Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/1826
Title: | IP core for efficient zero-run length compression of CNN feature maps | Authors: | Erdeljan, Andrea Vukobratović B. Struharik, Rastislav |
Issue Date: | 5-Jan-2018 | Journal: | 2017 25th Telecommunications Forum, TELFOR 2017 - Proceedings | Abstract: | © 2017 IEEE. Convolutional Neural Networks (CNNs) are becoming a fundamental tool for machine learning. High performance and energy efficiency are of great importance for deployments of CNNs in many embedded applications. Energy consumption during CNN processing is dominated by memory access and since large networks do not fit on on-chip storage, they require expensive DRAM access. This paper introduces an universal Output Stream Manager (OSM) which can be used to compress and format data coming from a CNN accelerator and reduce external memory access. The OSM exploits the sparsity of data and implements two Zero-Run Length encoding algorithms and can be easily reconfigured to optimize usage for different CNN layers. | URI: | https://open.uns.ac.rs/handle/123456789/1826 | ISBN: | 9781538630723 | DOI: | 10.1109/TELFOR.2017.8249397 |
Appears in Collections: | FTN Publikacije/Publications |
Show full item record
SCOPUSTM
Citations
4
checked on May 6, 2023
Page view(s)
17
Last Week
8
8
Last month
0
0
checked on May 10, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.