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

research-article

Public Access

DependableHD: A Hyperdimensional Learning Framework for Edge-Oriented Voltage-Scaled Circuits

Authors:

Hiromitsu Awano,

Noriyuki Miura,

Jun ShiomiAuthors Info & Claims

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

Pages 416 - 422

https://doi.org/10.1145/3566097.3567886

Published: 31 January 2023 Publication History

Abstract

Voltage scaling is one of the most promising approaches for energy efficiency improvement but also brings challenges to fully guaranteeing the stable operation in modern VLSI. To tackle such issues, we propose DependableHD, a learning framework based on HyperDimensional Computing (HDC), which supports the systems to tolerate bit-level memory failure in the low voltage region with high robustness. For the first time, DependableHD introduces the concept of margin enhancement for model retraining and utilizes noise injection to improve the robustness, which is capable of application in most state-of-the-art HDC algorithms. Our experiment shows that under 10% memory error, DependableHD exhibits a 1.22% accuracy loss on average, which achieves an 11.2× improvement compared to the baseline HDC solution. The hardware evaluation shows that DependableHD supports the systems to reduce the supply voltage from 400mV to 300mV, which provides a 50.41% energy consumption reduction while maintaining competitive accuracy performance.

References

[1]

Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, and Jorge L. Reyes-Ortiz. 2012. Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine. In AAL, José Bravo, Ramón Hervás, and Marcela Rodríguez (Eds.). Springer, 216--223.

[2]

B.H. Calhoun and A. Chandrakasan. 2004. Characterizing and Modeling Minimum Energy Operation for Subthreshold Circuits. In International Symposium on Low Power Electronics and Design. 90--95.

[3]

Ronald G Dreslinski, Michael Wieckowski, David Blaauw, Dennis Sylvester, and Trevor Mudge. 2010. Near-threshold computing: Reclaiming moore's law through energy efficient integrated circuits. Proc. IEEE 98, 2 (2010), 253--266.

[4]

Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. http://archive.ics.uci.edu/ml/datasets/ISOLET

[5]

Anteneh Gebregiorgis, Saman Kiamehr, Fabian Oboril, Rajendra Bishnoi, and Mehdi B Tahoori. 2016. A cross-layer analysis of soft error, aging and process variation in near threshold computing. In 2016 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, 205--210.

[6]

Alejandro Hernandez-Cane, Namiko Matsumoto, Eric Ping, and Mohsen Imani. 2021. OnlineHD: Robust, Efficient, and Single-Pass Online Learning Using Hyperdimensional System. In 2021 Design, Automation Test in Europe Conference Exhibition (DATE). 56--61.

[7]

M. Imani, J. Messerly, F. Wu, W. Pi, and T. Rosing. 2019. A Binary Learning Framework for Hyperdimensional Computing. In 2019 Design, Automation Test in Europe Conference Exhibition (DATE). 126--131.

[8]

Shailendra Jain, Surhud Khare, Satish Yada, V Ambili, Praveen Salihundam, Shiva Ramani, Sriram Muthukumar, M Srinivasan, Arun Kumar, Shasi Kumar Gb, Rajaraman Ramanarayanan, Vasantha Erraguntla, Jason Howard, Sriram Vangal, Saurabh Dighe, Greg Ruhl, Paolo Aseron, Howard Wilson, Nitin Borkar, Vivek De, and Shekhar Borkar. 2012. A 280mV-to-1.2V wide-operating-range IA-32 processor in 32nm CMOS. In 2012 IEEE International Solid-State Circuits Conference. 66--68.

[9]

Pentti Kanerva. 2009. Hyperdimensional Computing: An Introduction to Computing in Distributed Representation with High-Dimensional Random Vectors. Cognitive Computation 1 (06 2009).

[10]

Yann LeCun, Corinna Cortes, and CJ Burges. 2010. MNIST handwritten digit database. ATT Labs. Available: http://yann.lecun.com/exdb/mnist 2 (2010).

[11]

Dehua Liang, Masanori Hashimoto, and Hiromitsu Awano. 2021. BloomCA: A Memory Efficient Reservoir Computing Hardware Implementation Using Cellular Automata and Ensemble Bloom Filter. In 2021 Design, Automation Test in Europe Conference Exhibition (DATE). 587--590.

[12]

Dehua Liang, Jun Shiomi, Noriyuki Miura, and Hiromitsu Awano. 2022. DistriHD: A Memory Efficient Distributed Binary Hyperdimensional Computing Architecture for Image Classification. In 2022 IEEE Asia and South Pacific Design Automation Conference (ASP-DAC).

[13]

Prathyush Poduval, Yang Ni, Yeseong Kim, Kai Ni, Raghavan Kumar, Rosario Cammarota, and Mohsen Imani. 2021. Hyperdimensional Self-Learning Systems Robust to Technology Noise and Bit-Flip Attacks. In 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD).

[14]

Prathyush Poduval, Zhuowen Zou, Hassan Najafi, Houman Homayoun, and Mohsen Imani. 2021. Stochd: Stochastic hyperdimensional system for efficient and robust learning from raw data. In IEEE/ACM DAC.

