Marine bathymetry processing through GPGPU virtualization in high performance cloud computing

摘要

Fast technology development has influenced the widespread use of low-power devices in differentscientific, environmental, and everyday life areas, giving birth to the Internet of Things.In this paper, we focus on the context of marine studies, addressing the problem of marinebathymetry data processing and analysis via pervasive and Internet-connected sensors andlow-power distributed devices.Pervasiveand Internet-connectedlow-powerdevices (as the componentsinvolved in the sensing and processing actions) made diverse and different “things” asa worldwide-distributed system. Given the high complexity of the algorithms involved in thesestudies, which usually involve general-purpose graphic processing unit (GPGPU)computation, it isimpossible for the limited devices to perform the required calculations. To overcome these limitations,in this paper, we propose and implement a vertical application of GVirtuS, the open-sourceGPGPU virtualization and remoting service, for achieving high performance geographical datainterpolation in a high performance cloud computing scenario.We present an innovative implementationby comparing, in terms of performance and accuracy, the inverse distance weightingand kriging interpolation methods in their parallel implementations leveraging on CUDA-enabledGPGPUs.We present a real-world use case related to high-resolution bathymetry interpolationin a crowdsource data context in the Bay of Pozzuoli, Italy.