Return to search

Software Design of A Sequential Loop Optimization Method on Data Locality

The gap between processor speed and memory access performance increases continuingly. In order to improve performance degradation due to memory accesses, we can reduce memory block accesses by improving data locality. In this research, we focus on optimizing data locality in loops. We adopt an iterative greedy algorithm. It iteratively perform loop fission and loop fusion by moving strongly-connected components among loops subject to data dependence constraints. It evaluates data locality change of each move and decide if accept such move. Subsequently loops can be improved gradually forward optimal result.

Identiferoai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0911108-205400
Date11 September 2008
CreatorsLuo, Yong-En
ContributorsChia-Hsiung Kao, Tsung Lee, Chih-Chien Chen
PublisherNSYSU
Source SetsNSYSU Electronic Thesis and Dissertation Archive
LanguageCholon
Detected LanguageEnglish
Typetext
Formatapplication/pdf
Sourcehttp://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0911108-205400
Rightswithheld, Copyright information available at source archive

Page generated in 0.0019 seconds