Decomposition of natural join based on domain-interval fragmented column indices

The paper describes decomposition of natural join relational operator based on the column indices and domain-interval fragmentation. This decomposition admits parallel executing the resource-intensive relational operators without data transfers. All column index fragments are stored in main memory in compressed form to conserve space. During the parallel execution of relational operators, compressed index fragments are loaded on different processor cores. These cores unpack fragments, perform relational operator and compress fragments of partial result, which is a set of keys. Partial results are merged in the resulting set of keys. DBMS use the resulting set of keys for building the resulting table. Described approach allows efficient parallel query processing for very large databases on modern computing cluster systems with many-core accelerators. A prototype of the DBMS coprocessor system was implemented using this technique. The results of computational experiments are presented. These results confirm the efficiency of proposed approach.