Other formats:
BibTeX
LaTeX
RIS
@inproceedings{950789,
author = {Matela, Jiří and Šrom, Martin and Holub, Petr},
address = {Heidelberg},
booktitle = {Lecture Notes in Computer Science 7119},
doi = {http://dx.doi.org/10.1007/978-3-642-25929-6_13},
keywords = {JPEG2000; GPU; arithmetic coding; MQ-Coding; image compression; parallel; low-occupancy; CUDA},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Heidelberg},
isbn = {978-3-642-25928-9},
pages = {136-145},
publisher = {Springer Berlin / Heidelberg},
title = {Low GPU Occupancy Approach to Fast Arithmetic Coding in JPEG2000},
url = {http://www.springerlink.com/content/k773733872742728/},
year = {2012}
}
TY - JOUR
ID - 950789
AU - Matela, Jiří - Šrom, Martin - Holub, Petr
PY - 2012
TI - Low GPU Occupancy Approach to Fast Arithmetic Coding in JPEG2000
PB - Springer Berlin / Heidelberg
CY - Heidelberg
SN - 9783642259289
KW - JPEG2000
KW - GPU
KW - arithmetic coding
KW - MQ-Coding
KW - image compression
KW - parallel
KW - low-occupancy
KW - CUDA
UR - http://www.springerlink.com/content/k773733872742728/
L2 - http://www.springerlink.com/content/k773733872742728/
N2 - Arithmetic coding, and especially adaptive MQ-Coder of JPEG2000, is a serial process which does not match well specifics of GPUs as massively parallel processors. In this paper we study and evaluate several approaches to acceleration of MQ-Coding using commodity GPU hardware, including proposal of a new enhanced renormalization procedure. We conclude with "low occupancy approach" and 5.6--16x average speedup when compared to state of the art multi-threaded CPU implementations.
ER -
MATELA, Jiří, Martin ŠROM and Petr HOLUB. Low GPU Occupancy Approach to Fast Arithmetic Coding in JPEG2000. In \textit{Lecture Notes in Computer Science 7119}. Heidelberg: Springer Berlin / Heidelberg, 2012, p.~136-145. ISBN~978-3-642-25928-9. Available from: https://dx.doi.org/10.1007/978-3-642-25929-6\_{}13.
|
