Large-Scale Spatial Data Processing on GPUs and GPU-Accelerated Clusters

The General Purpose computing on Graphics Processing Units (GPGPUs) techniques represent a significantly different parallel computing scheme than the MapReduce/Hadoop based ones that are currently adopted by mainstream Big Data systems. The massive data parallel computing power provided by inexpensive commodity GPUs makes large-scale spatial data processing on GPUs and GPU-accelerated clusters attractive from both a research and practical perspective. In this article, we report our work on data parallel designs of spatial indexing, spatial joins and several other spatial operations, such as polygon rasterization, polygon decomposition and point interpolation. The data parallel designs are further scaled out to distributed computing nodes by integrating single-node GPU implementations with High-Performance Computing (HPC) toolset and the new generation in-memory Big Data systems such as Cloudera Impala. In addition to introducing GPGPU computing background and outlining data parallel designs for spatial operations, references to individual works are provided as a summary chart for interested readers to follow more details on designs, implementations and performance evaluations