Vectorization query processing method for CPU and GPU platforms

The invention relates to a vectorization query processing method for CPU and GPU platforms, and the method comprises the following steps: S1, dividing a data column of a fact table in a database into a plurality of vector fragments, and distributing each vector fragment into a corresponding thread; S2, generating dimension vectors for the query command SQL, and forming a grouping cube by all the dimension vectors; S3, carrying out vector connection operation on the vector fragments corresponding to the foreign key columns of the fact table and the dimension vectors to obtain address components recorded in the corresponding grouping cubes by the fact table, and recording the address components in corresponding positions of the vector indexes; S4, generating a grouping vector based on the grouping cube, accessing vector fragments of the measurement data corresponding to the fact table according to a non-null value of the vector index, performing aggregation calculation on the vector fragments, and mapping an ag