2,443
个编辑
更改
跳到导航
跳到搜索
第92行：
第92行： − Due to the emergent nature of [[agent-based model]]s (ABMs), it is critical that the population sizes in the simulations match the population sizes of the dynamic systems being modelled.<ref>{{cite journal+ 第107行：
第107行： − 随着[[基于主体的模型]]（ABM）的兴起，在建模时，仿真中的总体大小与动态系统的总体大小相匹配是至关重要的。+ − However, the performance of contemporary agent simulation frameworks has been inadequate to handle such large population sizes and parallel computing frameworks designed to run on [[computing cluster]]s has been limited by available bandwidth. As computing power increases with [[Moore's law]], the size and complexity of simulation frameworks can be expected to increase. The team of R. M. D’Souza, M. Lysenko and K Rahmani from [[Michigan Technological University]] used a Sugarscape model to demonstrate the power of [[Graphics processing unit]]s (GPU) in ABM simulations with over 50 updates per second with agent populations exceeding 2 million.+ − 但是，现代主体仿真程序框架的性能不足以处理如此大的人口规模，并且设计为在计算集群上运行的并行计算框架受到可用带宽的限制。根据摩尔定律，随着计算能力的增加，仿真框架的规模和复杂度也会随之增加。来自密歇根理工大学的R. M. D’Souza, M. Lysenko and K Rahmani使用糖域模型来证明ABM仿真中的图形处理单元（GPU）每秒更新50多次，主体人数超过200万。<ref>{{cite journal
→SugarScape on steroids
===SugarScape on steroids===
===SugarScape on steroids===
随着[[基于主体的模型]]（ABM）的兴起，在建模时，仿真中的总体大小与动态系统的总体大小相匹配是至关重要的。<ref>{{cite journal
|last1=Gilbert
|last1=Gilbert
|first1=Nigel
|first1=Nigel
|pmid=12011398
|pmid=12011398
}}</ref>
}}</ref>
但是，现代主体仿真程序框架的性能不足以处理如此大的人口规模，并且设计运行计算集群的并行计算框架受到可用带宽的限制。根据摩尔定律，随着计算能力的增加，仿真框架的规模和复杂度也会随之增加。来自密歇根理工大学的R. M. D’Souza, M. Lysenko and K Rahmani使用糖域模型来证明ABM仿真中的图形处理单元（GPU）每秒更新50多次，主体人数超过200万。<ref>{{cite journal
|title=SugarScape on steroids: simulating over a million agents at interactive rates
|title=SugarScape on steroids: simulating over a million agents at interactive rates
|first1=Roshan M.
|first1=Roshan M.