research-article

LUT-based RRAM Model for Neural Accelerator Circuit Simulation

Authors:

Emilio Pérez-Bosch Quesada,

Bakr Al Beattie,

Karlheinz Ochs,

Eduardo Pérez,

Philip Ostrovskyy,

Christian Wenger,

Gerhard KahmenAuthors Info & Claims

NANOARCH '23: Proceedings of the 18th ACM International Symposium on Nanoscale Architectures

Article No.: 35, Pages 1 - 6

https://doi.org/10.1145/3611315.3633273

Published: 25 January 2024 Publication History

Abstract

Neural hardware accelerators have been proven to be energy-efficient when used to solve tasks which can be mapped into an artificial neural network (ANN) structure. Resistive random-access memories (RRAMs) are currently under investigation together with several different memristive devices as promising technologies to build such accelerators combined together with complementary metal-oxide semiconductor (CMOS)-technologies in integrated circuits (ICs). While many research groups are actively developing sophisticated physical-based representations to better understand the underlying phenomena characterizing these devices, not much work has been dedicated to exploit the trade-off between simulation time and accuracy in the definition of low computational demanding models suitable to be used at many abstraction layers. Indeed, the design of complex mixed-signal systems as a neural hardware accelerators requires frequent interaction between the application- and the circuit-level that can be enabled only with the support of accurate and fast-simulating devices’ models. In this work, we propose a solution to fill the aforementioned gap with a lookup table (LUT)-based Verilog-A model of IHP’s 1-transistor-1-RRAM (1T1R) cell. In addition, the implementation challenges of conveying the communication between the abstract ANN simulation and the circuital analysis are tackled with a design flow for resistive neural hardware accelerators that features a custom Python wrapper. As a demonstration of the proposed design flow and 1T1R model, an ANN for the MNIST handwritten digit recognition task is assessed with the last layer verified in circuit simulation. The obtained recognition confidence intervals show a considerable discrepancy between the purely application-level PyTorch simulation and the proposed design flow which spans across the abstraction layers down to the circuital analysis.

References

[1]

Ping Chi 2016. PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory. In 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA). 27–39. https://doi.org/10.1109/ISCA.2016.13

Digital Library

[2]

Charlotteet Frenkel 2023. Bottom-Up and Top-Down Approaches for the Design of Neuromorphic Processing Systems: Tradeoffs and Synergies Between Natural and Artificial Intelligence. Proc. IEEE 111, 6 (2023), 623–652. https://doi.org/10.1109/JPROC.2023.3273520

[3]

Benoit Jacob 2018. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2704–2713. https://doi.org/10.48550/arXiv.1712.05877

[4]

Arya Jagath 2019. An Insight Into Physics Based RRAM Models – A Review. The Journal of Engineering 2019 (05 2019). https://doi.org/10.1049/joe.2018.5234

[5]

Corey Lammie 2022. MemTorch: An open-source simulation framework for memristive deep learning systems. Neurocomputing 485 (2022), 124–133. https://doi.org/10.48550/arXiv.2004.10971

Digital Library

[6]

Yann LeCun 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278–2324. https://doi.org/10.1109/5.726791

[7]

Alessandro Pappalardo. 2022. Xilinx/brevitas. (2022). https://doi.org/10.5281/zenodo.3333552

[8]

Xiaochen Peng 2020. DNN+ NeuroSim V2. 0: An end-to-end benchmarking framework for compute-in-memory accelerators for on-chip training. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 40, 11 (2020), 2306–2319. https://doi.org/10.48550/arXiv.2003.06471

Digital Library

[9]

Antonio J. Pérez-Ávila 2020. Behavioral modeling of multilevel HfO 2-based memristors for neuromorphic circuit simulation. In 2020 XXXV Conference on Design of Circuits and Integrated Systems (DCIS). IEEE, 1–6. https://doi.org/10.1109/DCIS51330.2020.9268652

[10]

Emilio Pérez-Bosch 2021. Toward Reliable Compact Modeling of Multilevel 1T-1R RRAM Devices for Neuromorphic Systems. Electronics 10 (03 2021), 645. https://doi.org/10.3390/electronics10060645

[11]

Emilio Perez-Bosch Quesada 2023. Experimental Assessment of Multilevel RRAM-Based Vector-Matrix Multiplication Operations for In-Memory Computing. IEEE Transactions on Electron Devices 70, 4 (2023), 2009–2014. https://doi.org/10.1109/TED.2023.3244509

[12]

Kamilya Smagulova 2023. Resistive Neural Hardware Accelerators. Proc. IEEE 111, 5 (2023), 500–527. https://doi.org/10.1109/JPROC.2023.3268092

