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

short-paper

The challenge of multi-operand adders in CNNs on FPGAs: how not to solve it!

Authors:

Kamel Abdelouahab,

Francois BerryAuthors Info & Claims

SAMOS '18: Proceedings of the 18th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation

Pages 157 - 160

https://doi.org/10.1145/3229631.3235024

Published: 15 July 2018 Publication History

Abstract

Convolutional Neural Networks (CNNs) are computationally intensive algorithms that currently require dedicated hardware to be executed. In the case of FPGA-Based accelerators, we point-out in this work the challenge of Multi-Operand Adders (MOAs) and their high resource utilization in an FPGA implementation of a CNN. To address this challenge, two optimization strategies, that rely on time-multiplexing and approximate computing, are investigated. At first glance, the two strategies looked promising to reduce the footprint of a given architectural mapping, but when synthesized on the device, none of them gave the expected results. Experimental sections analyze the reasons of these unexpected results.

References

[1]

Kamel Abdelouahab, Maxime Pelcat, Jocelyn Serot, Cedric Bourrasset, and Francois Berry. 2017. Tactics to Directly Map CNN graphs on Embedded FPGAs. IEEE Embedded Systems Letters (2017), 1--4.

[2]

Suyog Gupta, Ankur Agrawal, Pritish Narayanan, Kailash Gopalakrishnan, and Pritish Narayanan. 2015. Deep Learning with Limited Numerical Precision. In Proceedings of the International Conference on Machine Learning - ICML '15. 1737--1746. http://jmlr.org/proceedings/papers/v37/gupta15.pdf

Digital Library

[3]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition - CVPR '16. 770--778.

[4]

Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. 2016. Binarized neural networks. In Advances in Neural Information Processing Systems - NIPS' 16. 4107--4115. http://arxiv.org/abs/1602.02830

Digital Library

[5]

Honglan Jiang, Jie Han, and Fabrizio Lombardi. 2015. A Comparative Review and Evaluation of Approximate Adders. In Proceedings of the Edition on Great Lakes Symposium on VLSI - GLSVLSI '15. ACM Press, 343--348.

Digital Library

[6]

Alex Krizhevsky, Ilya Sutskever, Hinton Geoffrey E., and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems - NIPS'12. 1âĂŞ9.

Digital Library

[7]

Jonathan Long, Evan Shelhamer, and Trevor Darrell. 2015. Fully Convolutional Networks for Semantic Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition - CVPR '15. 3431--3440. https://people.eecs.berkeley.edu/~jonlong/long_shelhamer_fcn.pdf

[8]

Yufei Ma, Naveen Suda, Yu Cao, Sarma Vrudhula, and Jae-sun Seo. 2018. ALAMO: FPGA acceleration of deep learning algorithms with a modularized RTL compiler. Integration (1 2018).

[9]

H R Mahdiani, A Ahmadi, S M Fakhraie, and C Lucas. 2010. Bio-Inspired Imprecise Computational Blocks for Efficient VLSI Implementation of Soft-Computing Applications. IEEE Transactions on Circuits and Systems I: Regular Papers 57, 4 (4 2010), 850--862.

Digital Library

[10]

Eriko Nurvitadhi, Suchit Subhaschandra, Guy Boudoukh, Ganesh Venkatesh, Jaewoong Sim, Debbie Marr, Randy Huang, Jason OngGeeHock, Yeong Tat Liew, Krishnan Srivatsan, and Duncan Moss. 2017. Can FPGAs Beat GPUs in Accelerating Next-Generation Deep Neural Networks?. In Proceedings of the ACM/SIGDA International Symposium on Field-Programmable Gate Arrays - FPGA '17. 5--14.

