Academic Journals Database
Disseminating quality controlled scientific knowledge

CUDA Based Performance Evaluation of the Computational Efficiency of the DCT Image Compression Technique on Both the CPU and GPU

Author(s): Kgotlaetsile Mathews Modieginyane | Zenzo Polite Ncube and Naison Gasela

Journal: Advanced Computing : an International Journal
ISSN 2229-726X

Volume: 4;
Issue: 3;
Start page: 1;
Date: 2013;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Compute Unified Device Architecture | Peak Signal to Noise Ratio | Graphical Processing Units | Discrete Cosine Transform | Computational Efficiency.

Recent advances in computing such as the massively parallel GPUs (Graphical Processing Units),coupledwith the need to store and deliver large quantities of digital data especially images, has brought a numberof challenges for Computer Scientists, the research community and other stakeholders. These challenges,such as prohibitively large costs to manipulate the digital data amongst others, have been the focus of theresearch community in recent years and has led to the investigation of image compression techniques thatcan achieve excellent results. One such technique is the Discrete Cosine Transform, which helps separatean image into parts of differing frequencies and has the advantage of excellent energy-compaction.This paper investigates the use of the Compute Unified Device Architecture (CUDA) programming modelto implement the DCT based Cordic based Loeffler algorithm for efficient image compression. Thecomputational efficiency is analyzed and evaluated under both the CPU and GPU. The PSNR (Peak Signalto Noise Ratio) is used to evaluate image reconstruction quality in this paper. The results are presentedand discussed.

Tango Rapperswil
Tango Rapperswil

RPA Switzerland

RPA Switzerland

Robotic process automation