Faster catalog matching on Graphics Processing Units

One of the most fundamental problems in observational astronomy is the cross-identification of sources. Observations are made at different times in different wavelengths with separate instruments, resulting in a large set of independent observations. The scientific outcome is often limited by our ability to quickly perform associations across catalogs. The matching, however, is difficult scientifically, statistically as well as computationally. The former two require detailed physical modeling and advanced probabilistic concepts; the latter is due to the large volumes of data and the problem's combinatorial nature. In order to tackle the computational challenge and to prepare for future surveys we developed a new implementation on Graphics Processing Units. Our solution scales across multiple devices and can process hundreds of trillions of crossmatch candidates per second in a single machine.