one of the big advantages of FPGA's is the ability to have simple operations performed in a regular fashion, and with many units.
for example, an FIR filter could make use of 64 multiply-add units (for modern fpgas), and accept new input at 350MSPS (1 new input per clock cycle). Because the operation is fixed, there is no need to have any overhead or coordination from a microprocessor.
the coregen outputs have the advantage that they can be used as needed, usually in large numbers.
In the above, the FIR filter would be possible of significantly higher performace, at the cost of FPGA area. The microprocessor can do anything, as long as it is given enough time.