Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor

Nazim Altar Koca; Berkay Yildiz; Yusuf Caner Demirkol; Berna Örs

doi:10.23919/ELECO54474.2021.9677758

Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor

Nazim Altar Koca
, Berkay Yildiz
, Yusuf Caner Demirkol
, Berna Örs

Elektronik ve Hab.Müh.Bölümü

Istanbul Technical University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

1 Atıf (Scopus)

Özet

The need for domain-specific hardware architectures of neural network models is increasing with the rapid development of autonomous cars, robotics and IOT. For these data-driven systems, new fast and efficient hardware methodologies are introduced recently. In this study, a comparison between general purpose RISC-V processor and customized version of it will be presented. Customized version consists of local memory structure, special float computing unit and an interface to communicate with core. It is aimed to show by using the strong sides of these two hardware more efficient and fast architectures can be achieved.

Orijinal dil	İngilizce
Ana bilgisayar yayını başlığı	2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
Sayfalar	465-469
Sayfa sayısı	5
ISBN (Elektronik)	9786050114379
DOI'lar	https://doi.org/10.23919/ELECO54474.2021.9677758
Yayın durumu	Yayınlandı - 2021
Etkinlik	13th International Conference on Electrical and Electronics Engineering, ELECO 2021 - Virtual, Bursa, Türkiye Süre: 25 Kas 2021 → 27 Kas 2021

Yayın serisi

Adı	2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	13th International Conference on Electrical and Electronics Engineering, ELECO 2021
Ülke/Bölge	Türkiye
Şehir	Virtual, Bursa
Periyot	25/11/21 → 27/11/21

Bibliyografik not

Publisher Copyright:
© 2021 Chamber of Turkish Electrical Engineers.

Finansman

This study is supported by TUBITAK within the scope of 2209-A projects.

Finansörler
TUBITAK

Belgeye Erişim

10.23919/ELECO54474.2021.9677758

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Koca, N. A., Yildiz, B., Demirkol, Y. C., & Örs, B. (2021). Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor. In 2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021 (pp. 465-469). (2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ELECO54474.2021.9677758

Koca, Nazim Altar ; Yildiz, Berkay ; Demirkol, Yusuf Caner et al. / Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor. 2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 465-469 (2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021).

@inproceedings{99b9dbe4d88c4cd58ff2ed3e5f6bab24,

title = "Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor",

abstract = "The need for domain-specific hardware architectures of neural network models is increasing with the rapid development of autonomous cars, robotics and IOT. For these data-driven systems, new fast and efficient hardware methodologies are introduced recently. In this study, a comparison between general purpose RISC-V processor and customized version of it will be presented. Customized version consists of local memory structure, special float computing unit and an interface to communicate with core. It is aimed to show by using the strong sides of these two hardware more efficient and fast architectures can be achieved.",

author = "Koca, \{Nazim Altar\} and Berkay Yildiz and Demirkol, \{Yusuf Caner\} and Berna {\"O}rs",

note = "Publisher Copyright: {\textcopyright} 2021 Chamber of Turkish Electrical Engineers.; 13th International Conference on Electrical and Electronics Engineering, ELECO 2021 ; Conference date: 25-11-2021 Through 27-11-2021",

year = "2021",

doi = "10.23919/ELECO54474.2021.9677758",

language = "English",

series = "2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "465--469",

booktitle = "2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021",

address = "United States",

}

Koca, NA, Yildiz, B, Demirkol, YC & Örs, B 2021, Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor. in 2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021. 2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021, Institute of Electrical and Electronics Engineers Inc., pp. 465-469, 13th International Conference on Electrical and Electronics Engineering, ELECO 2021, Virtual, Bursa, Türkiye, 25/11/21. https://doi.org/10.23919/ELECO54474.2021.9677758

Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor. / Koca, Nazim Altar; Yildiz, Berkay; Demirkol, Yusuf Caner et al.
2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 465-469 (2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

TY - GEN

T1 - Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor

AU - Koca, Nazim Altar

AU - Yildiz, Berkay

AU - Demirkol, Yusuf Caner

AU - Örs, Berna

PY - 2021

Y1 - 2021

N2 - The need for domain-specific hardware architectures of neural network models is increasing with the rapid development of autonomous cars, robotics and IOT. For these data-driven systems, new fast and efficient hardware methodologies are introduced recently. In this study, a comparison between general purpose RISC-V processor and customized version of it will be presented. Customized version consists of local memory structure, special float computing unit and an interface to communicate with core. It is aimed to show by using the strong sides of these two hardware more efficient and fast architectures can be achieved.

AB - The need for domain-specific hardware architectures of neural network models is increasing with the rapid development of autonomous cars, robotics and IOT. For these data-driven systems, new fast and efficient hardware methodologies are introduced recently. In this study, a comparison between general purpose RISC-V processor and customized version of it will be presented. Customized version consists of local memory structure, special float computing unit and an interface to communicate with core. It is aimed to show by using the strong sides of these two hardware more efficient and fast architectures can be achieved.

UR - https://www.scopus.com/pages/publications/85125263521

U2 - 10.23919/ELECO54474.2021.9677758

DO - 10.23919/ELECO54474.2021.9677758

M3 - Conference contribution

AN - SCOPUS:85125263521

T3 - 2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021

SP - 465

EP - 469

BT - 2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th International Conference on Electrical and Electronics Engineering, ELECO 2021

Y2 - 25 November 2021 through 27 November 2021

ER -

Koca NA, Yildiz B, Demirkol YC, Örs B. Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor. In 2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 465-469. (2021 13th International Conference on Electrical and Electronics Engineering, ELECO 2021). doi: 10.23919/ELECO54474.2021.9677758

Multi-Layer Perceptron Hardware Accelerator on RISC-V Processor

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Finansman

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap