Running code on 16-core in parallella

Dears,
My graduation project on parallella and the main target of using parallella is optimization in time and power , now i have a code " modulation communication system block code " and i want to run this code into 16-core in parallel to optimize the time , i have tried to write 16 epiphany code every code run part of modulation block it it take more time to load 16 srec file onto 16 core .
any suggestions can help me please, ?
Thanks in Advance.
My graduation project on parallella and the main target of using parallella is optimization in time and power , now i have a code " modulation communication system block code " and i want to run this code into 16-core in parallel to optimize the time , i have tried to write 16 epiphany code every code run part of modulation block it it take more time to load 16 srec file onto 16 core .
any suggestions can help me please, ?
Thanks in Advance.