MNSIM 2.0: A behavior-level modeling tool for memristor-based neuromorphic computing systems

Zhenhua Zhu; Hanbo Sun; Kaizhong Qiu; Lixue Xia; Gokul Krishnan; Guohao Dai; Dimin Niu; Xiaoming Chen; X. Sharon Hu; Yu Cao; Yuan Xie; Yu Wang; Huazhong Yang

doi:10.1145/3386263.3407647

MNSIM 2.0: A behavior-level modeling tool for memristor-based neuromorphic computing systems

Zhenhua Zhu
, Hanbo Sun
, Kaizhong Qiu
, Lixue Xia
, Gokul Krishnan
, Guohao Dai
, Dimin Niu
, Xiaoming Chen
, X. Sharon Hu
, Yu Cao
, Yuan Xie
, Yu Wang
, Huazhong Yang

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

79 Scopus citations

Abstract

Memristor based neuromorphic computing systems give alternative solutions to boost the computing energy efficiency of Neural Network (NN) algorithms. Because of the large-scale applications and the large architecture design space, many factors will affect the computing accuracy and system's performance. In this work, we propose a behavior-level modeling tool for memristor-based neuromorphic computing systems, MNSIM 2.0, to model the performance and help researchers to realize an early-stage design space exploration. Compared with the former version and other benchmarks, MNSIM 2.0 has the following new features: 1. In the algorithm level, MNSIM 2.0 supports the inference accuracy simulation for mixed-precision NNs considering non-ideal factors. 2. In the architecture level, a hierarchical modeling structure for PIM systems is proposed. Users can customize their designs from the aspects of devices, interfaces, processing units, buffer designs, and interconnections. 3. Two hardware-aware algorithm optimization methods are integrated in MNSIM 2.0 to realize software-hardware co-optimization.

Original language	English (US)
Title of host publication	GLSVLSI 2020 - Proceedings of the 2020 Great Lakes Symposium on VLSI
Publisher	Association for Computing Machinery
Pages	83-88
Number of pages	6
ISBN (Electronic)	9781450379441
DOIs	https://doi.org/10.1145/3386263.3407647
State	Published - Sep 7 2020
Externally published	Yes
Event	30th Great Lakes Symposium on VLSI, GLSVLSI 2020 - Virtual, Online, China Duration: Sep 7 2020 → Sep 9 2020

Publication series

Name	Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

Conference

Conference	30th Great Lakes Symposium on VLSI, GLSVLSI 2020
Country/Territory	China
City	Virtual, Online
Period	9/7/20 → 9/9/20

Bibliographical note

Publisher Copyright:
© 2020 Association for Computing Machinery.

UN SDGs

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

SDG 7 Affordable and Clean Energy

Publisher link

10.1145/3386263.3407647

Find It

Find It at U of M Libraries

Cite this

Zhu, Z., Sun, H., Qiu, K., Xia, L., Krishnan, G., Dai, G., Niu, D., Chen, X., Sharon Hu, X., Cao, Y., Xie, Y., Wang, Y., & Yang, H. (2020). MNSIM 2.0: A behavior-level modeling tool for memristor-based neuromorphic computing systems. In GLSVLSI 2020 - Proceedings of the 2020 Great Lakes Symposium on VLSI (pp. 83-88). (Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI). Association for Computing Machinery. https://doi.org/10.1145/3386263.3407647

MNSIM 2.0: A behavior-level modeling tool for memristor-based neuromorphic computing systems. / Zhu, Zhenhua; Sun, Hanbo; Qiu, Kaizhong et al.
GLSVLSI 2020 - Proceedings of the 2020 Great Lakes Symposium on VLSI. Association for Computing Machinery, 2020. p. 83-88 (Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI).

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

Zhu, Z, Sun, H, Qiu, K, Xia, L, Krishnan, G, Dai, G, Niu, D, Chen, X, Sharon Hu, X, Cao, Y, Xie, Y, Wang, Y & Yang, H 2020, MNSIM 2.0: A behavior-level modeling tool for memristor-based neuromorphic computing systems. in GLSVLSI 2020 - Proceedings of the 2020 Great Lakes Symposium on VLSI. Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI, Association for Computing Machinery, pp. 83-88, 30th Great Lakes Symposium on VLSI, GLSVLSI 2020, Virtual, Online, China, 9/7/20. https://doi.org/10.1145/3386263.3407647

