期刊文献+

基于Geant4的射线探测仿真并行化研究 被引量:2

Study on Parallel Computing of Radiation Detector Simulation Based on Geant4
下载PDF
导出
摘要 Geant4是一个用于粒子物理的大型蒙特卡罗仿真计算机模拟工具包。Geant4的并行化对于提高仿真效率具有重要意义。采用ParGeant4在Event层次上实现了射线探测器的并行化仿真,在多核处理器单机和PC集群上考察了并行化对计算效率的影响,并记录其运行时间与对应的串行算法仿真进行了比较。结果表明,采用ParGeant4并行化后的程序较串行程序效率明显提高,提高效率依赖于样本数量;而采用PC集群的并行化程序效率提高更加显著。 Geant4 is a large and highly accurate Monte Carlo simulation software package used in particle physics field.Parallel computing is special important due to the precision of Monte Carlo simulation depends on the sampling quantity.In order to study the efficiency and prospects of parallelization of Geant4,a ParGeant4 toolkit was used to parallel a simulation application of neutron detector,evaluate its calculation efficiency and compare it with the same simulation using serial algorithm from the point of the running time.All the simulation tasks were executed on Multicore Processors PC and PC cluster sequentially.Result shows that the parallel version is more efficient than the original serial program and the improvement is obvious when the sampling number is huge,PC cluster parallel can offer higher efficient than the single PC multi-process parallel one.
出处 《核电子学与探测技术》 CAS CSCD 北大核心 2011年第11期1237-1240,共4页 Nuclear Electronics & Detection Technology
基金 国家自然科学基金重点项目(10935005) 国家自然科学基金重点专项(11055002) 中央高校基本科研业务费研究专项(2010SCU23001)
关键词 GEANT4 ParGeant4 并行计算 主仆式并行化 Geant4 ParGeant4 Parallel computing Master–worker parallelism
  • 相关文献

参考文献1

二级参考文献3

  • 1[1]J F Briesmeister.MCNP-A General Monte Carlo NParticle Transport Code[R].New Mexico:Los Alamos national Laboratory,2000:185~186
  • 2[2]F B Brown,Yasunobu Nagaya.The MCNP5 Random Number Generator[R],New Mexico:Los Alamos national Laboratory,2002:1~3
  • 3[3]W Gropp,E Lusk,D Buntinas,et.al.MPICH2 User's Guide[R],Chicago:Arognne National Laboratory,2005:1~26

共引文献4

同被引文献14

引证文献2

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部