A Real-Time Reconfigurable AI Processor Based on FPGA

Yue Ri Jeong, Kwonneung Cho, Youngwoo Jeong, Sun Beom Kwon, Seung Eun Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

As an AI application requires a lot of resources, optimization of hardware and software to target application is essential. Unlikely the software updates, it is hard to reconfigure the hardware architecture to the target application due to the static characteristics. In this paper, a real-time reconfigurable AI processor based on FPGA is proposed. The AI processor includes a reconfiguration block to update the FPGA and enables hardware reconfiguration with reasonable logic resources. The proposed reconfigurable AI processor was successfully implemented, and the feasibility was demonstrated by experimenting with the accuracy in various applications.

Original languageEnglish
Title of host publication2023 IEEE International Conference on Consumer Electronics, ICCE 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665491303
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Consumer Electronics, ICCE 2023 - Las Vegas, United States
Duration: 6 Jan 20238 Jan 2023

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
Volume2023-January
ISSN (Print)0747-668X

Conference

Conference2023 IEEE International Conference on Consumer Electronics, ICCE 2023
Country/TerritoryUnited States
CityLas Vegas
Period6/01/238/01/23

Keywords

  • AI application
  • hardware reconfiguration
  • optimization
  • reconfigurable AI processor

Fingerprint

Dive into the research topics of 'A Real-Time Reconfigurable AI Processor Based on FPGA'. Together they form a unique fingerprint.

Cite this