ACM Computing Surveys (CSUR)
| Hi-index | 0.00 |
This paper presents the current results of an investigation into the design of shared resource computing systems. A general and highly flexible system organization is described which incorporates great potential for fault tolerance. Some of the operating system functions required by such a system are sketched and the question of efficiently exploiting concurrency within a single job is addressed. A user environment is described in which the type of system outlined provides an economically attractive alternative to present approaches. A major goal of the current investigation is to better define shared resource organizations and the environments in which their use can be justified on grounds of efficiency and reliability.