StreamSVD: Low-rank approximation and streaming accelerator co-design
File(s)
Author(s)
Yu, Zhewen
Bouganis, Christos-Savvas
Type
Conference Paper
Abstract
The post-training compression of a Convolutional Neural Network (CNN) aims to produce Pareto-optimal designs on the accuracy-performance frontier when the access to training data is not possible. Low-rank approximation is one of the methods that is often utilised in such cases. However, existing work considers the low-rank approximation of the network and the optimisation of the hardware accelerator separately, leading to systems with sub-optimal performance. This work focuses on the efficient mapping of a CNN into an FPGA device, and presents StreamSVD, a model-accelerator co-design framework 1 . The framework considers simultaneously the compression of a CNN model through a hardware-aware low-rank approximation scheme, and the optimisation of the hardware accelerator's architecture by taking into account the approximation scheme's compute structure. Our results show that the co-designed StreamSVD outperforms existing work that utilises similar low-rank approximation schemes by providing better accuracy-throughput trade-off. The proposed framework also achieves competitive performance compared with other post-training compression methods, even outperforming them under certain cases.
Date Issued
2021-11-23
Date Acceptance
2021-11-01
Citation
2021 International Conference on Field-Programmable Technology (ICFPT), 2021, pp.69-77
Publisher
IEEE
Start Page
69
End Page
77
Journal / Book Title
2021 International Conference on Field-Programmable Technology (ICFPT)
Copyright Statement
Copyright © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Identifier
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000792703100010&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=a2bf6146997ec60c407a63945d4e92bb
Source
20th International Conference on Field-Programmable Technology (ICFPT)
Subjects
Computer Science
Computer Science, Interdisciplinary Applications
Engineering
Engineering, Electrical & Electronic
Science & Technology
Technology
Publication Status
Published
Start Date
2021-12-06
Finish Date
2021-12-10
Coverage Spatial
ELECTR NETWORK
Date Publish Online
2021-11-23