Optimizacija metode za kompresiju slikovnih podataka bez gubitaka pomoću grafičkog podsustava

undergraduate thesis

• Title (english): Optimization of Lossless Image Compression Method for GPGPU
• Author: Luka Strižić
• Mentor: Josip Knezović (mentor)
• Committee member: Josip Knezović (predsjednik povjerenstva)
• Committee member: Igor Čavrak (član povjerenstva)
• Committee member: Ivana Bosnić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Energetska učinkovitost postaje sve važnije u potrošačkoj elektronici, zato je cilj ovog rada usporediti energetsku učinkovitost, kao i vrijeme izvršavanja, CBP implementacije na procesoru i grafičkom podsutavu, koristeći CUDA-u za potonje. Testovi su provedeni koristeći komponente srednje klase u stolnom računalu i komponente visoke klase u serveru. One su uključivale Intel i3-4130, Intel Xeon E5-2620, nVidia GTX 750 Ti i nVidia GTX 980. CUDA verzija se pokazala kao energetski učinkovitija i brža nasprem jednodretvene procesorske izvedbe, međutim, potrebna su daljnja testiranja koja bi usporedila optimiziranu CUDA i višedretvenu procesorsku implementaciju, da se pokrije cijeli spektar. U svakom slučaju, hardver srednje klase je energetski učinkovitiji od hardvera visoke klase.

Abstract (english)

Power efficiency is becoming increasingly important in consumer electronics, which is why the aim of this thesis was to compare power efficiency, as well as execution time, of a Classification and Blending Prediction implementation on a CPU and a GPU, using CUDA for the latter. Test were conducted using mainstream components in a desktop PC and high end components in a server. They included Intel i3-4130, Intel Xeon E5-2620, nVidia GTX 750 Ti and nVidia GTX 980. The CUDA version proved to be both more efficient and faster than a singlethreaded CPU version, however, further tests should be done comparing optimized CUDA versus multithreaded CPU implementation to cover the whole spectrum. In any case, mainstream hardware is more energy efficient than high end hardware.

• Keywords: računalstvo opće namjene na grafičkom podsusavu; GPGPU; Compute Unified Device Architecture; CUDA; Classification and Blending Prediction; CBP; kompresija slika bey gubitaka
• Keywords (english): General-Purpose Computing on Graphics Processing Units; GPGPU; Compute Unified Device Architecture; CUDA; Classification and Blending Prediction; CBP; Lossless Image Compresion
• Language: english
• URN:NBN: urn:nbn:hr:168:971276
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 12:08:46