On the scalability of parallel computations on a network of workstations (Q1288746)

Domain decomposition method is confirmed to be a useful parallel technique for parallel simulation. Mesh partition strategy together with a master/slave construction represents a natural way of doing parallel distributed computations. In this paper, we discuss parallel strategies for domain decomposition technique, the load balancing, the communication issue among the processors, and explain the mechanism of a limit to the speed-up when the problem size increases to a certain value. We also search for the way to enhance the speed up and the scalability.