Show simple item record

dc.contributor.authorTrompouki, Matina M.
dc.contributor.authorKosmidis, Leonidas
dc.contributor.authorNavarro, Nacho
dc.contributor.otherBarcelona Supercomputing Center
dc.date.accessioned2018-03-26T08:52:26Z
dc.date.available2018-03-26T08:52:26Z
dc.date.issued2017-12-14
dc.identifier.citationTrompouki, M. M.; Kosmidis, L.; Navarro, N. An open benchmark implementation for multi-CPU multi-GPU pedestrian detection in automotive systems. A: "2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)". IEEE, 2017, p. 305-312.
dc.identifier.isbn978-1-5386-3093-8
dc.identifier.urihttp://hdl.handle.net/2117/115853
dc.description.abstractModern and future automotive systems incorporate several Advanced Driving Assistance Systems (ADAS). Those systems require significant performance that cannot be provided with traditional automotive processors and programming models. Multicore CPUs and Nvidia GPUs using CUDA are currently considered by both automotive industry and research community to provide the necessary computational power. However, despite several recent published works in this domain, there is an absolute lack of open implementations of GPU-based ADAS software, that can be used for benchmarking candidate platforms. In this work, we present a multi-CPU and GPU implementation of an open implementation of a pedestrian detection benchmark based on the Viola-Jones image recognition algorithm. We present our optimization strategies and evaluate our implementation on a multiprocessor system featuring multiple GPUs, showing an overall 88.5× speedup over the sequential version.
dc.description.sponsorshipThis work has been supported by the Spanish Ministry of Science and Innovation under grant TIN2015-65316P, the HiPEAC Network of Excellence and a Microsoft sponsored ACM SRC. The first two authors acknowledge Dr. Petrisor for her assistance in understanding and using the sequential version of the benchmark and dedicate this article to the memory of the late beloved advisor prof. Nacho Navarro, without whom this work would not have been possible.
dc.format.extent8 p.
dc.language.isoeng
dc.publisherIEEE
dc.subjectÀrees temàtiques de la UPC::Informàtica
dc.subject.lcshHigh performance computing
dc.subject.lcshParallel processing (Electronic computers)
dc.subject.otherDriver information systems
dc.subject.otherGraphics processing units
dc.subject.otherImage recognition
dc.subject.otherMultiprocessing systems
dc.subject.otherParallel architectures
dc.titleAn open benchmark implementation for multi-CPU multi-GPU pedestrian detection in automotive systems
dc.typeConference lecture
dc.subject.lemacProcessament en paral·lel (Ordinadors)
dc.subject.lemacSupercomputadors
dc.identifier.doi10.1109/ICCAD.2017.8203793
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://ieeexplore.ieee.org/document/8203793/
dc.rights.accessOpen Access
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/PE2013-2016/TIN2015-65316-P
upcommons.citation.publishedtrue
upcommons.citation.publicationName2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
upcommons.citation.startingPage305
upcommons.citation.endingPage312


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder