Effects of Multicore Distributed Memory Systems on Parallel Processing Applications

Complex problems need a longtime to be solved, with low efficiency and performance. Hence, to overcome these drawbacks, the approach of breaking the problem into independent parts and treating each part individually in the way that each processing element can execute its part of the problem simultaneously with the others. The systems that contain many computing elements combined. Parallel processing (PP) is divided into three types; shared, distributed, and hybrid memory systems are usually adopted. The aim of this research is to point out the effects of multicore distributed memory systems on PP applications that can reduce the total execution time of the programs. In this work, distributed- and shared-memory systems addressed depends on client/servers principles. However, to get the exact evaluation of our aim, just one client and one server have been depended. The algorithm used here is capable of calculating: The started, consumed, and terminated for CPU and total execution times, CPU usage of servers, and CPU and Total execution times for the client. The results compared with previous works depending on distributed memory systems, to overcome the previous drawbacks taking in the consideration the effects of multi-core processor. All of these algorithms are implemented using Java Language.