Incremental Connected Component Detection for Graph Streams on GPU

Studies on the real-time detection of connected components in graph streams have been carried out. The existing component method cannot process incrementally, and performance deteriorates due to frequent data transmission when GPU is used. In this paper, we propose a new incremental processing solve problems found methods for detecting GPUs. proposed minimizes amount be sent by determining subgraph affected stream update part recalculated. We consider number vertices quickly determine GPU. An asynchronous execution used shorten transfer time between CPU according changes. order show that provides fast GPU, evaluated its using various datasets.