Change search
ReferencesLink to record
Permanent link

Direct link
Linköping University, Department of Computer and Information Science. Linköping University, The Institute of Technology.
2014 (English)Independent thesis Basic level (university diploma), 10,5 credits / 16 HE creditsStudent thesisAlternative title
A study on GPGPU-Sim (English)
Abstract [en]

This thesis studies the impact of hardware features of graphics cards on performance of GPU computing using GPGPU-Sim simulation software tool. GPU computing is a growing topic in the world of computing, and could be an important milestone for computers. Therefore, such a study that seeks to identify the performance bottlenecks of the program with respect to hardware parameters of the devvice can be considered an important step towards tuning devices for higher efficiency.

In this work we selected convolution algorithm - a typical GPGPU application - and conducted several tests to study different performance parameters. These tests were performed on two simulated graphics cards (NVIDIA GTX480, NVIDIA Tesla C2050), which are supported by GPGPU-Sim. By changing the hardware parameters of graphics card such as memory cache sizes, frequency and the number of cores, we can make a fine-grained analysis on the effect of these parameters on the performance of the program.

A graphics card working on a picture convolution task releis on the L1 cache but has the worst performance with a small shared memory. Using this simulator to run performance tests on a theoretical GPU architecture could lead to better GPU design for embedded systems.

Place, publisher, year, edition, pages
2014. , 30 p.
Keyword [en]
GPGPU-Sim, Simulator, GPU computing
National Category
Other Engineering and Technologies not elsewhere specified
URN: urn:nbn:se:liu:diva-112574ISRN: LITH-IDA/LITH-EX-G--14/085--SEOAI: diva2:768349
Subject / course
Computer Engineering
Available from: 2014-12-08 Created: 2014-12-03 Last updated: 2014-12-08Bibliographically approved

Open Access in DiVA

fulltext(252 kB)330 downloads
File information
File name FULLTEXT01.pdfFile size 252 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Andersson, Filip
By organisation
Department of Computer and Information ScienceThe Institute of Technology
Other Engineering and Technologies not elsewhere specified

Search outside of DiVA

GoogleGoogle Scholar
Total: 330 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 446 hits
ReferencesLink to record
Permanent link

Direct link