Various arrangements for processing data sets using multiple processors are presented. A plurality of constraints may be received by a computer system. Each constraint may identify a data relationship that requires a subset of records of one or more data sets to be processed by a same processing device. A plurality of final constraints may be calculated. Each final constraint of the plurality of final constraints may be linked with a record. Each final constraint of the plurality of final constraints may be at least partially based on the plurality of constraints. Final constraints of the plurality of final constraints having a same value may be linked with records that are to be processed by the same processing device. At least partially based on the final constraint, the set of records may be distributed to a plurality of processing devices for processing.