Astrophysical data mining with GPU. A case study: genetic classification of globular clusters

TL;DR

This paper introduces a GPU-accelerated genetic algorithm for astrophysical data mining, specifically for classifying globular clusters, achieving significant speedups over CPU implementations.

Contribution

The paper presents a GPU-based implementation of a genetic algorithm for astrophysical data analysis, enabling faster processing and integration into a public web data mining platform.

Findings

200x speedup in training phase with GPU implementation

Successful detection of globular cluster candidates in HST images

Integration into a web-based data mining service

Abstract

We present a multi-purpose genetic algorithm, designed and implemented with GPGPU / CUDA parallel computing technology. The model was derived from our CPU serial implementation, named GAME (Genetic Algorithm Model Experiment). It was successfully tested and validated on the detection of candidate Globular Clusters in deep, wide-field, single band HST images. The GPU version of GAME will be made available to the community by integrating it into the web application DAMEWARE (DAta Mining Web Application REsource (http://dame.dsf.unina.it/beta_info.html), a public data mining service specialized on massive astrophysical data. Since genetic algorithms are inherently parallel, the GPGPU computing paradigm leads to a speedup of a factor of 200x in the training phase with respect to the CPU based version.