SRNPU: An Energy-Efficient CNN-Based Super-Resolution Processor With Tile-Based Selective Super-Resolution in Mobile Devices

Cited 3 time in webofscience Cited 0 time in scopus
  • Hit : 78
  • Download : 0
In this article, we propose an energy-efficient convolutional neural network (CNN) based super-resolution (SR) processor, super-resolution neural processing unit (SRNPU), for mobile applications. Traditionally, it is hard to realize real-time CNN-based SR on resource-limited platforms like mobile devices due to its massive amount of computation workload and communication bandwidth with external memory. The SRNPU can support the tile-based selective super-resolution (TSSR) which dynamically selects the proper sized CNN in a tile-by-tile manner. The TSSR reduces the computational workload of CNN-based SR by 31.1 % while maintaining image restoration performance. Moreover, a proposed selective caching based convolutional layer fusion ((SCLF)-L-2) can reduce 78.8% of external memory bandwidth with 93.2 % smaller on-chip memory footprint compared with previous layer fusion methods, by only caching short reuse distance intermediate feature maps. Additionally, reconfigurable cyclic ring architecture in the SRNPU enables maintaining high PE utilization by amortizing the reloading process caused by SC2LF operation under various convolutional layer configurations. The SRNPU is fabricated in 65 nm CMOS technology and occupies 4x4 mm(2) die area. The SRNPU has a peak power efficiency of 1.9 TOPS/Wat 0.75 V, 50 MHz. The SRNPU achieves 31.8 fps x2 scale Full-HD generation and 88.3 fps x4 scale Full-HD generation with higher restoration performance and power efficiency than previous SR hardware implementations. To the best of our knowledge, the SRNPU is the first ASIC implementation of the CNN-based SR algorithm which supports real-time Full-HD up-scaling.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2020-09
Language
English
Article Type
Article
Citation

IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS, v.10, no.3, pp.320 - 334

ISSN
2156-3357
DOI
10.1109/JETCAS.2020.3014454
URI
http://hdl.handle.net/10203/281889
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 3 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0