الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 9 |  |  |
| | | from | 9 | | |
Abstract
It is well known that parallel computing is one of the important ways of achieving high performance computing applications, in which multiple computer resources are used simultaneously to reduce the running time of these applications. Measuring the quality of randomness of a given sequence is a crucial problem that significantly affects the quality of many practical applications such as computer simulation, distributed algorithms, communications industry, and cryptography. In the first part of this thesis, we study classical Poker test, one of the most popular approaches for testing randomness, in parallel. In particular, we design classical Poker test programs using MATLAB, C++ language, and OpenMP. Motivated by the above applications, we develop and implement the classical Poker test in parallel with MATLAB using MEX-file with one, two, three and four threads which reducing the execution time of the test. This encourages us to apply Poker method for testing randomness using parallel MATLAB with OpenMP which speeds up the test. Over the last few decades, several stochastic algorithms have been proposed to solve the job-shop scheduling problems (JSSPs). The classical JSSP is one of the most important and difficult problems in the field of production scheduling (it is NP-hard problem). In the second part of this thesis, we study and implement an optimization algorithm, called Particle Swarm Optimization (PSO), using parallel MATLAB for solving JSSPs. The performance of PSO algorithm is evaluated in comparison with a number of benchmark instances. The results indicate that the running time of the parallel PSO algorithm is significantly less than that of the serial PSO algorithm.