[15]

Abbas Rahimi, Sohum Datta, Denis Kleyko, Edward Paxon Frady, Bruno Olshausen, Pentti Kanerva, and Jan M. Rabaey. 2017. High-Dimensional Computing as a Nanoscalable Paradigm. IEEE Transactions on Circuits and Systems I: Regular Papers 64, 9 (2017), 2508--2521.

[16]

Abbas Rahimi, Pentti Kanerva, and Jan M Rabaey. 2016. A robust and energy-efficient classifier using brain-inspired hyperdimensional computing. In Proceedings of the 2016 International Symposium on Low Power Electronics and Design. 64--69.

Digital Library

[17]

Adnan Siraj Rakin, Zhezhi He, and Deliang Fan. 2019. Bit-flip attack: Crushing neural network with progressive bit search. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 1211--1220.

[18]

Taejoong Song, Woojin Rim, Sunghyun Park, Yongho Kim, Giyong Yang, Hoonki Kim, Sanghoon Baek, Jonghoon Jung, Bongjae Kwon, Sungwee Cho, Hyuntaek Jung, Yongjae Choo, and Jaeseung Choi. 2017. A 10 nm FinFET 128 Mb SRAM With Assist Adjustment System for Power, Performance, and Area Optimization. IEEE Journal of Solid-State Circuits 52, 1 (2017), 240--249.

[19]

A. Wang and A. Chandrakasan. 2005. A 180-mV Subthreshold FFT Processor using a Minimum Energy Design Methodology. IEEE Journal of Solid-State Circuits 40, 1 (Jan. 2005), 310--319.

[20]

B. Zhai, L. Nazhandali, J. Olson, A. Reeves, M. Minuth, R. Helfand, S. Pant, D. Blaauw, and T. Austin. 2006. A 2.60pJ/Inst Subthreshold Sensor Processor for Optimal Energy Efficiency. In 2006 Symposium on VLSI Circuits, 2006. Digest of Technical Papers. 154--155.

Cited By

Genssler PMayahinia MThomann STahoori MAmrouch H(2024)DropHD: Technology/Algorithm Co-Design for Reliable Energy-Efficient NVM-Based Hyper-Dimensional Computing Under Voltage Scaling2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)10.23919/DATE58400.2024.10546626(1-6)Online publication date: 25-Mar-2024
https://doi.org/10.23919/DATE58400.2024.10546626
Liang DAwano HMiura NShiomi J(2024)A Robust and Energy Efficient Hyperdimensional Computing System for Voltage-scaled CircuitsACM Transactions on Embedded Computing Systems10.1145/362067123:6(1-20)Online publication date: 11-Sep-2024
https://dl.acm.org/doi/10.1145/3620671
Krautter JGenssler PSepanta GAmrouch HTahoori M(2023)Stress-Resiliency of AI Implementations on FPGAs2023 33rd International Conference on Field-Programmable Logic and Applications (FPL)10.1109/FPL60245.2023.00057(333-338)Online publication date: 4-Sep-2023
https://doi.org/10.1109/FPL60245.2023.00057

Index Terms

DependableHD: A Hyperdimensional Learning Framework for Edge-Oriented Voltage-Scaled Circuits
1. Hardware

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

Recommendations

A minimum total power methodology for projecting limits on CMOS GSI
Special section on low-power electronics and design

A circuit design methodology minimizing total power drain of a static complementary metal-oxide-semiconductor (CMOS) random logic network for a prescribed performance, operating temperature range, and short channel threshold voltage rolloff is ...
Reducing Transistor Variability for High Performance Low Power Chips

CMOS integrated-circuit supply-voltage reduction has plateaued in recent years as increased transistor variability has limited transistor-threshold voltage scaling. The deeply depleted channel transistor, implemented on bulk CMOS, provides a low-cost ...
A reduced voltage swing circuit using a single supply to enable lower voltage operation for SRAM-based memory

This paper presents a new read and write assist technique to enable lower voltage operation for Static Random Access Memory (SRAM). The ability to scale the operating voltage with frequency of the chip has big impact on power consumption (P@av^2). The ...

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

Funding Sources

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

3
Total Citations
View Citations
149
Total Downloads

Downloads (Last 12 months)81
Downloads (Last 6 weeks)6

Reflects downloads up to 13 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Genssler PMayahinia MThomann STahoori MAmrouch H(2024)DropHD: Technology/Algorithm Co-Design for Reliable Energy-Efficient NVM-Based Hyper-Dimensional Computing Under Voltage Scaling2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)10.23919/DATE58400.2024.10546626(1-6)Online publication date: 25-Mar-2024
https://doi.org/10.23919/DATE58400.2024.10546626
Liang DAwano HMiura NShiomi J(2024)A Robust and Energy Efficient Hyperdimensional Computing System for Voltage-scaled CircuitsACM Transactions on Embedded Computing Systems10.1145/362067123:6(1-20)Online publication date: 11-Sep-2024
https://dl.acm.org/doi/10.1145/3620671
Krautter JGenssler PSepanta GAmrouch HTahoori M(2023)Stress-Resiliency of AI Implementations on FPGAs2023 33rd International Conference on Field-Programmable Logic and Applications (FPL)10.1109/FPL60245.2023.00057(333-338)Online publication date: 4-Sep-2023
https://doi.org/10.1109/FPL60245.2023.00057

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

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

Media

Figures

Other

Tables

View Table of Contents