A novel forward-backward predictor based low-power DSP system

Byonghyo Shim, Ming Zhang, Naresh R. Shanbhag

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In this paper, we present a algorithmic noise tolerance (ANT) technique for low-power digital signal processing systems. The proposed technique employs a low-complexity forward-backward predictor to correct errors in a main DSP (MDSP) block due to voltage overscaling, which is an ultra low-voltage operating condition. For a frequency selective FIR filtering, it is shown that the proposed technique achieves up to 43% power savings over an optimally voltage scaled MDSP with a 5% area overhead.

Original languageEnglish
Title of host publicationIEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation
Pages331-336
Number of pages6
Publication statusPublished - 2004
Externally publishedYes
Event2004 IEEE Workshop on Signal Processing Systems Design and Implementation, Proceedings - Austin, TX, United States
Duration: 2004 Oct 132004 Oct 15

Other

Other2004 IEEE Workshop on Signal Processing Systems Design and Implementation, Proceedings
CountryUnited States
CityAustin, TX
Period04/10/1304/10/15

Fingerprint

Electric potential
Digital signal processing

ASJC Scopus subject areas

  • Media Technology
  • Signal Processing

Cite this

Shim, B., Zhang, M., & Shanbhag, N. R. (2004). A novel forward-backward predictor based low-power DSP system. In IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation (pp. 331-336)

A novel forward-backward predictor based low-power DSP system. / Shim, Byonghyo; Zhang, Ming; Shanbhag, Naresh R.

IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation. 2004. p. 331-336.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shim, B, Zhang, M & Shanbhag, NR 2004, A novel forward-backward predictor based low-power DSP system. in IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation. pp. 331-336, 2004 IEEE Workshop on Signal Processing Systems Design and Implementation, Proceedings, Austin, TX, United States, 04/10/13.
Shim B, Zhang M, Shanbhag NR. A novel forward-backward predictor based low-power DSP system. In IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation. 2004. p. 331-336
Shim, Byonghyo ; Zhang, Ming ; Shanbhag, Naresh R. / A novel forward-backward predictor based low-power DSP system. IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation. 2004. pp. 331-336
@inproceedings{90dd33b3022649b38b5da3663a853ffa,
title = "A novel forward-backward predictor based low-power DSP system",
abstract = "In this paper, we present a algorithmic noise tolerance (ANT) technique for low-power digital signal processing systems. The proposed technique employs a low-complexity forward-backward predictor to correct errors in a main DSP (MDSP) block due to voltage overscaling, which is an ultra low-voltage operating condition. For a frequency selective FIR filtering, it is shown that the proposed technique achieves up to 43{\%} power savings over an optimally voltage scaled MDSP with a 5{\%} area overhead.",
author = "Byonghyo Shim and Ming Zhang and Shanbhag, {Naresh R.}",
year = "2004",
language = "English",
pages = "331--336",
booktitle = "IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation",

}

TY - GEN

T1 - A novel forward-backward predictor based low-power DSP system

AU - Shim, Byonghyo

AU - Zhang, Ming

AU - Shanbhag, Naresh R.

PY - 2004

Y1 - 2004

N2 - In this paper, we present a algorithmic noise tolerance (ANT) technique for low-power digital signal processing systems. The proposed technique employs a low-complexity forward-backward predictor to correct errors in a main DSP (MDSP) block due to voltage overscaling, which is an ultra low-voltage operating condition. For a frequency selective FIR filtering, it is shown that the proposed technique achieves up to 43% power savings over an optimally voltage scaled MDSP with a 5% area overhead.

AB - In this paper, we present a algorithmic noise tolerance (ANT) technique for low-power digital signal processing systems. The proposed technique employs a low-complexity forward-backward predictor to correct errors in a main DSP (MDSP) block due to voltage overscaling, which is an ultra low-voltage operating condition. For a frequency selective FIR filtering, it is shown that the proposed technique achieves up to 43% power savings over an optimally voltage scaled MDSP with a 5% area overhead.

UR - http://www.scopus.com/inward/record.url?scp=17044382607&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17044382607&partnerID=8YFLogxK

M3 - Conference contribution

SP - 331

EP - 336

BT - IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation

ER -