This paper presents the design and implementation of the Generic Message Passing framework (GMP). The design of the GMP is guided by two goals: programmer productivity and run-time performance — particularly for parallel systems having both shared and distributed memory (e.g., clusters of SMPs). To achieve these goals simultaneously, the GMP uses a generic programming paradigm, allowing it to integrate seamlessly with modern generic libraries such as the C++ Standard Library. In addition the GMP presents a single parallel programming model, namely message passing. The implementation of the GMP fully exploits the architectural characteristics of its execution target for maximum run-time performance. Performance results are presented that demonstrate the effectiveness of the Generic Message Passing framework.