电信社群网络中介度的网格并行算法及调度算法

Grid Based Parallel and Schedule Algorithm for Betweenness Computation in Telecom Social Network Graph

为了解决电信社群网络中介度(图的一个几何量)计算中的海量计算问题,研究并实现了高性能网格并行计算方法.该算法采用层次性的二分法分割数据,能在较短的时间内完成大规模社群网络图各顶点中的介度计算.为了提高计算的加速比,提出了一种改进的网格并行调度算法,并采用动静态结合的方法来平衡负载.论证表明,改进算法的加速比、并行效率和平衡度都有提高,计算用时与网格上并行计算处理器数目成近似线形关系.

For betweeness computation in telecom social network graph with huge amount of data,a grid based parallel algorithm is presented.It adopts the hierarchic dichotomy of data.Meanwhile a new schedule strategy is proposed,that combines static and dynamic methods to reach load balance.The experimental results justified that the algorithm achieves a higher speedup ratio and the parallel efficiency,and the time consumption is approximately proportion to the number of parallel CPUs as well.