We are currently doing experimentations to compare applications with our prototype to applications using classical message-passing communications between processors. The first results, on small applications of matricial computing, show little difference of execution time. Usually the application using DOSMOS takes more time than the same application with message-passing communications (1.4 time more). But the applications using DOSMOS are much easy to write because all communications and data locations are hidden to the user. By the way, these applications are portable (they look like sequential version) and more reliable because the system manages all the communications. PVM has permitted an easy implementation of our system on network of stations. But in the future we want to take advantage of its portability, to install DOSMOS on a massively parallel machine, in order to validate the scalability of the approach.