Hartung-Gorre Verlag
Inh.: Dr.
Renate Gorre D-78465
Konstanz Fon: +49 (0)7533 97227 Fax: +49 (0)7533 97228 www.hartung-gorre.de
|
S
|
Series in
Microelectronics
edited by
Qiuting
Huang
Andreas Schenk
Mathieu
Maurice Luisier
Bernd
Witzigmann
Lukas Arno Jakob Cavigelli
Towards Energy-Efficient
Convolutional Neural
Network Inference
2019. XVIII, 234 pages. € 64,00.
ISBN 978-3-86628-651-1
Abstract:
Deep
learning and particularly
convolutional neural networks (CNNs) have become the
method of choice for most computer vision tasks.
The achieved leap
in accuracy has
dramatically increased the range
of possibilities and
created a demand
for running these compute and memory intensive algorithms on embedded
and mobile devices. In this thesis, we
evaluate the capabilities of software-programmable hardware, dive into specialized accelerators,
and explore the
potential of extremely
quantized CNNs—all with
special consideration to
external memory bandwidth, which
dominates the overall energy cost. We
establish that — including I/O — software-programmable platforms
can achieve 10–40 GOp/s/W, our specialized
accelerator for fixedpoint CNNs
achieves 630 GOp/s/W, binary-weight CNNs can be implemented with
up to 5.9 TOp/s/W and
very small binarized neural networks
implementable with purely
combinational logic could be run
directly on the sensor with 670 TOp/s/W.
About the Author
Lukas
Cavigelli was born in Zurich, Switzerland in 1990. He received
the M.Sc. degree
in electrical engineering and information
technology from ETH
Zurich in 2014.
He then joined
the group of Prof. Dr. Luca Benini at the
Integrated Systems Laboratory, ETH
Zurich, to pursue
a doctorate. Since his
graduation in 2019, he has continued his work there as a post-doctoral researcher. He has received the best paper award at the
VLSI-SoC’13 and the ICDSC’17 conferences and the Donald O. Pederson best paper
award of the IEEE Trans. on CAD in 2019.
Direkt bestellen bei / to
order directly from:
Hartung-Gorre Verlag / D-78465
Konstanz / Germany
Telefon: +49
(0) 7533 97227 Telefax: +49 (0) 7533
97228
http://www.hartung-gorre.de eMail: verlag@hartung-gorre.de