现行的采掘关联规则的并行算法基于经典的层次算法.该方法在每一次重复扫描数据库时都需要一次同步,这种同步运算对于共享内存多处理器并行机来说极大地降低了采掘性能,这种低效主要源于对共享的I/O通道的竞争.该文提出了在共享内存多处理机上采掘关联规则的异步算法APM.在APM中,所有参与计算的处理器能独立地产生备选集和计算支持度.而且,APM所需的扫描数据库的次数比层次方法所需的更少.该文还提出了一种增强APM的技术,使得该算法的性能对于数据分布更具有鲁棒性.文中实现了APM的变种算法,还实现了Apriori的并行版本Count Distribution算法.在SGI Power Challenge SMP并行机上,进行了性能分析,结果表明所提出的异步算法APM具有更好的性能和可扩展性.%All proposed parallel algorithms for mining association rules follow the conventional level-wise approach.It imposes a synchronization in every iteration in the computation which degrades greatly their performance if they are used to compute the rules on a shared-memory multi-processor parallel machine.The deficiency comes from the contention on the shared I/O channel when all processors are accessing the channel synchronously in every iteration.An asynchronous algorithm APM has been proposed for mining association rules on shared-memory multi-processor machine.All participating processors in APM generate candidates and count their supports independently without synchronization.Furthermore,it can finish the computation with fewer passes of database scanning than required in the level-wise approach.An optimization technique has been developed to enhance APM so that its performance would be insensitive to the data distribution.Two variants of APM and the synchronous algorithm Count Distribution,which is a parallel version of the popular serial mining algorithm Apriori,have been implemented on an SGI Power Challenge SMP parallel machine.The results show that the asynchronous algorithm APM performs much better,and is more scalable than the synchronous algorithm.
展开▼
