Change search
ReferencesLink to record
Permanent link

Direct link
The Potential of the Intel (R) Xeon Phi (TM) for Supervised Deep Learning
Linnaeus University, Faculty of Technology, Department of Computer Science.
Linnaeus University, Faculty of Technology, Department of Computer Science.
2015 (English)In: Proceedings: 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security & 2015 IEEE 12th International Conference on Embedded Software and Systems, IEEE Press, 2015, 758-765 p.Conference paper (Refereed)
Abstract [en]

Supervised learning of Convolutional Neural Networks (CNNs), also known as supervised Deep Learning, is a computationally demanding process. To find the most suitable parameters of a network for a given application, numerous training sessions are required. Therefore, reducing the training time per session is essential to fully utilize CNNs in practice. While numerous research groups have addressed the training of CNNs using GPUs, so far not much attention has been paid to the Intel Xeon Phi coprocessor. In this paper we investigate empirically and theoretically the potential of the Intel Xeon Phi for supervised learning of CNNs. We design and implement a parallelization scheme named CHAOS that exploits both the thread-and SIMD-parallelism of the coprocessor. Our approach is evaluated on the Intel Xeon Phi 7120P using the MNIST dataset of handwritten digits for various thread counts and CNN architectures. Results show a 103.5x speed up when training our large network for 15 epochs using 244 threads, compared to one thread on the coprocessor. Moreover, we develop a performance model and use it to assess our implementation and answer what-if questions.

Place, publisher, year, edition, pages
IEEE Press, 2015. 758-765 p.
National Category
Computer Systems
Research subject
Computer and Information Sciences Computer Science, Computer Science
URN: urn:nbn:se:lnu:diva-47951DOI: 10.1109/HPCC-CSS-ICESS.2015.45ISI: 000380408100115ISBN: 978-1-4799-8937-9OAI: diva2:877421
HPCC 2015, 24-26 Aug.
Available from: 2015-12-07 Created: 2015-12-07 Last updated: 2016-09-20Bibliographically approved

Open Access in DiVA

fulltext(1781 kB)9 downloads
File information
File name FULLTEXT01.pdfFile size 1781 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Viebke, AndrePllana, Sabri
By organisation
Department of Computer Science
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 9 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 32 hits
ReferencesLink to record
Permanent link

Direct link