Parallel Computational Modelling of Inelastic Neutron Scattering in Multi-node and Multi-core Architectures
Parallel Computational Modelling of Inelastic Neutron Scattering in Multi-node and Multi-core Architectures
复制标题
DOI：
10.1109/hpcc.2010.45
复制
发表时间：
2010-09
期刊：
影响因子：
--
通讯作者：
Michael T. Garba;H. González-Vélez;D. L. Roach
中科院分区：
文献类型：
--
作者：
Michael T. Garba;H. González-Vélez;D. L. Roach
本文探讨了初始并行实现的散射，计算密集型非弹性中子散射程序与多晶平均能力，通用格子程序（GULP）。特别重要的原子尺度上的结构调查，这项工作确定了相关的并行实现的SCATTER的计算功能，并提出了初步的结果，从多核和多节点环境的性能测试。我们最初的方法表现出近线性的可扩展性高达256 MPI进程的一个重要的模型。
This paper examines the initial parallel implementation of SCATTER, a computationally intensive inelastic neutron scattering routine with polycrystalline averaging capability, for the General Utility Lattice Program (GULP). Of particular importance to structural investigation on the atomic scale, this work identifies the computational features of SCATTER relevant to a parallel implementation and presents initial results from performance tests on multi-core and multi-node environments. Our initial approach exhibits near-linear scalability up to 256 MPI processes for a significant model.