VLSI Design of a High-Performance Multicontext MQ Arithmetic Coder

The MQ arithmetic coding, which is an adaptive arithmetic coding developing from Q coding, has become a major throughput bottleneck of JPEG2000 compression due to its inherent serial operations. To overcome the bottleneck, this brief proposes a high-performance hardware architecture of the multicont...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on very large scale integration (VLSI) systems Vol. 31; no. 3; pp. 396 - 400
Main Authors: Jing, Peng, Zhang, Wei, Yan, Long, Liu, Yanyan
Format: Journal Article
Language:English
Published: New York IEEE 01.03.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Arithmetic coding
Computer architecture
Context
Encoding
Figure of merit
FPGA
Hardware
Image coding
Integrated circuits
JPEG2000
MQ arithmetic coding
multicontext architecture
Power consumption
Registers
Symbols
Throughput
Transform coding
ISSN:1063-8210, 1557-9999
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The MQ arithmetic coding, which is an adaptive arithmetic coding developing from Q coding, has become a major throughput bottleneck of JPEG2000 compression due to its inherent serial operations. To overcome the bottleneck, this brief proposes a high-performance hardware architecture of the multicontext MQ coder. The proposed architecture is capable of concurrent coding for two adjacent more probable symbols (MPSs). Performance analysis results show that the proposed coder consumes 1.61 CXD pairs per cycle and achieves a throughput of 506.93 MSymbols/s under 0.5 bpp bit rate. The proposed architecture not only achieves high throughput, but also maintains both low hardware utilization and low power consumption. Compared with the state-of-the-art two-context coder, the figure of merit (FoM) is increased by 38%. Compared with the single-context coder, the power-delay product (PDP) is reduced by 49%.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1063-8210
1557-9999
DOI:10.1109/TVLSI.2023.3234023