversely impacted reliability because of increased errors due to process and environmental variations, and particle hits. Viewing hardware errors as analogous to measurement or system noise allows us to borrow results from estimation theory and extend Moore's law. The estimation-theoretic framework provides a design optimization formalization that enables power/reliability trade-off in broad classes of applications. Two applications described here show that specific instantiations of the framework yield significant power savings and system reliability.

KW - Estimation-theoretic computation

KW - Low-power IC design

KW - Robust gigascale systems

KW - Sensor networks-on-chip

UR - http://www.scopus.com/inward/record.url?scp=51449107569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449107569&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4517886

DO - 10.1109/ICASSP.2008.4517886

M3 - Conference contribution

AN - SCOPUS:51449107569

SN - 1424414849

SN - 9781424414840

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1421

EP - 1424

BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

Y2 - 31 March 2008 through 4 April 2008

ER -