[13]

Weier Wan 2022. A compute-in-memory chip based on resistive random-access memory. Nature 608 (08 2022), 504–512. https://doi.org/10.1038/s41586-022-04992-8

[14]

Jianan Wen 2021. Behavioral Model of Dot-Product Engine Implemented with 1T1R Memristor Crossbar Including Assessment. In 2021 24th International Symposium on Design and Diagnostics of Electronic Circuits & Systems (DDECS). 29–32. https://doi.org/10.1109/DDECS52668.2021.9417070

[15]

Jianan Wen 2022. Evaluating Read Disturb Effect on RRAM based AI Accelerator with Multilevel States and Input Voltages. In 2022 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT). 1–6. https://doi.org/10.1109/DFT56152.2022.9962345

[16]

Cheng-Xin Xue 2020. 15.4 A 22nm 2Mb ReRAM Compute-in-Memory Macro with 121-28TOPS/W for Multibit MAC Computing for Tiny AI Edge Devices. In 2020 IEEE International Solid- State Circuits Conference - (ISSCC). 244–246. https://doi.org/10.1109/ISSCC19947.2020.9063078

[17]

Ussama Zahid 2020. FAT: Training Neural Networks for Reliable Inference Under Hardware Faults. In 2020 IEEE International Test Conference (ITC). 1–10. https://doi.org/10.1109/ITC44778.2020.9325249

[18]

Furqan Zahoor 2020. Resistive Random Access Memory (RRAM): an Overview of Materials, Switching Mechanism, Performance, Multilevel Cell (MLC) Storage, Modeling, and Applications. Nanoscale Research Letters 2020 (05 2020), 15. https://doi.org/10.1186/s11671-020-03299-9

Cited By

Wen JVargas FZhu FReiser DBaroni AFritscher MPerez EReichenbach MWenger CKrstic M(2024)Cycle-Accurate FPGA Emulation of RRAM Crossbar Array: Efficient Device and Variability Modeling with Energy Consumption Assessment2024 IEEE 25th Latin American Test Symposium (LATS)10.1109/LATS62223.2024.10534601(1-6)Online publication date: 9-Apr-2024
https://doi.org/10.1109/LATS62223.2024.10534601

Index Terms

LUT-based RRAM Model for Neural Accelerator Circuit Simulation
1. Hardware
  1. Emerging technologies
    1. Analysis and design of emerging devices and systems
      1. Emerging tools and methodologies
    2. Memory and dense storage

Recommendations

An Almost Fully RRAM-Based LUT Design for Reconfigurable Circuits
Applied Reconfigurable Computing. Architectures, Tools, and Applications
Abstract
In the last decade, resistive random-access memory (RRAM) has been used in designing field-programmable gate arrays (FPGAs). The non-volatility of RRAM has made it a promising substitute for the traditional static random-access memory (SRAM) in ...
An RRAM-based MLC design approach

RRAM is an emerging technology with vast applications in computation and storage. RRAM with MLC capabilities is more interesting owing to its higher storage density. In this study, we proposed an approach for RRAM-based MLC design. The approach starts ...
Stochastic circuit breaker network model for bipolar resistance switching memories

We present a stochastic model for resistance switching devices in which a square grid of resistor breakers plays the role of the insulator switching layer. The probability of breaker switching between two fixed resistance values, $$R_\mathrm{OFF}$$ROFF ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

NANOARCH '23: Proceedings of the 18th ACM International Symposium on Nanoscale Architectures

December 2023

222 pages

ISBN:9798400703256

DOI:10.1145/3611315

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 the author(s) 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].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 25 January 2024

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

Deutsche Forschungsgemeinschaft (DFG)

Conference

NANOARCH '23

NANOARCH '23: 18th ACM International Symposium on Nanoscale Architectures

December 18 - 20, 2023

Dresden, Germany

Acceptance Rates

Overall Acceptance Rate 55 of 87 submissions, 63%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
94
Total Downloads

Downloads (Last 12 months)94
Downloads (Last 6 weeks)10

Reflects downloads up to 10 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Wen JVargas FZhu FReiser DBaroni AFritscher MPerez EReichenbach MWenger CKrstic M(2024)Cycle-Accurate FPGA Emulation of RRAM Crossbar Array: Efficient Device and Variability Modeling with Energy Consumption Assessment2024 IEEE 25th Latin American Test Symposium (LATS)10.1109/LATS62223.2024.10534601(1-6)Online publication date: 9-Apr-2024
https://doi.org/10.1109/LATS62223.2024.10534601

View Options

Get Access

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.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View Table of Contents