More Web Proxy on the site http://driver.im/

research-article

RVComp: Analog Variation Compensation for RRAM-Based in-Memory Computing

Authors:

Miguel Lastras,

Kwang-Ting ChengAuthors Info & Claims

ASPDAC '23: Proceedings of the 28th Asia and South Pacific Design Automation Conference

Pages 246 - 251

https://doi.org/10.1145/3566097.3567858

Published: 31 January 2023 Publication History

Abstract

Resistive Random Access Memory (RRAM) has shown great potential in accelerating memory-intensive computation in neural network applications. However, RRAM-based computing suffers from significant accuracy degradation due to the inevitable device variations. In this paper, we propose RVComp, a fine-grained analog Compensation approach to mitigate the accuracy loss of in-memory computing incurred by the Variations of the RRAM devices. Specifically, weights in the RRAM crossbar are accompanied by dedicated compensation RRAM cells to offset their programming errors with a scaling factor. A programming target shifting mechanism is further designed with the objectives of reducing the hardware overhead and minimizing the compensation errors under large device variations. Based on these two key concepts, we propose double and dynamic compensation schemes and the corresponding support architecture. Since the RRAM cells only account for a small fraction of the overall area of the computing macro due to the dominance of the peripheral circuitry, the overall area overhead of RVComp is low and manageable. Simulation results show RVComp achieves a negligible 1.80% inference accuracy drop for ResNet18 on the CIFAR-10 dataset under 30% device variation with only 7.12% area and 5.02% power overhead and no extra latency.

References

[1]

G. Charan et al. Accurate inference with inaccurate rram devices: A joint algorithm-design solution. IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 6(1):27--35, 2020.

[2]

L. Kull et al. A 3.1 mw 8b 1.2 gs/s single-channel asynchronous sar adc with alternate comparators for enhanced speed in 32 nm digital soi cmos. IEEE JSSC, 48(12):3049--3058, 2013.

[3]

C. Li et al. Analogue signal and image processing with large memristor crossbars. Nature electronics, 1(1):52--59, 2018.

[4]

W. Li et al. A 40-nm mlc-rram compute-in-memory macro with sparsity control, on-chip write-verify, and temperature-independent adc references. IEEE JSSC, 2022.

[5]

Z. Li et al. Rram-dnn: An rram and model-compression empowered all-weights-on-chip dnn accelerator. IEEE JSSC, 56(4):1105--1115, 2020.

[6]

Y. Liao et al. A compact model of analog rram with device and array nonideal effects for neuromorphic systems. IEEE Transactions on Electron Devices, 67(4):1593--1599, 2020.

[7]

J. Lin et al. Rescuing rram-based computing from static and dynamic faults. IEEE TCAD, 2020.

[8]

Y. Long et al. Design of reliable dnn accelerator with un-reliable reram. In 2019 DATE, pages 1769--1774. IEEE, 2019.

[9]

A. Mehonic et al. Simulation of inference accuracy using realistic rram devices. Frontiers in neuroscience, 13:593, 2019.

[10]

Z. Meng et al. Digital offset for rram-based neuromorphic computing: A novel solution to conquer cycle-to-cycle variation. In 2021 DATE, pages 1078--1083. IEEE, 2021.

[11]

V. Milo et al. Accurate program/verify schemes of resistive switching memory (rram) for in-memory neural network circuits. IEEE Transactions on Electron Devices, 68(8):3832--3837, 2021.

[12]

M. O'Halloran et al. A 10-nw 12-bit accurate analog storage cell with 10-aa leakage. IEEE JSSC, 39(11):1985--1996, 2004.

[13]

W. Wan et al. 33.1 a 74 tmacs/w cmos-rram neurosynaptic core with dynamically reconfigurable dataflow and in-situ transposable weights for probabilistic graphical models. In 2020 IEEE ISSCC, pages 498--500. IEEE, 2020.

[14]

C. Xue et al. Embedded 1-mb reram-based computing-in-memory macro with multibit input and weight for cnn-based ai edge processors. IEEE JSSC, 55(1):203--215, 2019.

[15]

P. Yao et al. Fully hardware-implemented memristor convolutional neural network. Nature, 577(7792):641--646, 2020.

[16]

J. Yoon et al. 29.1 a 40nm 64kb 56.67 tops/w read-disturb-tolerant compute-in-memory/digital rram macro with active-feedback-based read and in-situ write verification. In 2021 IEEE ISSCC, volume 64, pages 404--406. IEEE, 2021.

[17]

S. Yu et al. Rram for compute-in-memory: From inference to training. IEEE TCAS I, 68(7):2753--2765, 2021.

[18]

W. Zhang et al. Design guidelines of rram based neural-processing-unit: A joint device-circuit-algorithm analysis. In 2019 56th ACM/IEEE DAC, pages 1--6. IEEE, 2019.

Digital Library

[19]

Y. Zhu et al. Statistical training for neuromorphic computing using memristor-based crossbars considering process variations and noise. In 2020 DATE, pages 1590--1593. IEEE, 2020.

