摘要
§1.引言
核禁试后,在美国加速战略创新计划(ASCI)的推动下,世界和我国在高性能并行计算机研制、并行计算方法和并行软件研制上均取得长足发展,每秒上万亿次的高性能计算机对一般的科研部门已经不是一种奢望,它们使得一大批过去无法求解的问题如今容易实现.
The particle transport Monte Carlo code MCNP had been realized the paral-lelization in MPI (Message Passing Interface) in 1999. But due to adopting the leap random number producer, some differences were existed between the parallel result and the serial result. Now the same results have been achieved by using the segment random number. The speedup of the applied problem is the liner ups to 53 in 64-processors and the parallel efficiency is up to 83% in 64-processors.
出处
《数值计算与计算机应用》
CSCD
北大核心
2003年第3期161-166,共6页
Journal on Numerical Methods and Computer Applications
基金
中国工程物理研究院基金
