General reuse-centric CNN accelerator

buir.advisorÖztürk, Özcan
dc.contributor.authorÇiçek, Nihat Mert
dc.date.accessioned2021-02-10T13:20:02Z
dc.date.available2021-02-10T13:20:02Z
dc.date.copyright2021-02
dc.date.issued2021-02
dc.date.submitted2021-02-09
dc.descriptionCataloged from PDF version of article.en_US
dc.descriptionThesis (M.S.): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2021.en_US
dc.descriptionIncludes bibliographical references (leaves 48-53).en_US
dc.description.abstractReuse-centric CNN acceleration speeds up CNN inference by reusing computa-tions for similar neuron vectors in CNN’s input layer or activation maps. This new paradigm of optimizations is however largely limited by the overheads in neuron vector similarity detection, an important step in reuse-centric CNN. This thesis presents the first in-depth exploration of architectural support for reuse-centric CNN. It proposes a hardware accelerator, which improves neuron vector similar-ity detection and reduces the energy consumption of reuse-centric CNN inference. The accelerator is implemented to support a wide variety of network settings with a banked memory subsystem. Design exploration is performed through RTL sim-ulation and synthesis on an FPGA platform. When integrated into Eyeriss, the accelerator can potentially provide improvements up to 7.75X in performance. Furthermore, it can make the similarity detection up to 95.46% more energy-eÿcient, and it can accelerate the convolutional layer up to 3.63X compared to the software-based implementation running on the CPU.en_US
dc.description.provenanceSubmitted by Betül Özen (ozen@bilkent.edu.tr) on 2021-02-10T13:20:02Z No. of bitstreams: 1 Master_Thesis_Bilkent_NihatMertCicek_v3.pdf: 1581665 bytes, checksum: 7b7a558f724e85376a3f19ae8fec80a8 (MD5)en
dc.description.provenanceMade available in DSpace on 2021-02-10T13:20:02Z (GMT). No. of bitstreams: 1 Master_Thesis_Bilkent_NihatMertCicek_v3.pdf: 1581665 bytes, checksum: 7b7a558f724e85376a3f19ae8fec80a8 (MD5) Previous issue date: 2021-02en
dc.description.statementofresponsibilityby Nihat Mert Çiçeken_US
dc.embargo.release2021-08-09
dc.format.extentxi, 53 leaves : charts (some color) ; 30 cm.en_US
dc.identifier.itemidB151782
dc.identifier.urihttp://hdl.handle.net/11693/55049
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectCNNen_US
dc.subjectReuse-centricen_US
dc.subjectAcceleratoren_US
dc.subjectInferenceen_US
dc.titleGeneral reuse-centric CNN acceleratoren_US
dc.title.alternativeGenel yeniden kullanım merkezli CNN hızlandırıcıen_US
dc.typeThesisen_US
thesis.degree.disciplineComputer Engineering
thesis.degree.grantorBilkent University
thesis.degree.levelMaster's
thesis.degree.nameMS (Master of Science)

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Master_Thesis_Bilkent_NihatMertCicek_v3.pdf
Size:
1.51 MB
Format:
Adobe Portable Document Format
Description:
Full printable version

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: