设计并实现了一种基于高性能计算集群的并行关联规则挖掘方法.该算法采用分离的策略仅需对本地数据库进行一次访问,能有效降低I/O开销,同时利用MPI/OpenMP混合编程模式,最大限度降低数据在网络上的通信开销.在普通PC搭建的高性能计算集群的实验结果证明:基于高性能计算集群的关联规则算法效率较高,具有较好的加速比.
We design and implement a parallel association rules mining method based on high-performance computing clusters(HPC clusters) .The algorithm adopts the separation strategy to simply visit a local database only once , thus ,the inter-processor communication I/O overhead is reduced .What’s more ,that using MPI/OpenMP hybrid programming mode can minimize data communication overhead on the network .By using ordinary PC structures , HPC cluster experimental results verify that the proposed algorithm based on HPC offers higher efficiency and has a good speedup .