Lightning Talk: Efficiency and Programmability of DNN Accelerators and GPUs

Won Woo Ro

doi:10.1109/DAC56929.2023.10247689

Lightning Talk: Efficiency and Programmability of DNN Accelerators and GPUs

Won Woo Ro

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

While GPUs have provided high computational power for AI applications, their power efficiency may not be satisfied for applications requiring a high-speed response within a low power budget. Specialized deep neural network (DNN) accelerators have been developed to address this challenge. However, there are still limitations and concerns surrounding the adoption of DNN accelerators as a viable choice for commercial products. This lightning talk aims to highlight the importance of fast and domain-specific DNN accelerators and discuss the additional features they should possess besides speed and power efficiency. By addressing these points, the talk will shed light on the necessity of specialized DNN accelerators and explore potential areas for improvement to meet the growing demands of efficient and high-performance AI computations.

Original language	English
Title of host publication	2023 60th ACM/IEEE Design Automation Conference, DAC 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350323481
DOIs	https://doi.org/10.1109/DAC56929.2023.10247689
Publication status	Published - 2023
Event	60th ACM/IEEE Design Automation Conference, DAC 2023 - San Francisco, United States Duration: 2023 Jul 9 → 2023 Jul 13

Publication series

Name	Proceedings - Design Automation Conference
Volume	2023-July
ISSN (Print)	0738-100X

Conference

Conference	60th ACM/IEEE Design Automation Conference, DAC 2023
Country/Territory	United States
City	San Francisco
Period	23/7/9 → 23/7/13

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

All Science Journal Classification (ASJC) codes

Computer Science Applications
Control and Systems Engineering
Electrical and Electronic Engineering
Modelling and Simulation

Access to Document

10.1109/DAC56929.2023.10247689

Cite this

@inproceedings{e17c0e109c2f4161a501d451b623bb46,

title = "Lightning Talk: Efficiency and Programmability of DNN Accelerators and GPUs",

abstract = "While GPUs have provided high computational power for AI applications, their power efficiency may not be satisfied for applications requiring a high-speed response within a low power budget. Specialized deep neural network (DNN) accelerators have been developed to address this challenge. However, there are still limitations and concerns surrounding the adoption of DNN accelerators as a viable choice for commercial products. This lightning talk aims to highlight the importance of fast and domain-specific DNN accelerators and discuss the additional features they should possess besides speed and power efficiency. By addressing these points, the talk will shed light on the necessity of specialized DNN accelerators and explore potential areas for improvement to meet the growing demands of efficient and high-performance AI computations.",

author = "Ro, {Won Woo}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 60th ACM/IEEE Design Automation Conference, DAC 2023 ; Conference date: 09-07-2023 Through 13-07-2023",

year = "2023",

doi = "10.1109/DAC56929.2023.10247689",

language = "English",

series = "Proceedings - Design Automation Conference",

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

booktitle = "2023 60th ACM/IEEE Design Automation Conference, DAC 2023",

address = "United States",

}

Ro, WW 2023, Lightning Talk: Efficiency and Programmability of DNN Accelerators and GPUs. in 2023 60th ACM/IEEE Design Automation Conference, DAC 2023. Proceedings - Design Automation Conference, vol. 2023-July, Institute of Electrical and Electronics Engineers Inc., 60th ACM/IEEE Design Automation Conference, DAC 2023, San Francisco, United States, 23/7/9. https://doi.org/10.1109/DAC56929.2023.10247689

TY - GEN

T1 - Lightning Talk

T2 - 60th ACM/IEEE Design Automation Conference, DAC 2023

AU - Ro, Won Woo

PY - 2023

Y1 - 2023

N2 - While GPUs have provided high computational power for AI applications, their power efficiency may not be satisfied for applications requiring a high-speed response within a low power budget. Specialized deep neural network (DNN) accelerators have been developed to address this challenge. However, there are still limitations and concerns surrounding the adoption of DNN accelerators as a viable choice for commercial products. This lightning talk aims to highlight the importance of fast and domain-specific DNN accelerators and discuss the additional features they should possess besides speed and power efficiency. By addressing these points, the talk will shed light on the necessity of specialized DNN accelerators and explore potential areas for improvement to meet the growing demands of efficient and high-performance AI computations.

AB - While GPUs have provided high computational power for AI applications, their power efficiency may not be satisfied for applications requiring a high-speed response within a low power budget. Specialized deep neural network (DNN) accelerators have been developed to address this challenge. However, there are still limitations and concerns surrounding the adoption of DNN accelerators as a viable choice for commercial products. This lightning talk aims to highlight the importance of fast and domain-specific DNN accelerators and discuss the additional features they should possess besides speed and power efficiency. By addressing these points, the talk will shed light on the necessity of specialized DNN accelerators and explore potential areas for improvement to meet the growing demands of efficient and high-performance AI computations.

UR - http://www.scopus.com/inward/record.url?scp=85173123350&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85173123350&partnerID=8YFLogxK

U2 - 10.1109/DAC56929.2023.10247689

DO - 10.1109/DAC56929.2023.10247689

M3 - Conference contribution

AN - SCOPUS:85173123350

T3 - Proceedings - Design Automation Conference

BT - 2023 60th ACM/IEEE Design Automation Conference, DAC 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 9 July 2023 through 13 July 2023

ER -

Lightning Talk: Efficiency and Programmability of DNN Accelerators and GPUs

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this