CUDA-Acclerated SVM for Celestial Objects Classification

Peng, Nanbo

Recently, the developments in highly parallel Graphics Processing Units (GPUs) give us a new methold to solve advanced computation problems. We introduce an automated method called Support Vector Machine (SVM) based on Nvidia’s Compute Unified Device Architecture (CUDA) platform for classifying celestial objects. SVM have been proved a good algorithm for separating quasars from stars, but it takes a lof of time for training and predicting with large samples. Using the data adopted from the Sloan Digital Sky Survey (SDSS) Data Release Seven (DR7), CUDA-acclerated SVM shows achieving greatly improved speedups over commonly used SVM software running on a CPU. This approach is effective and applicable for quasar selection in order to compile an input catalogue for the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST).

Keywords: Graphics Processing Units (GPUs): Support Vector Machine (SVM): classification - quasars - stars

Return to poster list