GWMA: the parallel implementation of woodpecker mating algorithm on the GPU
Jianhu Gong, Morteza Karimzadeh Parizi
Abstract
The Woodpecker Mating Algorithm (WMA) is a new metaheuristic algorithm (MA) with high efficiency in solving optimization problems. Nevertheless, WMA needs many search agents to explore the problem space when handling complex problems, resulting in a long computational time. This paper focuses on the acceleration of WMA for solving optimization problems with parallelization in the graphics processing unit (GPU) to improve the speedup and decrease the execution time of the WMA, thereby retaining the quality of the optimal outcomes. The proposed algorithm provides various mechanisms for generating random factors on the host system, bulk transfer of these factors to the GPU, parallel initialization and evaluation of the initial population on GPU, updating and evaluating the search agents’ position. It also uses a decreasing mechanism to determine the best agent. The comparative evaluations of the parallel and serial WMA are based on a classical benchmark and CEC2017 test functions. In addition, the execution time of the GWMA is measured by other parallel MAs to represent the speed of the GWMA. The ultimate outcomes prove that the GWMA is run about 10–82 times quicker than the sequential WMA. Also, the GWMA is faster than other parallel algorithms in solving optimization problems.