Performance Evaluations for Parallel Image Filter on Multi- Core Computer using Java Threads
Uloženo v:
| Název: | Performance Evaluations for Parallel Image Filter on Multi- Core Computer using Java Threads |
|---|---|
| Autoři: | Devrim Akgün |
| Přispěvatelé: | The Pennsylvania State University CiteSeerX Archives |
| Zdroj: | http://research.ijcaonline.org/volume74/number11/pxc3889836.pdf. |
| Sbírka: | CiteSeerX |
| Témata: | General Terms Parallel Computing, Image Filtering, Java Threads Keywords Parallel image filter, multi- core processing |
| Popis: | Developing multi- core computer technology made it practical to accelerate image processing algorithms via parallel running threads. In this study, performance evaluations for parallel image convolution filter on a multi-core computer using Java thread utilities was presented. For this purpose, the efficiency of static and the dynamic load scheduling implementations are investigated on a multi- core computer with six cores processor. Dynamic load scheduling overhead results were measured experimentally. Also the effect of busy running environment on performance which usually occurs on due to other running processes is illustrated by experimental measurements. According to performance results, about 5.7 times acceleration over sequential implementation was obtained on a six cores computer for various image sizes |
| Druh dokumentu: | text |
| Popis souboru: | application/pdf |
| Jazyk: | English |
| Relation: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.403.1706; http://research.ijcaonline.org/volume74/number11/pxc3889836.pdf |
| Dostupnost: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.403.1706 http://research.ijcaonline.org/volume74/number11/pxc3889836.pdf |
| Rights: | Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| Přístupové číslo: | edsbas.F90A4067 |
| Databáze: | BASE |
Nájsť tento článok vo Web of Science | Abstrakt: | Developing multi- core computer technology made it practical to accelerate image processing algorithms via parallel running threads. In this study, performance evaluations for parallel image convolution filter on a multi-core computer using Java thread utilities was presented. For this purpose, the efficiency of static and the dynamic load scheduling implementations are investigated on a multi- core computer with six cores processor. Dynamic load scheduling overhead results were measured experimentally. Also the effect of busy running environment on performance which usually occurs on due to other running processes is illustrated by experimental measurements. According to performance results, about 5.7 times acceleration over sequential implementation was obtained on a six cores computer for various image sizes |
|---|