Detail publikačního výsledku

GPU Acceleration of 2D-DWT Image Compression in MATLAB with CUDA

ŠIMEK, V.

Originální název

GPU Acceleration of 2D-DWT Image Compression in MATLAB with CUDA

Anglický název

GPU Acceleration of 2D-DWT Image Compression in MATLAB with CUDA

Druh

Stať ve sborníku mimo WoS a Scopus

Originální abstrakt

Thisarticle will present the details about the acceleration of 2D wavelet-basedmedical data (image) compression on MATLAB with CUDA. It is obvious that thediagnostic materials (mostly as a certain type of image) are increasinglyacquired in a digital format. Therefore, common need to daily manipulate hugeamount of data brought about the issue of compression within a very lessstipulated amount of time. Attention will be given to the accelerationprocessing flow which exploits the massive parallel computational power offered by the latest NVIDIA graphicsprocessor unit (GPU). It brings a compute device that can be programmed using aC-like language using CUDA, (Compute Unified Device Architecture). In thesame time, a number of attractive features can be exploited for a broad classof intensive data parallel computation tasks. The final part of discussion outlines possible directionstowards future improvements of compression ratio and processing speed.

Anglický abstrakt

Thisarticle will present the details about the acceleration of 2D wavelet-basedmedical data (image) compression on MATLAB with CUDA. It is obvious that thediagnostic materials (mostly as a certain type of image) are increasinglyacquired in a digital format. Therefore, common need to daily manipulate hugeamount of data brought about the issue of compression within a very lessstipulated amount of time. Attention will be given to the accelerationprocessing flow which exploits the massive parallel computational power offered by the latest NVIDIA graphicsprocessor unit (GPU). It brings a compute device that can be programmed using aC-like language using CUDA, (Compute Unified Device Architecture). In thesame time, a number of attractive features can be exploited for a broad classof intensive data parallel computation tasks. The final part of discussion outlines possible directionstowards future improvements of compression ratio and processing speed.

Klíčová slova

GPU, CUDA, 2D wavelet transform, image compression, Matlab

Klíčová slova v angličtině

GPU, CUDA, 2D wavelet transform, image compression, Matlab

Autoři

ŠIMEK, V.

Rok RIV

2010

Vydáno

08.09.2008

Nakladatel

IEEE Computer Society

Místo

Liverpool

ISBN

978-0-7695-3325-4

Kniha

Proceedings 2nd UKSim European Symposium on Computer Modelling and Simulation

Strany od

274

Strany do

277

Strany počet

4

BibTex

@inproceedings{BUT32107,
  author="Václav {Šimek}",
  title="GPU Acceleration of 2D-DWT Image Compression in MATLAB with CUDA",
  booktitle="Proceedings 2nd UKSim European Symposium on Computer Modelling and Simulation",
  year="2008",
  pages="274--277",
  publisher="IEEE Computer Society",
  address="Liverpool",
  isbn="978-0-7695-3325-4"
}