Parallelization of graph labeling problem in multicore using OpenMP
R Muthuselvi, M. Muneeswari, K. Sudha, V. Vasantha · 2017 International Conference on Trends in Electronics and Informatics (ICEI) · 2017
Parallelization is the process used for reducing the time that provides an efficient result for the real time applications. Multicore architecture is a general purpose processor that consists of multiple cores on the same die and can execute programs simultaneously and parallelization can be applied effectively. Though the multiple cores are available in multicore architecture, only single core is utilized unless the programmer intervenes. It is very crucial to use the multiple cores effectively. There are many applications such as communication network addressing, X-Ray Crystallography, Radar Communication, Astronomy and Circuit design which use graph labeling problem for finding solutions. In real time, solving graph labeling problem is time consuming process when number of nodes is processed sequentially. In this work, parallelization is applied to the Graph labeling problem in multicore using OpenMP. It is found that CPU utilization is increased; speedup and execution time are reduced. After parallelization, the execution time is improved by 17.16s and CPU utilization is also improved by 50% on an average. Speedup is found to be 0.9888.