Memristor-based deep learning accelerators provide a promising solution to improve the energy efficiency of neuromorphic computing systems. However, the electrical properties and crossbar structure of memristors make these accelerators error-prone. To enable reliable memristor-based accelerators, a simulation platform is needed to precisely analyze the impact of non-ideal circuit and device properties on the inference accuracy. In this paper, we propose a flexible simulation framework, DL-RSIM, to tackle this challenge. DL-RSIM simulates the error rates of every sum-of-products computation in the memristor-based accelerator and injects the errors in the targeted TensorFlow-based neural network model. A rich set of reliability impact factors are explored by DL-RSIM, and it can be incorporated with any deep learning neural network implemented by TensorFlow. Using three representative convolutional neural networks as case studies, we show that DL-RSIM can guide chip designers to choose a reliability-friendly design option and develop reliability optimization techniques.

References

[1]

P.Y. Chen et al. 2018. NeuroSim: A Circuit-Level Macro Model for Benchmarking Neuro-Inspired Architectures in Online Learning. IEEE TCAD (2018), 1–1.

Google Scholar

[2]

W.H. Chen et al. 2018. A 65nm 1Mb nonvolatile computing-in-memory ReRAM macro with sub-16ns multiply-and-accumulate for binary DNN AI edge processors. In ISSCC. 494–496.

Google Scholar

[3]

P. Chi et al. 2016. PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory. In ISCA. 27–39.

Google Scholar

[4]

H. Esmaeilzadeh et al. 2012. Neural Acceleration for General-Purpose Approximate Programs. in MICRO. 449–460.

Google Scholar

[5]

Ben Feinberg et al. 2018. Making Memristive Neural Network Accelerators Reliable. In HPCA. 52–65.

Google Scholar

[6]

K.C. Hsu et al. 2015. A Study of Array Resistance Distribution and a Novel Operation Algorithm for WOx ReRAM Memory. In SSDM.

Google Scholar

[7]

M. Hu et al. 2016. Dot-product engine for neuromorphic computing: Programming 1T1M crossbar to accelerate matrix-vector multiplication. In DAC. 1–6.

Google Scholar

[8]

S.W. Keckler et al. 2011. GPUs and the Future of Parallel Computing. IEEE Micro (2011), 7–17.

Google Scholar

[9]

A. Shafiee et al. 2016. ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars. In ISCA. 14–26.

Google Scholar

[10]

F. Su et al. 2017. A 462GOPs/J RRAM-based nonvolatile intelligent processor for energy harvesting IoE system featuring nonvolatile logics and processing-in-memory. In VLSI-TSA. T260–T261.

Google Scholar

[11]

H.S.P. Wong et al. 2012. Metal-Oxide RRAM. Proc. IEEE (2012), 1951–1970.

Google Scholar

[12]

L. Xia et al. 2017. MNSIM: Simulation Platform for Memristor-based Neuromorphic Computing System. IEEE TCAD (2017), 1–1.

Google Scholar

Cited By

View all

Gao XWang HChen YZhang YShen ZJu L(2024)Static Scheduling of Weight Programming for DNN Acceleration with Resource Constrained PIMACM Transactions on Embedded Computing Systems10.1145/361565723:6(1-22)Online publication date: 11-Sep-2024
https://dl.acm.org/doi/10.1145/3615657
Gu FYang CLin IChang DLu DSchlichtmann U(2024)A Hardware Friendly Variation-Tolerant Framework for RRAM-Based Neuromorphic ComputingIEEE Transactions on Circuits and Systems I: Regular Papers10.1109/TCSI.2024.344318071:12(6419-6432)Online publication date: Dec-2024
https://doi.org/10.1109/TCSI.2024.3443180
Wu XHanson EWang NZheng QYang XYang HLi SCheng FPande PDoppa JChakrabarty KLi H(2024)Block-Wise Mixed-Precision Quantization: Enabling High Efficiency for Practical ReRAM-Based DNN AcceleratorsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2024.340919343:12(4558-4571)Online publication date: Dec-2024
https://doi.org/10.1109/TCAD.2024.3409193
Show More Cited By

Index Terms

DL-RSIM: A Simulation Framework to Enable Reliable ReRAM-based Accelerators for Deep Learning

Index terms have been assigned to the content through auto-classification.

Recommendations

DL-RSIM: A Reliability and Deployment Strategy Simulation Framework for ReRAM-based CNN Accelerators
Memristor-based deep learning accelerators provide a promising solution to improve the energy efficiency of neuromorphic computing systems. However, the electrical properties and crossbar structure of memristors make these accelerators error-prone. In ...
Petascale computing with accelerators
PPoPP '09: Proceedings of the 14th ACM SIGPLAN symposium on Principles and practice of parallel programming

A trend is developing in high performance computing in which commodity processors are coupled to various types of computational accelerators. Such systems are commonly called hybrid systems. In this paper, we describe our experience developing an ...
Parallelism in Deep Learning Accelerators
ASPDAC '20: Proceedings of the 25th Asia and South Pacific Design Automation Conference

Deep learning is the core of artificial intelligence and it achieves state-of-the-art in a wide range of applications. The intensity of computation and data in deep learning processing poses significant challenges to the conventional computing platforms. ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

2018 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)

Nov 2018

939 pages

Publisher

IEEE Press

Publication History

Published: 05 November 2018

Permissions

Request permissions for this article.