@inproceedings{fe5b784230ef47099086c76c796cfd6b,

title = "MNSIM 2.0: A behavior-level modeling tool for memristor-based neuromorphic computing systems",

abstract = "Memristor based neuromorphic computing systems give alternative solutions to boost the computing energy efficiency of Neural Network (NN) algorithms. Because of the large-scale applications and the large architecture design space, many factors will affect the computing accuracy and system's performance. In this work, we propose a behavior-level modeling tool for memristor-based neuromorphic computing systems, MNSIM 2.0, to model the performance and help researchers to realize an early-stage design space exploration. Compared with the former version and other benchmarks, MNSIM 2.0 has the following new features: 1. In the algorithm level, MNSIM 2.0 supports the inference accuracy simulation for mixed-precision NNs considering non-ideal factors. 2. In the architecture level, a hierarchical modeling structure for PIM systems is proposed. Users can customize their designs from the aspects of devices, interfaces, processing units, buffer designs, and interconnections. 3. Two hardware-aware algorithm optimization methods are integrated in MNSIM 2.0 to realize software-hardware co-optimization.",

author = "Zhenhua Zhu and Hanbo Sun and Kaizhong Qiu and Lixue Xia and Gokul Krishnan and Guohao Dai and Dimin Niu and Xiaoming Chen and \{Sharon Hu\}, X. and Yu Cao and Yuan Xie and Yu Wang and Huazhong Yang",

note = "Publisher Copyright: {\textcopyright} 2020 Association for Computing Machinery.; 30th Great Lakes Symposium on VLSI, GLSVLSI 2020 ; Conference date: 07-09-2020 Through 09-09-2020",

year = "2020",

month = sep,

day = "7",

doi = "10.1145/3386263.3407647",

language = "English (US)",

series = "Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI",

publisher = "Association for Computing Machinery",

pages = "83--88",

booktitle = "GLSVLSI 2020 - Proceedings of the 2020 Great Lakes Symposium on VLSI",

}

TY - GEN

T1 - MNSIM 2.0

T2 - 30th Great Lakes Symposium on VLSI, GLSVLSI 2020

AU - Zhu, Zhenhua

AU - Sun, Hanbo

AU - Qiu, Kaizhong

AU - Xia, Lixue

AU - Krishnan, Gokul

AU - Dai, Guohao

AU - Niu, Dimin

AU - Chen, Xiaoming

AU - Sharon Hu, X.

AU - Cao, Yu

AU - Xie, Yuan

AU - Wang, Yu

AU - Yang, Huazhong

PY - 2020/9/7

Y1 - 2020/9/7

N2 - Memristor based neuromorphic computing systems give alternative solutions to boost the computing energy efficiency of Neural Network (NN) algorithms. Because of the large-scale applications and the large architecture design space, many factors will affect the computing accuracy and system's performance. In this work, we propose a behavior-level modeling tool for memristor-based neuromorphic computing systems, MNSIM 2.0, to model the performance and help researchers to realize an early-stage design space exploration. Compared with the former version and other benchmarks, MNSIM 2.0 has the following new features: 1. In the algorithm level, MNSIM 2.0 supports the inference accuracy simulation for mixed-precision NNs considering non-ideal factors. 2. In the architecture level, a hierarchical modeling structure for PIM systems is proposed. Users can customize their designs from the aspects of devices, interfaces, processing units, buffer designs, and interconnections. 3. Two hardware-aware algorithm optimization methods are integrated in MNSIM 2.0 to realize software-hardware co-optimization.

AB - Memristor based neuromorphic computing systems give alternative solutions to boost the computing energy efficiency of Neural Network (NN) algorithms. Because of the large-scale applications and the large architecture design space, many factors will affect the computing accuracy and system's performance. In this work, we propose a behavior-level modeling tool for memristor-based neuromorphic computing systems, MNSIM 2.0, to model the performance and help researchers to realize an early-stage design space exploration. Compared with the former version and other benchmarks, MNSIM 2.0 has the following new features: 1. In the algorithm level, MNSIM 2.0 supports the inference accuracy simulation for mixed-precision NNs considering non-ideal factors. 2. In the architecture level, a hierarchical modeling structure for PIM systems is proposed. Users can customize their designs from the aspects of devices, interfaces, processing units, buffer designs, and interconnections. 3. Two hardware-aware algorithm optimization methods are integrated in MNSIM 2.0 to realize software-hardware co-optimization.

UR - https://www.scopus.com/pages/publications/85091286228

UR - https://www.scopus.com/pages/publications/85091286228#tab=citedBy

U2 - 10.1145/3386263.3407647

DO - 10.1145/3386263.3407647

M3 - Conference contribution

AN - SCOPUS:85091286228

T3 - Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

SP - 83

EP - 88

BT - GLSVLSI 2020 - Proceedings of the 2020 Great Lakes Symposium on VLSI

PB - Association for Computing Machinery

Y2 - 7 September 2020 through 9 September 2020

ER -

MNSIM 2.0: A behavior-level modeling tool for memristor-based neuromorphic computing systems

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this