Client server computing on message passing systems: Experiences with PVM-RPC The relationship between client-server distributed computing and message-passing parallel processing is explored in this work through an experimental RPC framework for the PVM system. The project investigates the potential for RPC to complement asynchronous message passing in PVM -- both to expand the domain of applications, and to evaluate the effectiveness of client-server computing for traditional scientific and numerical problem solving. Our design is intuitive and straightforward, and enables servers and clients to be developed with a minimum of additional effort in terms of programming and logistics. Our experiences with early implementations of PVM-RPC indicate that the client-server model is reasonably compatible with message passing and scientific algorithms, and furthermore, that the RPC layer introduces little if any performance overhead into message passing systems. Furthermore, support for simple versions of useful features such as transparent failure resilience and automatic load balancing are facilitated in this model.
Keywords for this software
References in zbMATH (referenced in 5 articles , 1 standard article )
Showing results 1 to 5 of 5.
- Lou, Der-Chuyan; Wu, Chia-Long; Ou, Rong-Yi: Application of parallel virtual machine framework to the strong prime problem (2002)
- Shyu, Shyong-Jian; Lin, B. M. T.: An application of parallel virtual machine framework to film production problem (2000)
- Annamalai, V.; Krishnamoorthy, C. S.; Kamakoti, V.: Adaptive finite element analysis on a parallel and distributed environment (1999)
- Krantz, A. T.; Sunderam, V. S.: Client server computing on message passing systems: Experiences with PVM-RPC (1997)
- Sunderam, Vaidy: Heterogeneous network computing: The next generation (1997)