Request Permissions

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

64
Total Citations
View Citations
429
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 25 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Gao XWang HChen YZhang YShen ZJu L(2024)Static Scheduling of Weight Programming for DNN Acceleration with Resource Constrained PIMACM Transactions on Embedded Computing Systems10.1145/361565723:6(1-22)Online publication date: 11-Sep-2024
https://dl.acm.org/doi/10.1145/3615657
Gu FYang CLin IChang DLu DSchlichtmann U(2024)A Hardware Friendly Variation-Tolerant Framework for RRAM-Based Neuromorphic ComputingIEEE Transactions on Circuits and Systems I: Regular Papers10.1109/TCSI.2024.344318071:12(6419-6432)Online publication date: Dec-2024
https://doi.org/10.1109/TCSI.2024.3443180
Wu XHanson EWang NZheng QYang XYang HLi SCheng FPande PDoppa JChakrabarty KLi H(2024)Block-Wise Mixed-Precision Quantization: Enabling High Efficiency for Practical ReRAM-Based DNN AcceleratorsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2024.340919343:12(4558-4571)Online publication date: Dec-2024
https://doi.org/10.1109/TCAD.2024.3409193
Han LPan RZhou ZLu HChen YYang HHuang PSun GLiu XKang J(2024)CoMN: Algorithm-Hardware Co-Design Platform for Nonvolatile Memory-Based Convolutional Neural Network AcceleratorsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2024.335822043:7(2043-2056)Online publication date: Jul-2024
https://doi.org/10.1109/TCAD.2024.3358220
Radhakrishnan APalliyalil JBabu SDorzhigulov AJames A(2024)PyMem: A Graphical User Interface Tool for Neuromemristive Hardware–Software Co-DesignIEEE Open Journal of the Industrial Electronics Society10.1109/OJIES.2024.33630935(81-90)Online publication date: 2024
https://doi.org/10.1109/OJIES.2024.3363093
Wei XDeng JWang XLi ZJiang NYue H(2024)CraftRGP: A Comprehensive Reliability Analysis Framework Towards ReRAM-Based Graph Processing2024 IEEE International Test Conference in Asia (ITC-Asia)10.1109/ITC-Asia62534.2024.10661337(1-6)Online publication date: 18-Aug-2024
https://doi.org/10.1109/ITC-Asia62534.2024.10661337
Hong SChung Y(2024)ReShare: A Resource-Efficient Weight Pattern Sharing Scheme for Memristive DNN Accelerators2024 IEEE International Symposium on Circuits and Systems (ISCAS)10.1109/ISCAS58744.2024.10558167(1-5)Online publication date: 19-May-2024
https://doi.org/10.1109/ISCAS58744.2024.10558167
Chiang HNien CCheng HHuang K(2024)ReAIM: A ReRAM-based Adaptive Ising Machine for Solving Combinatorial Optimization Problems2024 ACM/IEEE 51st Annual International Symposium on Computer Architecture (ISCA)10.1109/ISCA59077.2024.00015(58-72)Online publication date: 29-Jun-2024
https://doi.org/10.1109/ISCA59077.2024.00015
Fritscher MSingh SRizzi TBaroni AReiser DMallah MHartmann DBende AKempen TUhlmann MKahmen GFey DRana VMenzel SReichenbach MKrstic MMerchant FWenger C(2024)A flexible and fast digital twin for RRAM systems applied for training resilient neural networksScientific Reports10.1038/s41598-024-73439-z14:1Online publication date: 10-Oct-2024
https://doi.org/10.1038/s41598-024-73439-z
Aguirre FSebastian ALe Gallo MSong WWang TYang JLu WChang MIelmini DYang YMehonic AKenyon AVillena MRoldán JWu YHsu HRaghavan NSuñé JMiranda EEltawil ASetti GSmagulova KSalama KKrestinskaya OYan XAng KJain SLi SAlharbi OPazos SLanza M(2024)Hardware implementation of memristor-based artificial neural networksNature Communications10.1038/s41467-024-45670-915:1Online publication date: 4-Mar-2024
https://doi.org/10.1038/s41467-024-45670-9
Show More Cited By

View Options

View options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Abstract

References

Cited By

Index Terms

Recommendations

DL-RSIM: A Reliability and Deployment Strategy Simulation Framework for ReRAM-based CNN Accelerators

Petascale computing with accelerators

Parallelism in Deep Learning Accelerators

Comments

Information

Published In

Publisher

Publication History

Permissions

Qualifiers

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Cited By

View options

Login options

Full Access

Figures

Other

Share

Share this Publication link

Share on social media

Affiliations