Cited By

Huang YHe JCheng TTsui CYe TDe V(2024)RWriC: A Dynamic Writing Scheme for Variation Compensation for RRAM-based In-Memory ComputingProceedings of the 61st ACM/IEEE Design Automation Conference10.1145/3649329.3656227(1-6)Online publication date: 23-Jun-2024
https://dl.acm.org/doi/10.1145/3649329.3656227
Huai SKong HLuo XLi SSubramaniam RMakaya CLin QLiu W(2023)CRIMP: Compact & Reliable DNN Inference on In-Memory Processing via Crossbar-Aligned Compression and Non-ideality AdaptationACM Transactions on Embedded Computing Systems10.1145/360911522:5s(1-25)Online publication date: 9-Sep-2023
https://dl.acm.org/doi/10.1145/3609115
Diware SGebregiorgis AJoshi RHamdioui SBishnoi R(2023)Mapping-aware Biased Training for Accurate Memristor-based Neural Networks2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)10.1109/AICAS57966.2023.10168661(1-5)Online publication date: 11-Jun-2023
https://doi.org/10.1109/AICAS57966.2023.10168661
Show More Cited By

Index Terms

RVComp: Analog Variation Compensation for RRAM-Based in-Memory Computing
1. Hardware
  1. Emerging technologies
    1. Analysis and design of emerging devices and systems
      1. Emerging architectures

Recommendations

PRIME: a novel processing-in-memory architecture for neural network computation in ReRAM-based main memory
ISCA'16

Processing-in-memory (PIM) is a promising solution to address the "memory wall" challenges for future computer systems. Prior proposed PIM architectures put additional computation logic in or near memory. The emerging metal-oxide resistive random access ...
Design of a large-scale storage-class RRAM system
ICS '13: Proceedings of the 27th international ACM conference on International conference on supercomputing

Resistive Random Access Memory (RRAM) is a promising next generation non-volatile memory (NVM) technology, thanks to its performance potential, endurance and ease-of-integration with standard silicon CMOS processes. While prior work has evaluated RRAM ...
PRIME: a novel processing-in-memory architecture for neural network computation in ReRAM-based main memory
ISCA '16: Proceedings of the 43rd International Symposium on Computer Architecture

Processing-in-memory (PIM) is a promising solution to address the "memory wall" challenges for future computer systems. Prior proposed PIM architectures put additional computation logic in or near memory. The emerging metal-oxide resistive random access ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

ASPDAC '23: Proceedings of the 28th Asia and South Pacific Design Automation Conference

January 2023

807 pages

ISBN:9781450397834

DOI:10.1145/3566097

General Chair:
Atsushi Takahashi
Tokyo Institute of Technology

Copyright © 2023 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGDA: ACM Special Interest Group on Design Automation

In-Cooperation

IPSJ
IEEE CAS
IEEE CEDA
IEICE

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 31 January 2023

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

ASPDAC '23

Sponsor:

SIGDA

ASPDAC '23: 28th Asia and South Pacific Design Automation Conference

January 16 - 19, 2023

Tokyo, Japan

Acceptance Rates

ASPDAC '23 Paper Acceptance Rate 102 of 328 submissions, 31%;

Overall Acceptance Rate 466 of 1,454 submissions, 32%

Upcoming Conference

ASPDAC '25

Sponsor:
sigda

30th Asia and South Pacific Design Automation Conference

January 20 - 23, 2025

Tokyo , Japan

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
248
Total Downloads

Downloads (Last 12 months)89
Downloads (Last 6 weeks)6

Reflects downloads up to 13 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Huang YHe JCheng TTsui CYe TDe V(2024)RWriC: A Dynamic Writing Scheme for Variation Compensation for RRAM-based In-Memory ComputingProceedings of the 61st ACM/IEEE Design Automation Conference10.1145/3649329.3656227(1-6)Online publication date: 23-Jun-2024
https://dl.acm.org/doi/10.1145/3649329.3656227
Huai SKong HLuo XLi SSubramaniam RMakaya CLin QLiu W(2023)CRIMP: Compact & Reliable DNN Inference on In-Memory Processing via Crossbar-Aligned Compression and Non-ideality AdaptationACM Transactions on Embedded Computing Systems10.1145/360911522:5s(1-25)Online publication date: 9-Sep-2023
https://dl.acm.org/doi/10.1145/3609115
Diware SGebregiorgis AJoshi RHamdioui SBishnoi R(2023)Mapping-aware Biased Training for Accurate Memristor-based Neural Networks2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)10.1109/AICAS57966.2023.10168661(1-5)Online publication date: 11-Jun-2023
https://doi.org/10.1109/AICAS57966.2023.10168661
Yang ZLiu KDuan YFan MZhang QJin Z(2023)Three Challenges in ReRAM-Based Process-In-Memory for Neural Network2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)10.1109/AICAS57966.2023.10168640(1-5)Online publication date: 11-Jun-2023
https://doi.org/10.1109/AICAS57966.2023.10168640

View Options

Login options

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

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents