Lupulus: A Flexible Hardware Accelerator for Neural Networks

Andreas Toftegaard Kristensen, Robert Giterman, Alexios Balatsoukas-Stimming, Andreas Burg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Neural networks have become indispensable for a wide range of applications, but they suffer from high computationaland memory-requirements, requiring optimizations from the algorithmic description of the network to the hardware implementation. Moreover, the high rate of innovation in machine learning makes it important that hardware implementations provide a high level of programmability to support current and future requirements of neural networks. In this work, we present a flexible hardware accelerator for neural networks, called Lupulus, supporting various methods for scheduling and mapping of operations onto the accelerator. Lupulus was implemented in a 28nm FD-SOI technology and demonstrates a peak performance of 380GOPS/GHz with latencies of 21.4ms and 183.6ms for the convolutional layers of AlexNet and VGG-16, respectively.

Original languageEnglish
Title of host publication2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1608-1612
Number of pages5
ISBN (Electronic)9781509066315
DOIs
StatePublished - May 2020
Externally publishedYes
Event2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Barcelona, Spain
Duration: 4 May 20208 May 2020

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2020-May
ISSN (Print)1520-6149

Conference

Conference2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020
Country/TerritorySpain
CityBarcelona
Period4/05/208/05/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Fingerprint

Dive into the research topics of 'Lupulus: A Flexible Hardware Accelerator for Neural Networks'. Together they form a unique fingerprint.

Cite this