A Paralleled Large-Scale Astronomical Cross-Matching Function

Multi-wavelength data cross-match among multiple catalogs is a basic and unavoidable step to make distributed digital archives accessible and interoperable. As current catalogs often contain millions or billions objects, it is a typical data-intensive computation problem. In this paper, a high-efficient parallel approach of astronomical cross-match is introduced. We issue our partitioning and parallelization approach, after that we address some problems introduced by task partition and give the solutions correspondingly, including a sky splitting function HEALPix we selected which play a key role on both the task partitioning and the database indexing, and a quick bit-operation algorithm we advanced to resolve the block-edge problem. Our experiments prove that the function has a marked performance superiority comparing with the previous functions and is fully applicable to large-scale cross-match.