A database coprocessor for high-performance cluster computing systems with many-core accelerators is described. This coprocessor uses distributed columnar indexes with interval fragmentation. The operation of the coprocessor engine is considered by an example of natural join processing. The parallel decomposition of natural join operator is performed using distributed columnar indexes. The proposed approach allow one to perform relational operators on computing clusters without massive data exchange. The results of computational experiments on Intel Xeon Phi confirm the efficiency of the developed methods and algorithms.

Keywords: columnar data representation, columnar indexes, database coprocessor, interval fragmentation, parallel database system, cluster computing systems with many-core accelerators, Intel Xeon Phi.

• PDF (Full text in Russian, References in English)   (603KB)



• PDF. zip (Full text in Russian, References in English)   (549KB)