In this paper, a novel hardware/software co-design architecture of Genetic-Algorithm (GA) driven Field Programmable Gate Array (FPGA) based decision making engine for cognitive radio is presented. Cognitive radio, which can greatly utilize the natural spectrum resource, is able to reconfigure the radio parameters according to environment change. The radio parameters defined by behavior encapsulated in the genes (frequency, modulation, power, bit error rate) of a chromosome. In our work, the modules of GA such as random number generator (RNG), Cross over, mutation are designed, synthesized using Verilog HDL. Only the fitness module implemented on NIOS processor using C. The complete design is simulated on ModelSim and implementation design targeted on ALTERA Cyclone II FPGA. By analyzing the results, the hardware/software co-design based GA yields a significant speedup over which implemented by software. This approach will attempt to increase data rate and minimize the transmission error, power consumption caused by external environment change. © 2013 IEEE.