【摘要】 海洋数值模式当前已经成为海洋研究和预测的核心工具,其高分辨率。多物理过程的发展趋势对数值模式计算速度也提出了越来越高的要求。为了使得海洋数值模式更好的适应计算机基础架构,充分发挥现代化计算机体系的计算特点,提高计算效率,本文提出了一种简单易行且有效的代码现代化优化方案,并以MASNUM海浪模式为例进行了测试。首先利用诊断工具Intel Vtune Amplifier XE和Intel Trace Analyzer Collector,对模式的性能和负载均衡性进行了分析;之后,针对热点函数,在单节点上制定了4个优化步骤,包括编译器选项优化,串行和标量优化,向量化和OpenMP并行优化。结果表明,经过优化后,单节点内模式的计算速度可以提高1.95倍,多节点的模式强扩展性呈线性。这表明本文提出的代码现代化方案是一种行之有效的优化方法。更多还原

【Abstract】 Numerical model has become one of key tools for ocean research and prediction,and the demand for increasing the computational efficiency is now necessary and urgent.In order to make full use of the modern computer architecture and improve ocean model′s computational efficiency,a code optimization scheme,which is demonstrated by using MASNUM wave model as an example,was proposed in this paper.Firstly,Intel Vtune Amplifier XE and Intel Trace Analyzer Collector were used to evaluate the performance and load balancing of the MASNUM wave model.Then four steps of optimization,which are compiler options,serial and scalar optimization,vectorization,and MPI/OpenMP parallelization,are designed for hotspot function located by Intel Vtune Amplifier XE.The result shows that after optimization,the computational speed can be improved up to 1.95 times in a single node,and strong-scalability of the model is almost linear when computation is extended to multi nodes,suggesting that our code optimization is very effective.更多还原