New opportunities for processing the OSI-7 layer protocols using parallel processing (transputers).

Abstract

The attractiveness of the OSI-7 layer model is closely dependent upon a highly ambitious intent to promote a series of quasi-universal standards to coordinate the communication between heterogeneous applications, whatever the distributed architectures might be. However, a major criticism of the OSI-model is the performance and the handling of the presentation layer. This paper deals with the evaluation of parallel processing techniques operating at the upper levels of the OSI-model using transputers in a parallel co-processor. It is shown that the performance problem is highly dependent on the structure of the protocol stack and its implementation. With the object-oriented modularization of the protocol stack, an architecture of a possible co-processor using transputers is considered and its performance is considered adequate. An ideal configuration is briefly presented. A final performance appraisal of the parallelism effect is discussed with some insight into the future.