Parallel Optimization of IDW Interpolation Algorithm on Multicore Platform
Due to increasing power consumption,heat dissipation,and other physical issues,the architecture of central processing unit (CPU) has been turning to multicore rapidly in recent years.Multicore processor is packaged with multiple processor cores in the same chip,which not only offers increased performance,but also presents significant challenges to application developers.As a matter of fact,in GIS field most of current GIS algorithms were implemented serially and could not best exploit the parallelism potential on such multicore platforms.In this paper,we choose Inverse Distance Weighted spatial interpolation algorithm (IDW) as an example to study how to optimize current serial GIS algorithms on multicore platform in order to maximize performance speedup.With the help of OpenMP,threading methodology is introduced to split and share the whole interpolation work among processor cores.After parallel optimization,execution time of interpolation algorithm is greatly reduced and good performance speedup is achieved.For example,performance speedup on Intel Xeon 5310 is 1.943 with 2 execution threads and 3.695 with 4 execution threads respectively.An additional output comparison between pre-optimization and post-optimization is carried out and shows that parallel optimization does to affect final interpolation result.
multicore processor parallel optimization IDW interpolation OpenMP
Xuefeng Guan Huayi Wu
State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,129 Luoyu Road,Wuhan 430079,P.R.China
国际会议
第16届国际地理信息科学与技术大会(16th International Conference on GeoInformatics and the Joint Conference)
广州
英文
2008-06-28（万方平台首次上网日期，不代表论文的发表时间）