Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications

Jörg Henkel; Lokesh Siddhu; Hassan Nassar; Lars Bauer; Jian Jia Chen; Christian Hakert; Tristan Seidl; Kuan Hsun Chen; Xiaobo Sharon Hu; Mengyuan Li; Chia Lin Yang; Ming Liang Wei

doi:10.1145/3676536.3697114

Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications

Jörg Henkel
, Lokesh Siddhu^*
, Hassan Nassar
, Lars Bauer
, Jian Jia Chen
, Christian Hakert
, Tristan Seidl
, Kuan Hsun Chen
, Xiaobo Sharon Hu
, Mengyuan Li
, Chia Lin Yang
, Ming Liang Wei

^*Corresponding author for this work

Computer Architecture Design and Test for Embedded Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

119 Downloads (Pure)

Abstract

With the rapid development of the Internet of Things, machine learning applications on edge devices with limited resources face challenges due to large data scales and irregular memory access patterns. Non-volatile memory (NVM) technologies provide promising solutions by offering larger capacity, low leakage power, and data persistence. In this paper, we discuss the potential of NVM technology in enhancing machine learning applications by improving energy efficiency and reducing latency through in-memory computation and different NVM write modes. The insights from this analysis provide valuable guidance to device researchers and system architects working to develop high-performance systems for machine learning and accelerators in large-scale search applications using NVMs.

Original language	English
Title of host publication	Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024
Publisher	IEEE
ISBN (Electronic)	9798400710773
DOIs	https://doi.org/10.1145/3676536.3697114
Publication status	Published - 9 Apr 2025
Event	43rd International Conference on Computer-Aided Design, ICCAD 2024 - New York, United States Duration: 27 Oct 2024 → 31 Oct 2024 Conference number: 43

Publication series

Name	IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
ISSN (Print)	1092-3152

Conference

Conference	43rd International Conference on Computer-Aided Design, ICCAD 2024
Abbreviated title	ICCAD 2024
Country/Territory	United States
City	New York
Period	27/10/24 → 31/10/24

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Access to Document

10.1145/3676536.3697114Licence: CC BY

3676536.3697114Final published version, 763 KBLicence: CC BY

Cite this

Henkel, J., Siddhu, L., Nassar, H., Bauer, L., Chen, J. J., Hakert, C., Seidl, T., Chen, K. H., Hu, X. S., Li, M., Yang, C. L., & Wei, M. L. (2025). Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications. In Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024 Article 125 (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD). IEEE. https://doi.org/10.1145/3676536.3697114

@inproceedings{3422a4206e2c41d0b6a75340fa3ba7f6,

title = "Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications",

abstract = "With the rapid development of the Internet of Things, machine learning applications on edge devices with limited resources face challenges due to large data scales and irregular memory access patterns. Non-volatile memory (NVM) technologies provide promising solutions by offering larger capacity, low leakage power, and data persistence. In this paper, we discuss the potential of NVM technology in enhancing machine learning applications by improving energy efficiency and reducing latency through in-memory computation and different NVM write modes. The insights from this analysis provide valuable guidance to device researchers and system architects working to develop high-performance systems for machine learning and accelerators in large-scale search applications using NVMs.",

author = "J{\"o}rg Henkel and Lokesh Siddhu and Hassan Nassar and Lars Bauer and Chen, \{Jian Jia\} and Christian Hakert and Tristan Seidl and Chen, \{Kuan Hsun\} and Hu, \{Xiaobo Sharon\} and Mengyuan Li and Yang, \{Chia Lin\} and Wei, \{Ming Liang\}",

note = "Publisher Copyright: {\textcopyright} 2024 Copyright is held by the owner/author(s).; 43rd International Conference on Computer-Aided Design, ICCAD 2024, ICCAD 2024 ; Conference date: 27-10-2024 Through 31-10-2024",

year = "2025",

month = apr,

day = "9",

doi = "10.1145/3676536.3697114",

language = "English",

series = "IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD",

publisher = "IEEE",

booktitle = "Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024",

address = "United States",

}

Henkel, J, Siddhu, L, Nassar, H, Bauer, L, Chen, JJ, Hakert, C, Seidl, T, Chen, KH, Hu, XS, Li, M, Yang, CL & Wei, ML 2025, Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications. in Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024., 125, IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, IEEE, 43rd International Conference on Computer-Aided Design, ICCAD 2024, New York, United States, 27/10/24. https://doi.org/10.1145/3676536.3697114

Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications. / Henkel, Jörg; Siddhu, Lokesh; Nassar, Hassan et al.
Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024. IEEE, 2025. 125 (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications

AU - Henkel, Jörg

AU - Siddhu, Lokesh

AU - Nassar, Hassan

AU - Bauer, Lars

AU - Chen, Jian Jia

AU - Hakert, Christian

AU - Seidl, Tristan

AU - Chen, Kuan Hsun

AU - Hu, Xiaobo Sharon

AU - Li, Mengyuan

AU - Yang, Chia Lin

AU - Wei, Ming Liang

N1 - Conference code: 43

PY - 2025/4/9

Y1 - 2025/4/9

N2 - With the rapid development of the Internet of Things, machine learning applications on edge devices with limited resources face challenges due to large data scales and irregular memory access patterns. Non-volatile memory (NVM) technologies provide promising solutions by offering larger capacity, low leakage power, and data persistence. In this paper, we discuss the potential of NVM technology in enhancing machine learning applications by improving energy efficiency and reducing latency through in-memory computation and different NVM write modes. The insights from this analysis provide valuable guidance to device researchers and system architects working to develop high-performance systems for machine learning and accelerators in large-scale search applications using NVMs.

AB - With the rapid development of the Internet of Things, machine learning applications on edge devices with limited resources face challenges due to large data scales and irregular memory access patterns. Non-volatile memory (NVM) technologies provide promising solutions by offering larger capacity, low leakage power, and data persistence. In this paper, we discuss the potential of NVM technology in enhancing machine learning applications by improving energy efficiency and reducing latency through in-memory computation and different NVM write modes. The insights from this analysis provide valuable guidance to device researchers and system architects working to develop high-performance systems for machine learning and accelerators in large-scale search applications using NVMs.

UR - https://www.scopus.com/pages/publications/105003641889

U2 - 10.1145/3676536.3697114

DO - 10.1145/3676536.3697114

M3 - Conference contribution

AN - SCOPUS:105003641889

T3 - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

BT - Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024

PB - IEEE

T2 - 43rd International Conference on Computer-Aided Design, ICCAD 2024

Y2 - 27 October 2024 through 31 October 2024

ER -

Henkel J, Siddhu L, Nassar H, Bauer L, Chen JJ, Hakert C et al. Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications. In Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2024. IEEE. 2025. 125. (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD). doi: 10.1145/3676536.3697114

Co-Designing NVM-based Systems for Machine Learning and In-memory Search Applications

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this