A Real Time Super Resolution Accelerator with Tilted Layer Fusion

An Jung Huang, Kai Chieh Hsu, Tian Sheuan Chang

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

4 Scopus citations

Abstract

Deep learning based superresolution achieves high-quality results, but its heavy computational workload, large buffer, and high external memory bandwidth inhibit its usage in mobile devices. To solve the above issues, this paper proposes a real-time hardware accelerator with the tilted layer fusion method that reduces the external DRAM bandwidth by 92% and just needs 102KB on-chip memory. The design implemented with a 40nm CMOS process achieves 1920xl080@60fps throughput with 544. 3K gate count when running at 600MHz; it has higher throughput and lower area cost than previous designs.

Original languageEnglish
Title of host publicationIEEE International Symposium on Circuits and Systems, ISCAS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2665-2669
Number of pages5
ISBN (Electronic)9781665484855
DOIs
StatePublished - 2022
Event2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022 - Austin, United States
Duration: 27 May 20221 Jun 2022

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume2022-May
ISSN (Print)0271-4310

Conference

Conference2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022
Country/TerritoryUnited States
CityAustin
Period27/05/221/06/22

Keywords

  • Convolutional Neural Networks (CNNs)
  • deep learning accelerators
  • layer fusion
  • real-time
  • super-resolution

Fingerprint

Dive into the research topics of 'A Real Time Super Resolution Accelerator with Tilted Layer Fusion'. Together they form a unique fingerprint.

Cite this