GPU-based cloud performance for LiDAR data processing

Goal of this paper is to compare the timing/performance results of CPU and GPU on local and Cloud platform for processing massive Light Detecting and Ranging (LiDAR) topographic data. We have used locally various multi-core CPU technologies as well as GPU implementations on various graphics cards of nVidia which support CUDA, where as a cloud computing infrastructure we utilized various components of the Amazon Web Services (AWS). In order to study the performance, we have developed and implemented vertex decimation algorithm for data reduction of LiDAR point cloud. Our presentation will demonstrate the preliminary results by comparing the multi-core CPU and GPU based implementations of the code, as well as the comparison with cloud performance.