Using Naming Strategies to Make Massively Parallel Systems Work

To handle massively parallel systems and make them usable, an adaptive, application-oriented operating system is required. The application orientedness is represented by the family concept of parallel operating systems. Incremental loading of operating system services supports the family character by automatically extending the system's active object structure when it is necessary. This way, also the switching between different operating system family members may be realized. A new active object will be incrementally loaded if its invocation fails because it does not yet exist. This is noticed during object binding while using the naming services. The use of the naming system is exploited and extended to get a flexible and configurable mechanism for triggering incremental loading. This mechanism is built by the freely definable naming strategies and exceptions that result again in a family, namely a family of naming services.

PROGRAMMING TOOLS FOR PARALLEL COMPUTERS

Although software tools already have a place on serial and vector computers they are becoming increasingly important for parallel computing. Message passing libraries, parallel operating systems and high level parallel languages are the basic software tools necessary to implement a parallel processing program. These tools up to now have been specific to each parallel computer system and a short survey will be given. The aim of another class of software tools for parallel computers is to help in writing or rewriting application programs. Because automatic parallelization tools are not very successful, an interactive component has to be incorporated. We will concentrate here on the discussion of SPEFY, a parallel program development facility.