High-performance polyline intersection based spatial join on GPU-accelerated clusters

Abstract

The rapid growing volumes of spatial data have brought significant challenges on developing high-performance spatial data processing techniques in parallel and distributed computing environments. Spatial joins are important data management techniques in gaining insights from large-scale geospatial data. While several distributed spatial join techniques based on spatial partitions have been implemented on top of existing Big Data systems, they are not capable of natively exploiting massively data parallel computing power provided by modern commodity Graphics Processing Units (GPUs). In this study, as an important component of our research initiative in developing high-performance spatial join techniques on GPUs, we have designed and implemented a polyline intersection based spatial join technique that is capable of exploiting massively data parallel computing power on GPUs. The proposed polyline intersection based spatial join technique is integrated into a customized lightweight distributed execution engine that natively supports spatial partitions. We empirically evaluate the performance of the proposed spatial join technique on both a standalone GPU-equipped workstation and Amazon EC2 GPU-accelerated clusters and demonstrate its high performance when comparing with the state-of-the-art.