Digital Library

[11]

Jiantao Qiu, Jie Wang, Song Yao, Kaiyuan Guo, Boxun Li, Erjin Zhou, Jincheng Yu, Tianqi Tang, Ningyi Xu, Sen Song, Yu Wang, and Huazhong Yang. 2016. Going Deeper with Embedded FPGA Platform for Convolutional Neural Network. In Proceedings of the ACM/SIGDA International Symposium on Field-Programmable Gate Arrays - FPGA '16. ACM, New York, NY, USA, 26--35.

Digital Library

[12]

Mohammad Rastegari, Vicente Ordonez, Joseph Redmon, and Ali Farhadi. 2016. XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. In Proceedings of the European Conference on Computer Vision - ECCV' 16. https://arxiv.org/pdf/1603.05279.pdf

[13]

Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. Technical Report. http://arxiv.org/abs/1804.02767

[14]

Yevgen Voronenko and Markus Püschel. 2007. Multiplierless multiple constant multiplication. ACM Transactions on Algorithms 3, 2 (5 2007), 11--es.

Digital Library

[15]

Jiaxiang Wu, Cong Leng, Yuhang Wang, Qinghao Hu, and Jian Cheng. 2016. Quantized Convolutional Neural Networks for Mobile Devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition - CVPR '16. 4820--4828. http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Wu_Quantized_Convolutional_Neural_CVPR_2016_paper.pdf

[16]

Chen Zhang, Peng Li, Guangyu Sun, Yijin Guan, Bingjun Xiao, and Jason Cong. 2015. Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks. In Proceedings of the ACM/SIGDA International Symposium on Field-Programmable Gate Arrays - FPGA '15 (FPGA). 161--170.

Digital Library

Cited By

Usman MZahid ADin Farrukh F(2023)Efficient Multipliers for CNN with Optimized Compression Techniques2023 20th International Bhurban Conference on Applied Sciences and Technology (IBCAST)10.1109/IBCAST59916.2023.10713003(291-296)Online publication date: 22-Aug-2023
https://doi.org/10.1109/IBCAST59916.2023.10713003
OK DPremson YSakthivel R(2022)Vedic Multiplier and Wallace Tree Adders Based Optimised Processing Element Unit for CNN on FPGA2022 IEEE International Power and Renewable Energy Conference (IPRECON)10.1109/IPRECON55716.2022.10059532(1-6)Online publication date: 16-Dec-2022
https://doi.org/10.1109/IPRECON55716.2022.10059532
Zahid AUsman MUd Din Farrukh F(2022)Energy-Efficient Approximate Booth Multipliers for Convolutional Neural Networks2022 19th International Bhurban Conference on Applied Sciences and Technology (IBCAST)10.1109/IBCAST54850.2022.9990150(268-272)Online publication date: 16-Aug-2022
https://doi.org/10.1109/IBCAST54850.2022.9990150
Show More Cited By

The challenge of multi-operand adders in CNNs on FPGAs: how not to solve it!
1. Hardware
  1. Integrated circuits
    1. Logic circuits

Recommendations

Fast, Efficient Floating-Point Adders and Multipliers for FPGAs

Floating-point applications are a growing trend in the FPGA community. As such, it has become critical to create floating-point units optimized for standard FPGA technology. Unfortunately, the FPGA design space is very different from the VLSI design ...
Multioperand Redundant Adders on FPGAs

Although redundant addition is widely used to design parallel multioperand adders for ASIC implementations, the use of redundant adders on Field Programmable Gate Arrays (FPGAs) has generally been avoided. The main reasons are the efficient ...
Efficient AES implementations on ASICs and FPGAs
AES'04: Proceedings of the 4th international conference on Advanced Encryption Standard

In this article, we present two AES hardware architectures: one for ASICs and one for FPGAs. Both architectures utilize the similarities of encryption and decryption to provide a high throughput using only a relatively small area. The presented ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

SAMOS '18: Proceedings of the 18th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation

July 2018

263 pages

ISBN:9781450364942

DOI:10.1145/3229631

General Chair:
Trevor Mudge
University of Michigan - Ann Arbor
,
Program Chair:
Dionisios N. Pnevmatikatos
Technical University of Crete and ICS - FORTH, Greece

