A QUANTITATIVE STUDY OF PARALLEL SCIENTIFIC APPLICATIONS WITH EXPLICIT COMMUNICATION

This paper studies the behavior of scientific applications running on distributed memory parallel computers. Our goal is to quantify the Roa ring point, memory, I/O, and communication requirements of highly para llel scientific applications that perform explicit communication. In a ddition to quantifying these requirements for fixed problem sizes and numbers of processors, we develop analytical models for the effects of changing the problem size and the degree of parallelism for several o f the applications. The contribution of our paper is that it provides quantitative data about real parallel scientific applications in a man ner that is largely independent of the specific machine on which the a pplication was run. Such data, which are clearly very valuable to an a rchitect who is designing a new parallel computer, were not previously available. For example, the majority of research papers in interconne ction networks have used simulated communication loads consisting of f ixed-size messages. Our data, which show that using such simulated loa ds is unrealistic, can be used to generate more realistic communicatio n loads.