Scalable time definite integration in parallel computing

Abstract

In parallel computing, the memory requirement is an important problem, and in parallel software development, it is vital to optimize the memory management strategy. Programmers need to know the memory optimizing degree. But, the parallel programs' performance evaluation metric speedup only refers to computing time, without considering the memory cost when executing programs. In this paper, the relationship between computing time and memory requirement is expressed by a formula, with which the influence of memory requirement in parallel computing can be calculated. The experiment results demonstrate that the scalable time definite integration proposed in this paper, can properly predict parallel computing time under certain parallel system size, and also could reflect the operating environment's working capacity.