Compressed sensing by phase change memories: Coping with encoder non-linearities

Carmine Paolino; Alessio Antolini; Fabio Pareschi; Mauro Mangia; Riccardo Rovatti; Eleonora Franchi Scarselli; Antonio Gnudi; Gianluca Setti; Roberto Canegallo; Marcella Carissimi; Marco Pasotti

doi:10.1109/ISCAS51556.2021.9401176

Compressed sensing by phase change memories: Coping with encoder non-linearities

Carmine Paolino, Alessio Antolini, Fabio Pareschi, Mauro Mangia, Riccardo Rovatti, Eleonora Franchi Scarselli, Antonio Gnudi, Gianluca Setti, Roberto Canegallo, Marcella Carissimi, Marco Pasotti

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

3 Scopus citations

Abstract

Several recent works have shown the advantages of using phase-change memory (PCM) in developing brain-inspired computing approaches. In particular, PCM cells have been applied to the direct computation of matrix-vector multiplications in the analog domain. However, the intrinsic nonlinearity of these cells with respect to the applied voltage is detrimental. In this paper we consider a PCM array as the encoder in a Compressed Sensing (CS) acquisition system, and investigate the effect of the non-linearity of the cells. We introduce a CS decoding strategy that is able to compensate for PCM nonlinearities by means of an iterative approach. At each step, the current signal estimate is used to approximate the average behaviour of the PCM cells used in the encoder. Monte Carlo simulations relying on a PCM model extracted from an STMicrolectronics 90 nm BCD chip validate the performance of the algorithm with various degrees of nonlinearities, showing up to 35 dB increase in median performance as compared to standard decoding procedures.

Original language	English (US)
Title of host publication	Proceedings - IEEE International Symposium on Circuits and Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Print)	9781728192017
DOIs	https://doi.org/10.1109/ISCAS51556.2021.9401176
State	Published - Jan 1 2021
Externally published	Yes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-02-15

Access to Document

10.1109/ISCAS51556.2021.9401176

Cite this

Paolino, C., Antolini, A., Pareschi, F., Mangia, M., Rovatti, R., Scarselli, E. F., Gnudi, A., Setti, G., Canegallo, R., Carissimi, M., & Pasotti, M. (2021). Compressed sensing by phase change memories: Coping with encoder non-linearities. In Proceedings - IEEE International Symposium on Circuits and Systems Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS51556.2021.9401176

@inproceedings{3b475324bbbd4e8cb571ee75236580f7,

title = "Compressed sensing by phase change memories: Coping with encoder non-linearities",

abstract = "Several recent works have shown the advantages of using phase-change memory (PCM) in developing brain-inspired computing approaches. In particular, PCM cells have been applied to the direct computation of matrix-vector multiplications in the analog domain. However, the intrinsic nonlinearity of these cells with respect to the applied voltage is detrimental. In this paper we consider a PCM array as the encoder in a Compressed Sensing (CS) acquisition system, and investigate the effect of the non-linearity of the cells. We introduce a CS decoding strategy that is able to compensate for PCM nonlinearities by means of an iterative approach. At each step, the current signal estimate is used to approximate the average behaviour of the PCM cells used in the encoder. Monte Carlo simulations relying on a PCM model extracted from an STMicrolectronics 90 nm BCD chip validate the performance of the algorithm with various degrees of nonlinearities, showing up to 35 dB increase in median performance as compared to standard decoding procedures.",

author = "Carmine Paolino and Alessio Antolini and Fabio Pareschi and Mauro Mangia and Riccardo Rovatti and Scarselli, {Eleonora Franchi} and Antonio Gnudi and Gianluca Setti and Roberto Canegallo and Marcella Carissimi and Marco Pasotti",

note = "Generated from Scopus record by KAUST IRTS on 2023-02-15",

year = "2021",

month = jan,

day = "1",

doi = "10.1109/ISCAS51556.2021.9401176",

language = "English (US)",

isbn = "9781728192017",

booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Paolino, C, Antolini, A, Pareschi, F, Mangia, M, Rovatti, R, Scarselli, EF, Gnudi, A, Setti, G, Canegallo, R, Carissimi, M & Pasotti, M 2021, Compressed sensing by phase change memories: Coping with encoder non-linearities. in Proceedings - IEEE International Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/ISCAS51556.2021.9401176

TY - GEN

T1 - Compressed sensing by phase change memories: Coping with encoder non-linearities

AU - Paolino, Carmine

AU - Antolini, Alessio

AU - Pareschi, Fabio

AU - Mangia, Mauro

AU - Rovatti, Riccardo

AU - Scarselli, Eleonora Franchi

AU - Gnudi, Antonio

AU - Setti, Gianluca

AU - Canegallo, Roberto

AU - Carissimi, Marcella

AU - Pasotti, Marco

N1 - Generated from Scopus record by KAUST IRTS on 2023-02-15

PY - 2021/1/1

Y1 - 2021/1/1

N2 - Several recent works have shown the advantages of using phase-change memory (PCM) in developing brain-inspired computing approaches. In particular, PCM cells have been applied to the direct computation of matrix-vector multiplications in the analog domain. However, the intrinsic nonlinearity of these cells with respect to the applied voltage is detrimental. In this paper we consider a PCM array as the encoder in a Compressed Sensing (CS) acquisition system, and investigate the effect of the non-linearity of the cells. We introduce a CS decoding strategy that is able to compensate for PCM nonlinearities by means of an iterative approach. At each step, the current signal estimate is used to approximate the average behaviour of the PCM cells used in the encoder. Monte Carlo simulations relying on a PCM model extracted from an STMicrolectronics 90 nm BCD chip validate the performance of the algorithm with various degrees of nonlinearities, showing up to 35 dB increase in median performance as compared to standard decoding procedures.

AB - Several recent works have shown the advantages of using phase-change memory (PCM) in developing brain-inspired computing approaches. In particular, PCM cells have been applied to the direct computation of matrix-vector multiplications in the analog domain. However, the intrinsic nonlinearity of these cells with respect to the applied voltage is detrimental. In this paper we consider a PCM array as the encoder in a Compressed Sensing (CS) acquisition system, and investigate the effect of the non-linearity of the cells. We introduce a CS decoding strategy that is able to compensate for PCM nonlinearities by means of an iterative approach. At each step, the current signal estimate is used to approximate the average behaviour of the PCM cells used in the encoder. Monte Carlo simulations relying on a PCM model extracted from an STMicrolectronics 90 nm BCD chip validate the performance of the algorithm with various degrees of nonlinearities, showing up to 35 dB increase in median performance as compared to standard decoding procedures.

UR - https://ieeexplore.ieee.org/document/9401176/

UR - http://www.scopus.com/inward/record.url?scp=85109016154&partnerID=8YFLogxK

U2 - 10.1109/ISCAS51556.2021.9401176

DO - 10.1109/ISCAS51556.2021.9401176

M3 - Conference contribution

SN - 9781728192017

BT - Proceedings - IEEE International Symposium on Circuits and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Compressed sensing by phase change memories: Coping with encoder non-linearities

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this