Your browser does not allow JavaScript!
JavaScript is necessary for the proper functioning of this website. Please enable JavaScript or use a modern browser.
|
|
SLO
|
ENG
|
Cookies and privacy
DKUM
EPF - Faculty of Business and Economics
FE - Faculty of Energy Technology
FERI - Faculty of Electrical Engineering and Computer Science
FF - Faculty of Arts
FGPA - Faculty of Civil Engineering, Transportation Engineering and Architecture
FKBV - Faculty of Agriculture and Life Sciences
FKKT - Faculty of Chemistry and Chemical Engineering
FL - Faculty of Logistic
FNM - Faculty of Natural Sciences and Mathematics
FOV - Faculty of Organizational Sciences in Kranj
FS - Faculty of Mechanical Engineering
FT - Faculty of Tourism
FVV - Faculty of Criminal Justice and Security
FZV - Faculty of Health Sciences
MF - Faculty of Medicine
PEF - Faculty of Education
PF - Faculty of Law
UKM - University of Maribor Library
UM - University of Maribor
UZUM - University of Maribor Press
COBISS
Faculty of Business and Economic, Maribor
Faculty of Agriculture and Life Sciences, Maribor
Faculty of Logistics, Celje, Krško
Faculty of Organizational Sciences, Kranj
Faculty of Criminal Justice and Security, Ljubljana
Faculty of Health Sciences
Library of Technical Faculties, Maribor
Faculty of Medicine, Maribor
Miklošič Library FPNM, Maribor
Faculty of Law, Maribor
University of Maribor Library
Bigger font
|
Smaller font
Introduction
Search
Browsing
Upload document
Statistics
Login
First page
>
Show document
Show document
Title:
ČASOVNO UČINKOVITO STISKANJE PODATKOV NA GPU
Authors:
ID
Jerovšek, Robert
(
Author
)
ID
Žalik, Borut
(
Mentor
)
More about this mentor...
ID
Mongus, Domen
(
Comentor
)
Files:
UNI_Jerovsek_Robert_2011.pdf
(1,94 MB)
MD5: ADF9E7EAD1CE4B974BFEB95FFCE89F66
PID:
20.500.12556/dkum/74128041-9c87-46ee-9a3d-7e2a919edb22
Language:
Slovenian
Work type:
Undergraduate thesis
Organization:
FERI - Faculty of Electrical Engineering and Computer Science
Abstract:
Zaradi fizikalnih omejitev se je razvoj centralnih procesnih enot preusmeril iz večanja frekvence delovanja v večanje števila njihovih jeder. Tako je časovna učinkovitost algoritmov vse bolj odvisna od zmožnosti njihovega paralelnega izvajanja. V diplomskem delu predstavimo prilagoditev splošnonamenskega algoritma stiskanja podatkov za paralelno izvajanje. V ta namen najprej razdelimo vhodni niz podatkov v bloke in vsakega izmed njih neodvisno stisnemo. Izvajanje nato prenesemo na grafično procesno enoto s pomočjo programskega jezika OpenCL. Nadaljnje pohitritve dosežemo z uporabo pomnilnika konstant in pomnilnika tekstur. Z rezultati pokažemo, da lahko izvajalni čas v primerjavi s časom potrebnim za stiskanje na centralni procesni enoti tako tudi razpolovimo.
Keywords:
GPGPU
,
brezizgubno stiskanje podatkov
,
LZJB
,
OpenCL
,
paralelno programiranje
Place of publishing:
Maribor
Publisher:
[R. Jerovšek]
Year of publishing:
2011
PID:
20.500.12556/DKUM-19238
UDC:
004.925(043.2)
COBISS.SI-ID:
15218966
NUK URN:
URN:SI:UM:DK:NKMOMWMZ
Publication date in DKUM:
12.07.2011
Views:
2499
Downloads:
173
Metadata:
Categories:
KTFMB - FERI
Cite this work
Plain text
BibTeX
EndNote XML
EndNote/Refer
RIS
ABNT
ACM Ref
AMA
APA
Chicago 17th Author-Date
Harvard
IEEE
ISO 690
MLA
Vancouver
:
Copy citation
Average score:
(0 votes)
Your score:
Voting is allowed only for
logged in
users.
Share:
Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.
Secondary language
Language:
English
Title:
TIME EFFICIENT DATA COMPRESSION ON GPU
Abstract:
Processor development has, due to physical constraints, shifted from increasing clock speed to increasing the number of processor cores. Thus, time efficiency of algorithms increasingly depends more on their parallel execution capabilities. In this diploma work we present our enhancements to increase the performance of a general purpose data compression algorithm. We do this by first dividing our input data into individual data blocks which are then independantly compressed. Afterwards, the execution is transferred to the graphics processing unit. Further improvement is made by using the constants and texture memory. The results show that the execution time is halved in comparison to the execution time needed on the central processing unit.
Keywords:
GPGPU
,
losseless data compression
,
LZJB
,
OpenCL
,
parallel programming
Comments
Leave comment
You must
log in
to leave a comment.
Comments (0)
0 - 0 / 0
There are no comments!
Back