Copyright © 2018 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]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 15 July 2018

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Funding Sources

Conference

SAMOS XVIII

SAMOS XVIII: Architectures, Modeling, and Simulation

July 15 - 19, 2018

Pythagorion, Greece

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

9
Total Citations
View Citations
113
Total Downloads

Downloads (Last 12 months)13
Downloads (Last 6 weeks)1

Reflects downloads up to 11 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Usman MZahid ADin Farrukh F(2023)Efficient Multipliers for CNN with Optimized Compression Techniques2023 20th International Bhurban Conference on Applied Sciences and Technology (IBCAST)10.1109/IBCAST59916.2023.10713003(291-296)Online publication date: 22-Aug-2023
https://doi.org/10.1109/IBCAST59916.2023.10713003
OK DPremson YSakthivel R(2022)Vedic Multiplier and Wallace Tree Adders Based Optimised Processing Element Unit for CNN on FPGA2022 IEEE International Power and Renewable Energy Conference (IPRECON)10.1109/IPRECON55716.2022.10059532(1-6)Online publication date: 16-Dec-2022
https://doi.org/10.1109/IPRECON55716.2022.10059532
Zahid AUsman MUd Din Farrukh F(2022)Energy-Efficient Approximate Booth Multipliers for Convolutional Neural Networks2022 19th International Bhurban Conference on Applied Sciences and Technology (IBCAST)10.1109/IBCAST54850.2022.9990150(268-272)Online publication date: 16-Aug-2022
https://doi.org/10.1109/IBCAST54850.2022.9990150
Farrukh FZhang CJiang YZhang ZWang ZWang ZJiang H(2020)Power Efficient Tiny Yolo CNN using Reduced Hardware Resources based on Booth Multiplier and WALLACE Tree AddersIEEE Open Journal of Circuits and Systems10.1109/OJCAS.2020.3007334(1-1)Online publication date: 2020
https://doi.org/10.1109/OJCAS.2020.3007334
Jo CLee K(2020)Bit-Serial multiplier based Neural Processing Element with Approximate adder tree2020 International SoC Design Conference (ISOCC)10.1109/ISOCC50952.2020.9332993(286-287)Online publication date: 21-Oct-2020
https://doi.org/10.1109/ISOCC50952.2020.9332993
Kowsalya T(2020)RETRACTED ARTICLE: A novel cognitive Wallace compressor based multi operand adders in CNN architecture for FPGAJournal of Ambient Intelligence and Humanized Computing10.1007/s12652-020-02402-312:7(7263-7271)Online publication date: 7-Aug-2020
https://doi.org/10.1007/s12652-020-02402-3
Liu XChen FHa Y(2019)Area Efficient Box Filter Acceleration by Parallelizing with Optimized Adder Tree2019 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)10.1109/ISVLSI.2019.00019(55-60)Online publication date: Jul-2019
https://doi.org/10.1109/ISVLSI.2019.00019
Farrukh FXie TZhang CWang Z(2019)A Solution to Optimize Multi-Operand Adders in CNN Architecture on FPGA2019 IEEE International Symposium on Circuits and Systems (ISCAS)10.1109/ISCAS.2019.8702777(1-4)Online publication date: May-2019
https://doi.org/10.1109/ISCAS.2019.8702777
Wu XHu RBao Y(2019)Parallelism Optimized Architecture on FPGA for Real-Time Traffic Light DetectionIEEE Access10.1109/ACCESS.2019.29590847(178167-178176)Online publication date: 2019
https://doi.org/10.1109/ACCESS.2019.2959084
Mayannavar SWali U(2019)Design of Hardware Accelerator for Artificial Neural Networks Using Multi-operand AdderInformation, Communication and Computing Technology10.1007/978-981-15-1384-8_14(167-177)Online publication date: 13-Nov-2019
https://doi.org/10.1007/978-981-15-1384-8_14

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