A method and system to optimize throughput of executable program code are provided. The system comprises a profiler to receive a representation of a plurality of functions, an aggregator, and a mapper to map the plurality of aggregates to a plurality of processors. The aggregator may be configured to create an aggregate for each function from the plurality of functions thereby creating a plurality of aggregates, choose an optimization action between grouping and duplication based on the number of aggregates in the plurality of aggregates, the number of available processing elements (PEs), and execution time of each aggregate, and perform the chosen optimization action.