可视化并行编程平台中进程拓扑图的自动调整

并行计算技术的发展促进了并行可视化编程平台的出现,但众多的平台侧重于并行程序的生成、编译和调试而忽略了与用户的交互。针对众多可视化编程平台中复杂进程拓扑图调整困难的问题,在图形化抽象的基础上,提出了对立边的概念,通过建立位置约束和调整约束关系来设计进程拓扑图的自动调整策略,并在自主开发的并行可视化编程平台上予以实现,通过实例证明此策略的有效性和可行性。

基于MPI的Jacobi迭代算法的并行化

Jacobi迭代算法是解线性方程组的最常用的方法,具有广泛的应用。Jacobi迭代属于计算密集型[1],将并行计算技术应用到Jacobi迭代中,具有重要的意义。通过使用消息传递编程模型mpi提供的向量数据类型和虚拟进程拓扑来实现Jacobi迭代的并行化。

Topological spaces via phenotype--genotype spaces

Researchers hope that establishing a notion of proximity using topology will help to clarify the biological processes underlying the evolution of living organisms. The simple model presented here, using RNA shapes, can carry over to more general and complex genotype-phenotype systems. Proximity is an important component of continuity, in both real-world and topological terms. Consequently, phenotype spaces provide an appropriate setting for modeling and investigating continuous and discontinuous evolutionary change.