Experiences of the GPU Thread Configuration and Shared Memory

DaeHwan Kim
Additional contact information
DaeHwan Kim: Department of Electronics Engineering, Suwon Science College, 288 Seja-ro, Jeongnam-myun, Hwaseong-si, Gyeonggi-do, Rep. of Korea

European Journal of Engineering and Technology Research, 2018, vol. 3, issue 7, 12-15

Abstract: Nowadays, GPU processors are widely used for general-purpose parallel computation applications. In the GPU programming, thread and block configuration is one of the most important decisions to be made, which increases parallelism and hides instruction latency. However, in many cases, it is often difficult to have sufficient parallelism to hide all the latencies, where the high latencies are often caused by the global memory accesses. In order to reduce the number of those accesses, the shared memory is instead used which is much faster than the global memory being located on a chip. The performance of the proposed thread configuration is evaluated on the GPU 960 processor. The experimental result shows that the best configuration improves the performance by 7.3 times compared to the worst configuration in the experiment. The experiences are also discussed for the shared memory performance when compared to that of the global memory.

Keywords: GPU; Performance; Thread; Shared Memory (search for similar items in EconPapers)
Date: 2018
References: Add references at CitEc
Citations:

Downloads: (external link)
https://eu-opensci.org/index.php/ejeng/article/view/60788 Abstract page (text/html)
https://eu-opensci.org/index.php/ejeng/article/download/60788/11920 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:epw:ejeng0:v:3:y:2018:i:7:id:60788

DOI: 10.24018/ejeng.2018.3.7.788

Access Statistics for this article

More articles in European Journal of Engineering and Technology Research from European Open Science
Bibliographic data for series maintained by Support ().