Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Performance landscape of CNN acceleration tools and resource constrained platforms

Miliadis Panagiotis

Simple record


URIhttp://purl.tuc.gr/dl/dias/D2FD3227-CA1F-4EF7-9FB3-9BA5A04CA1CE-
Identifierhttps://doi.org/10.26233/heallink.tuc.82994-
Languageen-
Extent89 pagesen
TitlePerformance landscape of CNN acceleration tools and resource constrained platformsel
TitleΑξιολόγηση της απόδοσης των εργαλείων επιτάχυνσης των συνελικτικών νευρωνικών δικτύων και των πλατφορμών περιορισμένων πόρωνel
CreatorMiliadis Panagiotisen
CreatorΜηλιαδης Παναγιωτηςel
Contributor [Thesis Supervisor]Pnevmatikatos Dionysiosen
Contributor [Thesis Supervisor]Πνευματικατος Διονυσιοςel
Contributor [Committee Member]Dollas Apostolosen
Contributor [Committee Member]Δολλας Αποστολοςel
Contributor [Committee Member]Theodoropoulos Dimitriosen
Contributor [Committee Member]Θεοδωροπουλος Δημητριοςel
PublisherΠολυτεχνείο Κρήτηςel
PublisherTechnical University of Creteen
Academic UnitTechnical University of Crete::School of Electrical and Computer Engineeringen
Academic UnitΠολυτεχνείο Κρήτης::Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστώνel
Content SummaryOver the last years, a rapid growth in the development of applications that are based on Convolutional Neural Networks is observed. Despite of the large advances in processor units, the use of computer vision tasks is still challenging in resource constrained platforms. This thesis will present four toolkits, that accelerate the performance of inference applications by targeting the processor units from the top hardware vendors; Intel, Nvidia, Arm and Xilinx. In order to achieve optimal execution, the toolkits exploit the hardware acceleration that processors provide, as well as special processor units and platforms, which are specially developed for deep learning inference tasks. The most well-known models for each task are described, alongside with the frameworks that the toolkits support and are used for model representation. Last but not least, real-world performance results are collected for different batches of images, in order to achieve a performance landscape of the existing tools.en
Type of ItemΔιπλωματική Εργασίαel
Type of ItemDiploma Worken
Licensehttp://creativecommons.org/licenses/by-nc/4.0/en
Date of Item2019-09-02-
Date of Publication2019-
SubjectCNNen
SubjectAccelerationen
SubjectAcceleration toolsen
Bibliographic CitationPanagiotis Miliadis, "Performance landscape of CNN acceleration tools and resource constrained platforms", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2019en
Bibliographic CitationΠαναγιώτης Μηλιάδης, "Αξιολόγηση της απόδοσης των εργαλείων επιτάχυνσης των συνελικτικών νευρωνικών δικτύων και των πλατφορμών περιορισμένων πόρων", Διπλωματική Εργασία, Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών, Πολυτεχνείο Κρήτης, Χανιά, Ελλάς, 2019el

Available Files

Services

Statistics