Distributed computing applications rely on transmissions of messages between processes. However, as workstations are not intended to manage this kind of communications, it is necessary to use some communication tools known as message passing libraries. Currently, MPI (Message Passing Interface) and PVM (Parallel Virtual Machine) are the most used. In addition, the need for interoperability among the rapidly proliferating amount of hardware and software led to the definition of CORBA (Common Object Request Broker Architecture), which standardizes the execution support of distributed object applications. This architecture offers good interoperability and encapsulation support. Moreover, its method invocation mechanism, offers several features and can be used as a good communication model. Consequently, the use of such an architecture for distributed and grid computing applications seems interesting and promising. However, CORBA is always criticized on the performance level. By taking account of all these elements, a performance evaluation of CORBA seems necessary. The aim of the paper is to present benchmark results of some CORBA implementations (ORBacus and TAO) and to compare them with those of the two message passing libraries MPI (MPICH and LAM) and PVM, by using a Network of WorkStations (NOW).

Parallelism and concurrency have long been considered as non essential during the cursus of the average programmer. However, thanks to technological advances, new promising forms of parallel computing are now appearing, e.g. "network computing", which are inexpensive and easy to use.In this paper, we present new points to focus on when teaching parallel computing, in addition to the basic principles of it, to let students be aware of problems that often arise when implementing parallel algorithms on this new architecture. Besides, we experimented a different type of exam mainly based on an exercise that had to be solved stepwise, putting the engineering students in a situation which is similar to their future job.