Efficient implementation of communication software is of critical importance for high-speed networks. We analyze performance bottlenecks in existing implementations and propose two techniques for improvements: The first exploits parallelism not only in the actions of the FSMs, but also in the runtime system of the protocol stack. The second integrates adjacent layers leading to considerable savings in inter-layer interface handling and in the number of transitions occurring in the FSMs. Both techniques are discussed in the context of OSI upper layers, and are based on protocol specification in Estelle.
Dieser Eintrag ist Teil der Universitätsbibliographie.
Das Dokument wird vom Publikationsserver der Universitätsbibliothek Mannheim bereitgestellt.