Performance Estimation of a BOINC-Based Desktop Grid for Large-Scale Molecular Docking.

This paper addresses the performance evaluation of a heterogeneous distributed computing environment (Desktop Grid) for large-scale medicinal chemistry experiments in silico. Dynamic change of the set of computational nodes, their heterogeneity and unreliability impose difficulties on task scheduling and algorithm scaling. We analyze the performance, provide efficiency metrics, statistics and analysis of the volunteer computing project SiDock@home.